> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.runtype.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.runtype.com/_mcp/server. # Execute a flow or agent POST https://api.runtype.com/v1/dispatch Content-Type: application/json Main dispatch endpoint for flow and agent execution with record resolution. Supports streaming via SSE or synchronous JSON responses. Send the RFC 7240 `Prefer: respond-async` header to receive a durable execution handle immediately, then poll its status URL for completion. A saved agent may run on the durable session lane; the admission headers `x-runtype-concurrency` (reject, supersede, queue, steer), `x-runtype-coalesce` (true) and `idempotency-key` then apply exactly as on `POST /v1/agents/{id}/execute`, and are ignored for in-process execution except steer, which fails explicitly on unsupported lanes. `x-runtype-concurrency: auto` sends the same user-message deltas as steer and lets a classifier choose: while a turn runs, a message that belongs to it steers and an independent one queues as the next turn; with nothing running it is an ordinary turn with no route report. A routed or downgraded answer carries `X-Runtype-Busy-Message-Route` (steer or queue) and `X-Runtype-Busy-Message-Source` (classifier, shadow, abstained, timeout, error, unanswered, circuit\_open, or disabled), plus `X-Runtype-Busy-Message-Probability` and `X-Runtype-Busy-Message-Model` when the classifier answered; JSON bodies repeat them as `busyMessageRoute`. Where auto cannot route (in-process execution, stored history, a flow, no conversationId, coalesce, Prefer: respond-async) it keeps the default admission and reports source `disabled`. Any other x-runtype-concurrency value is refused with 400 INVALID\_CONCURRENCY\_MODE. Steer accepts only new user-message deltas, preserves the active execution configuration and authority, and returns a deliveryId with a deliveryStatusUrl. Prefer: respond-async with steer returns a native delivery receipt without queuing an HTTP replay. Reference: https://docs.runtype.com/api-reference/runtype-api/dispatch/execute-a-flow-or-agent ## Authentication - `Authorization` header (bearer token, required) — API key or Clerk session token ## Servers - `https://api.runtype.com` (Production, default) - `https://api.runtype-staging.com` (Staging) ## Request ### Body (application/json) This endpoint expects a Dispatch_executeAFlowOrAgent_Request. - `Dispatch_executeAFlowOrAgent_Request` - DispatchExecuteAFlowOrAgentRequest0 - DispatchExecuteAFlowOrAgentRequest1 ## Response ### 200 Execution result (SSE stream or JSON) - Streaming response of `ExecutionStreamEvent`. - ExecutionStreamEvent0 - ExecutionStreamEvent1 - ExecutionStreamEvent2 - ExecutionStreamEvent3 - ExecutionStreamEvent4 - ExecutionStreamEvent5 - ExecutionStreamEvent6 - ExecutionStreamEvent7 - ExecutionStreamEvent8 - ExecutionStreamEvent9 - ExecutionStreamEvent10 - ExecutionStreamEvent11 - ExecutionStreamEvent12 - ExecutionStreamEvent13 - ExecutionStreamEvent14 - ExecutionStreamEvent15 - ExecutionStreamEvent16 - ExecutionStreamEvent17 - ExecutionStreamEvent18 - ExecutionStreamEvent19 - ExecutionStreamEvent20 - ExecutionStreamEvent21 - ExecutionStreamEvent22 - ExecutionStreamEvent23 - ExecutionStreamEvent24 - ExecutionStreamEvent25 - ExecutionStreamEvent26 - ExecutionStreamEvent27 - ExecutionStreamEvent28 - ExecutionStreamEvent29 - ExecutionStreamEvent30 - ExecutionStreamEvent31 - ExecutionStreamEvent32 - ExecutionStreamEvent33 - ExecutionStreamEvent34 - ExecutionStreamEvent35 - ExecutionStreamEvent36 - ExecutionStreamEvent37 ### 202 Durable fire-and-forget handle accepted via `Prefer: respond-async`. Poll statusUrl for completion. Carries a `Preference-Applied: respond-async` header. - Streaming response of `AsyncDispatchHandle`. - `executionId` (string, required) — The durable execution handle — poll with this. - `status` (enum, required) — Host lifecycle at acceptance or idempotent delivery replay. - Allowed values: `queued`, `running`, `paused`, `completed`, `failed`, `cancelled`, `interrupted` - `statusUrl` (string, required) — Relative URL for polling this execution. - `targetKind` (enum, required) — Kind of execution target. - Allowed values: `flow`, `agent` - `accepted` (boolean, optional) - `busyMessageRoute` (BusyMessageRouteReport, optional) - `claudeManagedAgentId` (string, optional) — Present only for ephemeral inline-create dispatch. - `conversationId` (string, optional) — Conversation id, when the request belongs to a conversation. - `deliveryId` (string, optional) — Stable input-delivery identity, distinct from the host execution. - `deliveryStatus` (enum, optional) - Allowed values: `pending`, `applied`, `settled`, `not_applied` - `deliveryStatusUrl` (string, optional) — Poll this receipt to distinguish pending, applied, settled, and not-applied input. - `eventsUrl` (string, optional) - `targetId` (string, optional) — Saved flow or agent id, when known. ## Errors ### 400 Bad Request Error Validation error - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 401 Unauthorized Error Unauthorized - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 402 Payment Required Error Payment required - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 403 Forbidden Error Insufficient permissions - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 404 Not Found Error Saved flow not found (FLOW_NOT_FOUND), a version selector that names no pointer (alias_not_found, alias_archived, alias_expired, version_not_found), or a saved agent with no runnable live version (AGENT_NOT_DEPLOYED) - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 409 Conflict Error The durable conversation is busy (CONVERSATION_BUSY names the occupant execution and its phase; honor Retry-After or send x-runtype-concurrency: steer) - `code` (enum, required) - Allowed values: `CONVERSATION_BUSY` - `error` (string, required) - `executionId` (string, optional) — The execution holding the conversation slot. Poll /v1/executions/\{executionId}/status, or send x-runtype-concurrency: steer to attach to it. - `phase` (enum, optional) — Where the occupant is: `claiming` (admitted, not yet started; a steer attaches through the claim), `running`, `paused` (a steer stays pending until an authorized resume), or `queued` (an earlier queue-only turn is waiting). - Allowed values: `claiming`, `running`, `paused`, `queued` ### 422 Unprocessable Entity Error The dispatch cannot run: a persisted-flow hash miss (FLOW_DEFINITION_REQUIRED, retry with the full definition), a shaped-wrong definition write (FLOW_DEFINITION_WRITE_REJECTED), no flow definition (FLOW_DEFINITION_MISSING), an unresolvable record or definition (FLOW_RECORD_UNRESOLVED, FLOW_DEFINITION_UNRESOLVED), or a capability the runtime lane cannot host (RUNTIME_LANE_INELIGIBLE, with `reasons`) - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 429 Too Many Requests Error Rate limit exceeded - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ### 500 Internal Server Error Internal server error - `code` (string, required) — Stable error code: `INTERNAL_ERROR` unless the route documents its own. - `error` (string, required) - `details` (list of InternalErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. - `message` (string, optional) — Plain-language guidance: retry, then contact support with the `requestId`. - `requestId` (string, optional) — The `X-Runtype-Request-ID` of the failed request, for support. ### 503 Service Unavailable Error Asynchronous execution unavailable - `error` (string, required) - `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs. - `details` (list of ErrorDetailsItems, optional) - `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs. ## Types ### DispatchExecuteAFlowOrAgentRequest0 - `flow` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Flow, required) - `agent` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Agent, optional) - `clientTools` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems, optional) - `clientToolsPolicy` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsPolicy, optional) - `conversationId` (string, optional) - `credentialProxies` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0CredentialProxiesItems, optional) - `endUser` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0EndUser, optional) — The end user (the person) the turn runs as. Exposed to tools as _endUser.*, drives memory-profile sharding, and satisfies an end-user-isolated tenancyStrategy. Distinct from _user (the Builder User). - `history` (enum, optional) — Where this turn's prior history comes from. "inline" (the default, and today's behavior) replays exactly the `messages` sent here. "stored" replays the transcript saved on the `conversationId` conversation, treats `messages` as the new delta, and appends both the delta and the settled assistant turn back onto it; it requires a saved `agent.agentId` and a `conversationId`, and is refused for a flow dispatch, an inline or `claude_managed` agent, `Prefer: respond-async`, a steer (`x-runtype-concurrency: steer`), or a resume. - Allowed values: `inline`, `stored` - `identityProof` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0IdentityProof, optional) — Customer-native auth proof for the Identity Exchange. When present and the surface has a matching integration, the verified tenant/end-user replace any body-asserted tenant/endUser (which are never trusted for web-embedded callers). When Identity Exchange admission is disabled for the caller, the proof is accepted but ignored and confers no trust. - `inputs` (map from string to any, optional) - `messages` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItems, optional) — Conversation history for this turn, or with `history: "stored"` only the new delta. A `system` message that is not the first message keeps its position on OpenAI-family models (so a per-turn system message sent last leaves the cached leading prompt untouched) and is folded into the leading system prompt on providers that require a single leading system turn. A `tool` message must carry `toolResults` answering an assistant `toolCalls` entry issued earlier in the array. - `options` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Options, optional, default: {"autoAppendMetadata":false,"createVersion":false,"debugMode":false,"environment":"development","flowMode":"existing","recordMode":"existing","storeResults":true,"streamResponse":true}) - `record` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Record, optional) - `secrets` (map from string to string, optional) — Retired on BOTH dispatch targets. A NON-EMPTY map is rejected with 400: RUNTIME\_AGENT\_TRANSIENT\_SECRETS\_UNSUPPORTED on an agent dispatch, RUNTIME\_FLOW\_TRANSIENT\_SECRETS\_UNSUPPORTED on a flow dispatch (the flow target used to drop the map silently). An empty map is accepted and does nothing. Store credentials as managed secrets and reference them as \{\{secret:NAME}}. The field is kept on the wire for compatibility only. - `tenant` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Tenant, optional) — The product tenant (a customer of your product, under your Builder Org) the turn runs within. Exposed to tools as _tenant.*. ### DispatchExecuteAFlowOrAgentRequest1 - `agent` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Agent, required) - `clientTools` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems, optional) - `clientToolsPolicy` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsPolicy, optional) - `conversationId` (string, optional) - `credentialProxies` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1CredentialProxiesItems, optional) - `endUser` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1EndUser, optional) — The end user (the person) the turn runs as. Exposed to tools as _endUser.*, drives memory-profile sharding, and satisfies an end-user-isolated tenancyStrategy. Distinct from _user (the Builder User). - `flow` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Flow, optional) - `history` (enum, optional) — Where this turn's prior history comes from. "inline" (the default, and today's behavior) replays exactly the `messages` sent here. "stored" replays the transcript saved on the `conversationId` conversation, treats `messages` as the new delta, and appends both the delta and the settled assistant turn back onto it; it requires a saved `agent.agentId` and a `conversationId`, and is refused for a flow dispatch, an inline or `claude_managed` agent, `Prefer: respond-async`, a steer (`x-runtype-concurrency: steer`), or a resume. - Allowed values: `inline`, `stored` - `identityProof` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1IdentityProof, optional) — Customer-native auth proof for the Identity Exchange. When present and the surface has a matching integration, the verified tenant/end-user replace any body-asserted tenant/endUser (which are never trusted for web-embedded callers). When Identity Exchange admission is disabled for the caller, the proof is accepted but ignored and confers no trust. - `inputs` (map from string to any, optional) - `messages` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItems, optional) — Conversation history for this turn, or with `history: "stored"` only the new delta. A `system` message that is not the first message keeps its position on OpenAI-family models (so a per-turn system message sent last leaves the cached leading prompt untouched) and is folded into the leading system prompt on providers that require a single leading system turn. A `tool` message must carry `toolResults` answering an assistant `toolCalls` entry issued earlier in the array. - `options` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Options, optional, default: {"autoAppendMetadata":false,"createVersion":false,"debugMode":false,"environment":"development","flowMode":"existing","recordMode":"existing","storeResults":true,"streamResponse":true}) - `record` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Record, optional) - `secrets` (map from string to string, optional) — Retired on BOTH dispatch targets. A NON-EMPTY map is rejected with 400: RUNTIME\_AGENT\_TRANSIENT\_SECRETS\_UNSUPPORTED on an agent dispatch, RUNTIME\_FLOW\_TRANSIENT\_SECRETS\_UNSUPPORTED on a flow dispatch (the flow target used to drop the map silently). An empty map is accepted and does nothing. Store credentials as managed secrets and reference them as \{\{secret:NAME}}. The field is kept on the wire for compatibility only. - `tenant` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Tenant, optional) — The product tenant (a customer of your product, under your Builder Org) the turn runs within. Exposed to tools as _tenant.*. ### ExecutionStreamEvent0 - `executionId` (string, required) - `kind` (enum, required) - Allowed values: `agent`, `flow` - `seq` (double, required) - `startedAt` (string, required) - `type` (enum, required) - Allowed values: `execution_start` - `agentId` (string, optional) - `agentName` (string, optional) - `config` (map from string to any, optional) - `flowId` (string, optional) - `flowName` (string, optional) - `maxTurns` (double, optional) - `resumed` (boolean, optional) - `source` (string, optional) - `totalSteps` (double, optional) ### ExecutionStreamEvent1 - `executionId` (string, required) - `kind` (enum, required) - Allowed values: `agent`, `flow` - `seq` (double, required) - `success` (boolean, required) - `type` (enum, required) - Allowed values: `execution_complete` - `claudeManagedAgentId` (string, optional) - `completedAt` (string, optional) - `durationMs` (double, optional) - `externalAgent` (ExecutionStreamEventOneOf1ExternalAgent, optional) - `failedSteps` (double, optional) - `finalOutput` (string, optional) - `iterations` (double, optional) - `outcome` (enum, optional) — How the execution ended: `completed`, `error`, or `aborted` (cancelled, interrupted, or superseded by the caller or host). Absent on frames from older producers: treat `execution_error` as `error` and `execution_complete` as `completed`, or `error` when `success` is false. - Allowed values: `completed`, `error`, `aborted` - `stepErrorCount` (double, optional) - `stopReason` (string, optional) - `successfulSteps` (double, optional) - `totalCost` (double, optional) - `totalSteps` (double, optional) - `totalTokens` (ExecutionStreamEventOneOf1TotalTokens, optional) - `totalTokensUsed` (double, optional) ### ExecutionStreamEvent2 - `error` (ExecutionStreamEventOneOf2Error, required) - `executionId` (string, required) - `kind` (enum, required) - Allowed values: `agent`, `flow` - `seq` (double, required) - `type` (enum, required) - Allowed values: `execution_error` - `blockReason` (string, optional) - `code` (string, optional) - `completedAt` (string, optional) - `finalOutput` (string, optional) - `outcome` (enum, optional) — How the execution ended: `completed`, `error`, or `aborted` (cancelled, interrupted, or superseded by the caller or host). Absent on frames from older producers: treat `execution_error` as `error` and `execution_complete` as `completed`, or `error` when `success` is false. - Allowed values: `completed`, `error`, `aborted` - `stopReason` (string, optional) - `upgradeUrl` (string, optional) ### ExecutionStreamEvent3 - `executionId` (string, required) - `id` (string, required) - `role` (enum, required) - Allowed values: `user`, `assistant`, `system` - `seq` (double, required) - `type` (enum, required) - Allowed values: `turn_start` - `iteration` (double, optional) - `subagent` (ExecutionStreamEventOneOf3Subagent, optional) - `turnIndex` (double, optional) ### ExecutionStreamEvent4 - `executionId` (string, required) - `id` (string, required) - `role` (enum, required) - Allowed values: `user`, `assistant`, `system` - `seq` (double, required) - `type` (enum, required) - Allowed values: `turn_complete` - `attributes` (map from string to ExecutionStreamEventOneOf4Attributes, optional) - `completedAt` (string, optional) - `content` (string, optional) - `cost` (double, optional) - `estimatedContextBreakdown` (ExecutionStreamEventOneOf4EstimatedContextBreakdown, optional) - `fallback` (ExecutionStreamEventOneOf4Fallback, optional) - `iteration` (double, optional) - `stopReason` (enum, optional) - Allowed values: `end_turn`, `max_tool_calls`, `length`, `content_filter`, `error`, `unknown` - `subagent` (ExecutionStreamEventOneOf4Subagent, optional) - `tokens` (ExecutionStreamEventOneOf4Tokens, optional) ### ExecutionStreamEvent5 - `executionId` (string, required) - `id` (string, required) - `ordinal` (integer, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `model_call_start` - `iteration` (double, optional) - `model` (string, optional) - `provider` (string, optional) - `startedAt` (string, optional) - `stepId` (string, optional) - `subagent` (ExecutionStreamEventOneOf5Subagent, optional) - `turnId` (string, optional) ### ExecutionStreamEvent6 - `executionId` (string, required) - `id` (string, required) - `ordinal` (integer, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `model_call_complete` - `attributes` (map from string to ExecutionStreamEventOneOf6Attributes, optional) - `completedAt` (string, optional) - `cost` (double, optional) - `durationMs` (double, optional) - `finishReason` (string, optional) - `iteration` (double, optional) - `model` (string, optional) - `provider` (string, optional) - `responseModel` (string, optional) - `subagent` (ExecutionStreamEventOneOf6Subagent, optional) - `success` (boolean, optional) - `tokens` (ExecutionStreamEventOneOf6Tokens, optional) - `turnId` (string, optional) ### ExecutionStreamEvent7 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `step_start` - `index` (double, optional) - `name` (string, optional) - `outputVariable` (string, optional) - `startedAt` (string, optional) - `stepType` (string, optional) - `subagent` (ExecutionStreamEventOneOf7Subagent, optional) - `totalSteps` (double, optional) ### ExecutionStreamEvent8 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `step_complete` - `completedAt` (string, optional) - `cost` (double, optional) - `durationMs` (double, optional) - `error` (string, optional) - `fallback` (ExecutionStreamEventOneOf8Fallback, optional) - `name` (string, optional) - `result` (any, optional) - `stepType` (string, optional) - `stopReason` (enum, optional) - Allowed values: `end_turn`, `max_tool_calls`, `length`, `content_filter`, `error`, `unknown` - `subagent` (ExecutionStreamEventOneOf8Subagent, optional) - `success` (boolean, optional) - `tokensUsed` (double, optional) - `unresolvedVariables` (list of string, optional) ### ExecutionStreamEvent9 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `step_skip` - `index` (double, optional) - `name` (string, optional) - `skippedAt` (string, optional) - `stepType` (string, optional) - `totalSteps` (double, optional) - `when` (string, optional) ### ExecutionStreamEvent10 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `text_start` - `parentToolCallId` (string, optional) - `role` (enum, optional) - Allowed values: `user`, `assistant`, `system` - `stepId` (string, optional) - `subagent` (ExecutionStreamEventOneOf10Subagent, optional) - `turnId` (string, optional) ### ExecutionStreamEvent11 - `delta` (string, required) - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `text_delta` - `subagent` (ExecutionStreamEventOneOf11Subagent, optional) ### ExecutionStreamEvent12 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `text_complete` - `subagent` (ExecutionStreamEventOneOf12Subagent, optional) - `text` (string, optional) ### ExecutionStreamEvent13 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `reasoning_start` - `parentToolCallId` (string, optional) - `scope` (enum, optional) - Allowed values: `turn`, `loop` - `subagent` (ExecutionStreamEventOneOf13Subagent, optional) ### ExecutionStreamEvent14 - `delta` (string, required) - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `reasoning_delta` - `subagent` (ExecutionStreamEventOneOf14Subagent, optional) ### ExecutionStreamEvent15 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `reasoning_complete` - `scope` (enum, optional) - Allowed values: `turn`, `loop` - `subagent` (ExecutionStreamEventOneOf15Subagent, optional) - `text` (string, optional) ### ExecutionStreamEvent16 - `executionId` (string, required) - `id` (string, required) - `mediaType` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `media_start` - `role` (enum, optional) - Allowed values: `user`, `assistant`, `system` - `toolCallId` (string, optional) ### ExecutionStreamEvent17 - `delta` (string, required) - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `media_delta` ### ExecutionStreamEvent18 - `executionId` (string, required) - `id` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `media_complete` - `data` (string, optional) - `mediaType` (string, optional) - `toolCallId` (string, optional) - `url` (string, optional) ### ExecutionStreamEvent19 - `artifactType` (enum, required) - Allowed values: `markdown`, `component` - `id` (string, required) - `type` (enum, required) - Allowed values: `artifact_start` - `component` (string, optional) - `executionId` (string, optional) - `file` (ExecutionStreamEventOneOf19File, optional) - `seq` (double, optional) - `title` (string, optional) ### ExecutionStreamEvent20 - `delta` (string, required) - `id` (string, required) - `type` (enum, required) - Allowed values: `artifact_delta` - `executionId` (string, optional) - `seq` (double, optional) ### ExecutionStreamEvent21 - `component` (string, required) - `id` (string, required) - `props` (map from string to any, required) - `type` (enum, required) - Allowed values: `artifact_update` - `executionId` (string, optional) - `seq` (double, optional) ### ExecutionStreamEvent22 - `id` (string, required) - `type` (enum, required) - Allowed values: `artifact_complete` - `executionId` (string, optional) - `seq` (double, optional) ### ExecutionStreamEvent23 - `executionId` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `source` - `id` (string, optional) - `sourceType` (string, optional) - `title` (string, optional) - `url` (string, optional) ### ExecutionStreamEvent24 - `executionId` (string, required) - `seq` (double, required) - `state` (map from string to any, required) - `type` (enum, required) - Allowed values: `state_snapshot` - `iteration` (double, optional) ### ExecutionStreamEvent25 - `executionId` (string, required) - `patch` (list of ExecutionStreamEventOneOf25PatchItems, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `state_delta` - `iteration` (double, optional) ### ExecutionStreamEvent26 - `executionId` (string, required) - `seq` (double, required) - `toolCallId` (string, required) - `toolName` (string, required) - `toolType` (string, required) - `type` (enum, required) - Allowed values: `tool_start` - `annotations` (ExecutionStreamEventOneOf26Annotations, optional) - `hiddenParameterNames` (list of string, optional) - `iteration` (double, optional) - `origin` (enum, optional) - Allowed values: `webmcp`, `sdk` - `pageOrigin` (string, optional) - `parameters` (map from string to any, optional) - `startedAt` (string, optional) - `stepId` (string, optional) - `subagent` (ExecutionStreamEventOneOf26Subagent, optional) ### ExecutionStreamEvent27 - `delta` (string, required) - `executionId` (string, required) - `seq` (double, required) - `toolCallId` (string, required) - `type` (enum, required) - Allowed values: `tool_input_delta` - `subagent` (ExecutionStreamEventOneOf27Subagent, optional) ### ExecutionStreamEvent28 - `executionId` (string, required) - `parameters` (map from string to any, required) - `seq` (double, required) - `toolCallId` (string, required) - `type` (enum, required) - Allowed values: `tool_input_complete` - `hiddenParameterNames` (list of string, optional) - `subagent` (ExecutionStreamEventOneOf28Subagent, optional) - `toolName` (string, optional) ### ExecutionStreamEvent29 - `delta` (string, required) - `executionId` (string, required) - `seq` (double, required) - `toolCallId` (string, required) - `type` (enum, required) - Allowed values: `tool_output_delta` ### ExecutionStreamEvent30 - `executionId` (string, required) - `seq` (double, required) - `success` (boolean, required) - `toolCallId` (string, required) - `type` (enum, required) - Allowed values: `tool_complete` - `error` (string, optional) - `executionTime` (double, optional) - `iteration` (double, optional) - `result` (any, optional) - `stepId` (string, optional) - `subagent` (ExecutionStreamEventOneOf30Subagent, optional) - `toolCost` (double, optional) - `toolName` (string, optional) ### ExecutionStreamEvent31 - `approvalId` (string, required) - `executionId` (string, required) - `seq` (double, required) - `toolName` (string, required) - `type` (enum, required) - Allowed values: `approval_start` - `description` (string, optional) - `externalAgent` (ExecutionStreamEventOneOf31ExternalAgent, optional) - `iteration` (double, optional) - `parameters` (map from string to any, optional) - `reason` (string, optional) - `startedAt` (string, optional) - `subagent` (ExecutionStreamEventOneOf31Subagent, optional) - `timeout` (double, optional) - `toolCallId` (string, optional) - `toolType` (string, optional) ### ExecutionStreamEvent32 - `approvalId` (string, required) - `decision` (enum, required) - Allowed values: `approved`, `denied`, `timeout` - `executionId` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `approval_complete` - `completedAt` (string, optional) - `resolvedBy` (enum, optional) - Allowed values: `user`, `system` ### ExecutionStreamEvent33 - `executionId` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `await` - `annotations` (ExecutionStreamEventOneOf33Annotations, optional) - `awaitReason` (string, optional) - `awaitedAt` (string, optional) - `crawlId` (string, optional) - `elicitation` (ExecutionStreamEventOneOf33Elicitation, optional) - `externalAgent` (ExecutionStreamEventOneOf33ExternalAgent, optional) - `origin` (enum, optional) - Allowed values: `webmcp`, `sdk` - `pageOrigin` (string, optional) - `parameters` (map from string to any, optional) - `stepId` (string, optional) - `toolCallId` (string, optional) - `toolId` (string, optional) - `toolName` (string, optional) ### ExecutionStreamEvent34 - `error` (ExecutionStreamEventOneOf34Error, required) - `executionId` (string, required) - `seq` (double, required) - `type` (enum, required) - Allowed values: `error` - `recoverable` (boolean, optional) ### ExecutionStreamEvent35 - `epoch` (integer, required) - `executionId` (string, required) - `kind` (enum, required) - Allowed values: `compaction` - `phase` (enum, required) - Allowed values: `start`, `complete` - `reason` (enum, required) - Allowed values: `threshold`, `overflow`, `manual`, `surface_policy`, `provider_mismatch` - `seq` (double, required) - `strategy` (enum, required) - Allowed values: `provider_native`, `summary` - `tier` (integer, required) - `type` (enum, required) - Allowed values: `context_notice` - `outcome` (enum, optional) - Allowed values: `ok`, `failed`, `gap`, `skipped` - `tokensAfter` (double, optional) - `tokensBefore` (double, optional) ### ExecutionStreamEvent36 - `executionId` (string, required) - `seq` (double, required) - `timestamp` (string, required) - `type` (enum, required) - Allowed values: `ping` ### ExecutionStreamEvent37 - `name` (string, required) - `type` (enum, required) - Allowed values: `custom` - `executionId` (string, optional) - `seq` (double, optional) - `value` (any, optional) ### BusyMessageRouteReport - `route` (enum, required) — Where the message went: into the running execution, or after it. - Allowed values: `steer`, `queue` - `source` (enum, required) — Why this route applied. - Allowed values: `classifier`, `abstained`, `timeout`, `error`, `unanswered`, `circuit_open`, `disabled` - `model` (string, optional) — The decision model that answered. - `probability` (double, optional) — Probability the message belongs to the running work (classifier only). - `steerUnavailable` (boolean, optional) — The classifier chose steer but the running execution could no longer take input. ### ErrorDetailsItems - `message` (string, required) - `code` (string, optional) — Stable Runtype validation code (e.g. MISSING_REQUIRED_FIELD, INVALID_ENUM). - `path` (string, optional) — Dotted JSON path to the offending field. - `suggestion` (string, optional) — Actionable hint (allowed values, accepted range, …). ### InternalErrorDetailsItems - `message` (string, required) - `code` (string, optional) — Stable Runtype validation code (e.g. MISSING_REQUIRED_FIELD, INVALID_ENUM). - `path` (string, optional) — Dotted JSON path to the offending field. - `suggestion` (string, optional) — Actionable hint (allowed values, accepted range, …). ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Flow - `agents` (map from string to any, optional) - `contentHash` (string, optional) - `description` (string, optional) - `id` (string, optional) - `name` (string, optional) - `steps` (list of any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Agent - `advisor` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentAdvisor, optional, nullable) - `agentId` (string, optional) - `agentType` (enum, optional) - Allowed values: `runtype`, `claude_managed` - `alias` (string, optional) - `artifacts` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentArtifacts, optional) - `busyMessageRouting` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentBusyMessageRouting, optional) - `claudeManagedConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentClaudeManagedConfig, optional) - `durability` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentDurability, optional) - `errorHandling` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandling, optional) - `frequencyPenalty` (double, optional) - `loggingPolicy` (enum, optional) - Allowed values: `default`, `on`, `off` - `loopConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentLoopConfig, optional) - `maxTokens` (integer, optional) - `memory` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentMemory, optional) - `model` (string, optional) - `name` (string, optional) - `piiRedaction` (enum, optional) - Allowed values: `default`, `off`, `redact` - `presencePenalty` (double, optional) - `reasoning` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentReasoning, optional) - `sandbox` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandbox, optional) - `seed` (integer, optional) - `systemPrompt` (string, optional) - `temperature` (double, optional) - `temporal` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTemporal, optional) - `tenancyStrategy` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTenancyStrategy, optional) - `tools` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTools, optional) - `topK` (integer, optional) - `topP` (double, optional) - `versionId` (string, optional) - `voice` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoice, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsPolicy - `allowlist` (list of string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0CredentialProxiesItems - `hostnamePattern` (string, required) - `injectionMode` (enum, required) - Allowed values: `bearer_header`, `api_key_header`, `query_param`, `basic_auth` - `secretKey` (string, required) - `envVarName` (string, optional) - `injectionConfig` (map from string to any, optional, default: {}) - `pathPattern` (string, optional, default: /*) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0EndUser The end user (the person) the turn runs as. Exposed to tools as _endUser.*, drives memory-profile sharding, and satisfies an end-user-isolated tenancyStrategy. Distinct from _user (the Builder User). - `id` (string, required) - `email` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0IdentityProof Customer-native auth proof for the Identity Exchange. When present and the surface has a matching integration, the verified tenant/end-user replace any body-asserted tenant/endUser (which are never trusted for web-embedded callers). When Identity Exchange admission is disabled for the caller, the proof is accepted but ignored and confers no trust. - `provider` (string, required) - `token` (string, required) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItems - `content` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContent, required) - `role` (enum, required) - Allowed values: `system`, `user`, `assistant`, `tool` - `toolCalls` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsToolCallsItems, optional) — Assistant messages only. Every entry must be answered by the next tool message. - `toolResults` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsToolResultsItems, optional) — Tool messages only, and required on them. ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Options - `autoAppendMetadata` (boolean, optional, default: false) - `cache` (boolean, optional) — Set false to disable prompt caching for this request (no cache markers, no cache routing keys). Use for workloads where deterministic byte-identical requests must never share provider cache state, or to A/B against cached behavior. Default: caching follows the account rollout. - `clientToolOutputs` (map from string to any, optional) - `createVersion` (boolean, optional, default: false) - `debugMode` (boolean, optional, default: false) - `environment` (enum, optional, default: development) - Allowed values: `development`, `production` - `flowMode` (enum, optional, default: existing) - Allowed values: `existing`, `create`, `virtual`, `upsert` - `flowTimeoutMs` (integer, optional) — Continuous Flow timeout. Values above 900000 ms require a Flow request detached with Prefer: respond-async; the asynchronous maximum is 1800000 ms. - `flowVersionId` (string, optional) - `localInference` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsLocalInference, optional) - `loggingPolicy` (enum, optional) - Allowed values: `default`, `on`, `off` - `modelOverride` (string, optional) - `recordMode` (enum, optional, default: existing) - Allowed values: `existing`, `create`, `virtual` - `resumeFrom` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsResumeFrom, optional) - `stepTimeoutMs` (integer, optional) — Per-step timeout. Values above 600000 ms require a Flow request detached with Prefer: respond-async; the asynchronous maximum is 1800000 ms. - `storeResults` (boolean, optional, default: true) - `streamResponse` (boolean, optional, default: true) - `upsertOptions` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsUpsertOptions, optional) - `useRuntimePackage` (boolean, optional) — Execution-lane selector. `false` is RETIRED on AGENT dispatches: the legacy agent engine it selected has been deleted, so it is rejected with 400 LEGACY_AGENT_LANE_RETIRED (still carrying the RFC 9745 `Deprecation` + `X-API-Deprecation-Warning` response headers). Omitted and `true` are now IDENTICAL for agents: both run an eligible agent on the @runtypelabs/runtime lane, and both answer a definition the lane cannot execute faithfully with 400 RUNTIME_AGENT_PARITY_FOLD_UNSUPPORTED rather than degrading it. For FLOW dispatches the field is accepted but ignored: eligible flows always use the runtime lane, while ineligible flows still fold to legacy silently. - `versionLabel` (string, optional) - `versionNotes` (string, optional) - `versionType` (enum, optional) - Allowed values: `published`, `draft`, `test`, `virtual` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Record - `id` (string, optional) - `metadata` (map from string to any, optional) - `name` (string, optional) - `ownerId` (string, optional) - `type` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0Tenant The product tenant (a customer of your product, under your Builder Org) the turn runs within. Exposed to tools as _tenant.*. - `id` (string, required) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Agent - `advisor` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentAdvisor, optional, nullable) - `agentId` (string, optional) - `agentType` (enum, optional) - Allowed values: `runtype`, `claude_managed` - `alias` (string, optional) - `artifacts` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentArtifacts, optional) - `busyMessageRouting` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentBusyMessageRouting, optional) - `claudeManagedConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentClaudeManagedConfig, optional) - `durability` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentDurability, optional) - `errorHandling` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandling, optional) - `frequencyPenalty` (double, optional) - `loggingPolicy` (enum, optional) - Allowed values: `default`, `on`, `off` - `loopConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentLoopConfig, optional) - `maxTokens` (integer, optional) - `memory` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentMemory, optional) - `model` (string, optional) - `name` (string, optional) - `piiRedaction` (enum, optional) - Allowed values: `default`, `off`, `redact` - `presencePenalty` (double, optional) - `reasoning` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentReasoning, optional) - `sandbox` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandbox, optional) - `seed` (integer, optional) - `systemPrompt` (string, optional) - `temperature` (double, optional) - `temporal` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTemporal, optional) - `tenancyStrategy` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTenancyStrategy, optional) - `tools` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTools, optional) - `topK` (integer, optional) - `topP` (double, optional) - `versionId` (string, optional) - `voice` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoice, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsPolicy - `allowlist` (list of string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1CredentialProxiesItems - `hostnamePattern` (string, required) - `injectionMode` (enum, required) - Allowed values: `bearer_header`, `api_key_header`, `query_param`, `basic_auth` - `secretKey` (string, required) - `envVarName` (string, optional) - `injectionConfig` (map from string to any, optional, default: {}) - `pathPattern` (string, optional, default: /*) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1EndUser The end user (the person) the turn runs as. Exposed to tools as _endUser.*, drives memory-profile sharding, and satisfies an end-user-isolated tenancyStrategy. Distinct from _user (the Builder User). - `id` (string, required) - `email` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Flow - `agents` (map from string to any, optional) - `contentHash` (string, optional) - `description` (string, optional) - `id` (string, optional) - `name` (string, optional) - `steps` (list of any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1IdentityProof Customer-native auth proof for the Identity Exchange. When present and the surface has a matching integration, the verified tenant/end-user replace any body-asserted tenant/endUser (which are never trusted for web-embedded callers). When Identity Exchange admission is disabled for the caller, the proof is accepted but ignored and confers no trust. - `provider` (string, required) - `token` (string, required) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItems - `content` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContent, required) - `role` (enum, required) - Allowed values: `system`, `user`, `assistant`, `tool` - `toolCalls` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsToolCallsItems, optional) — Assistant messages only. Every entry must be answered by the next tool message. - `toolResults` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsToolResultsItems, optional) — Tool messages only, and required on them. ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Options - `autoAppendMetadata` (boolean, optional, default: false) - `cache` (boolean, optional) — Set false to disable prompt caching for this request (no cache markers, no cache routing keys). Use for workloads where deterministic byte-identical requests must never share provider cache state, or to A/B against cached behavior. Default: caching follows the account rollout. - `clientToolOutputs` (map from string to any, optional) - `createVersion` (boolean, optional, default: false) - `debugMode` (boolean, optional, default: false) - `environment` (enum, optional, default: development) - Allowed values: `development`, `production` - `flowMode` (enum, optional, default: existing) - Allowed values: `existing`, `create`, `virtual`, `upsert` - `flowTimeoutMs` (integer, optional) — Continuous Flow timeout. Values above 900000 ms require a Flow request detached with Prefer: respond-async; the asynchronous maximum is 1800000 ms. - `flowVersionId` (string, optional) - `localInference` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsLocalInference, optional) - `loggingPolicy` (enum, optional) - Allowed values: `default`, `on`, `off` - `modelOverride` (string, optional) - `recordMode` (enum, optional, default: existing) - Allowed values: `existing`, `create`, `virtual` - `resumeFrom` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsResumeFrom, optional) - `stepTimeoutMs` (integer, optional) — Per-step timeout. Values above 600000 ms require a Flow request detached with Prefer: respond-async; the asynchronous maximum is 1800000 ms. - `storeResults` (boolean, optional, default: true) - `streamResponse` (boolean, optional, default: true) - `upsertOptions` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsUpsertOptions, optional) - `useRuntimePackage` (boolean, optional) — Execution-lane selector. `false` is RETIRED on AGENT dispatches: the legacy agent engine it selected has been deleted, so it is rejected with 400 LEGACY_AGENT_LANE_RETIRED (still carrying the RFC 9745 `Deprecation` + `X-API-Deprecation-Warning` response headers). Omitted and `true` are now IDENTICAL for agents: both run an eligible agent on the @runtypelabs/runtime lane, and both answer a definition the lane cannot execute faithfully with 400 RUNTIME_AGENT_PARITY_FOLD_UNSUPPORTED rather than degrading it. For FLOW dispatches the field is accepted but ignored: eligible flows always use the runtime lane, while ineligible flows still fold to legacy silently. - `versionLabel` (string, optional) - `versionNotes` (string, optional) - `versionType` (enum, optional) - Allowed values: `published`, `draft`, `test`, `virtual` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Record - `id` (string, optional) - `metadata` (map from string to any, optional) - `name` (string, optional) - `ownerId` (string, optional) - `type` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1Tenant The product tenant (a customer of your product, under your Builder Org) the turn runs within. Exposed to tools as _tenant.*. - `id` (string, required) ### ExecutionStreamEventOneOf1ExternalAgent - `contextId` (string, optional) - `taskId` (string, optional) ### ExecutionStreamEventOneOf1TotalTokens - `input` (double, required) - `output` (double, required) ### ExecutionStreamEventOneOf2Error - string - ExecutionStreamEventOneOf2Error1 ### ExecutionStreamEventOneOf3Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf4Attributes - string - double - boolean ### ExecutionStreamEventOneOf4EstimatedContextBreakdown - `categories` (map from string to ExecutionStreamEventOneOf4EstimatedContextBreakdownCategories, required) - `estimatedTotalTokens` (double, required) - `contextWindowSize` (double, optional) - `estimatedUtilizationPercent` (double, optional) ### ExecutionStreamEventOneOf4Fallback - `attempts` (list of ExecutionStreamEventOneOf4FallbackAttemptsItems, required) - `exhausted` (boolean, required) - `used` (boolean, required) - `model` (string, optional) - `reason` (string, optional, nullable) ### ExecutionStreamEventOneOf4Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf4Tokens - `input` (double, required) - `output` (double, required) ### ExecutionStreamEventOneOf5Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf6Attributes - string - double - boolean ### ExecutionStreamEventOneOf6Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf6Tokens - `input` (double, required) - `output` (double, required) - `cacheRead` (double, optional) - `cacheWrite` (double, optional) - `reasoning` (double, optional) ### ExecutionStreamEventOneOf7Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf8Fallback - `attempts` (list of ExecutionStreamEventOneOf8FallbackAttemptsItems, required) - `exhausted` (boolean, required) - `used` (boolean, required) - `model` (string, optional) - `reason` (string, optional, nullable) ### ExecutionStreamEventOneOf8Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf10Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf11Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf12Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf13Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf14Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf15Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf19File - `mimeType` (string, required) - `path` (string, required) - `language` (string, optional) ### ExecutionStreamEventOneOf25PatchItems - `op` (enum, required) - Allowed values: `add`, `remove`, `replace`, `move`, `copy`, `test` - `path` (string, required) - `from` (string, optional) - `value` (any, optional) ### ExecutionStreamEventOneOf26Annotations - `consequentialHint` (boolean, optional) - `debugging` (boolean, optional) - `destructiveHint` (boolean, optional) - `idempotentHint` (boolean, optional) - `openWorldHint` (boolean, optional) - `readOnlyHint` (boolean, optional) - `untrustedContentHint` (boolean, optional) ### ExecutionStreamEventOneOf26Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf27Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf28Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf30Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf31ExternalAgent - `contextId` (string, optional) - `taskId` (string, optional) ### ExecutionStreamEventOneOf31Subagent - `toolName` (string, required) - `agentName` (string, optional) - `parentToolCallId` (string, optional) ### ExecutionStreamEventOneOf33Annotations - `consequentialHint` (boolean, optional) - `debugging` (boolean, optional) - `destructiveHint` (boolean, optional) - `idempotentHint` (boolean, optional) - `openWorldHint` (boolean, optional) - `readOnlyHint` (boolean, optional) - `untrustedContentHint` (boolean, optional) ### ExecutionStreamEventOneOf33Elicitation - `message` (string, required) - `mode` (enum, required) - Allowed values: `form`, `url` - `pauseCount` (double, optional) - `requestedSchema` (map from string to any, optional) - `requests` (list of ExecutionStreamEventOneOf33ElicitationRequestsItems, optional) - `serverName` (string, optional) - `url` (string, optional) ### ExecutionStreamEventOneOf33ExternalAgent - `contextId` (string, optional) - `taskId` (string, optional) ### ExecutionStreamEventOneOf34Error - string - ExecutionStreamEventOneOf34Error1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentAdvisor - `model` (string, required) - `systemPrompt` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentArtifacts - `enabled` (boolean, required) - `types` (list of enum, required) - Allowed values: `markdown`, `component` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentBusyMessageRouting - `classifierModel` (string, optional) - `mode` (enum, optional) - Allowed values: `enforced`, `off` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentClaudeManagedConfig - `anthropicAgentId` (string, optional) - `anthropicAgentVersion` (integer, optional) - `anthropicEnvironmentId` (string, optional) - `autoDelete` (boolean, optional) - `model` (string, optional) - `setupMode` (enum, optional) - Allowed values: `create`, `connect` - `systemPrompt` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentDurability - `forced` (enum, optional) - Allowed values: `durable`, `in_process` - `maxBudgetMs` (integer, optional, nullable) - `watchLeaseMs` (integer, optional, nullable) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandling - `onError` (enum, required) - Allowed values: `fail`, `continue`, `fallback` - `fallbacks` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems, optional) - `triggers` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingTriggersItems, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentLoopConfig - `enableReflection` (boolean, optional) - `maxCost` (double, optional) - `maxTurns` (integer, optional) - `reflectionInterval` (integer, optional) - `treatLengthCutoffAsFailure` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentMemory - `enabled` (boolean, required) - `injectSummary` (boolean, optional) - `pointerScope` (enum, optional) - Allowed values: `shared`, `alias`, `version` - `profileTemplate` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentReasoning - boolean - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentReasoning1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandbox - `enabled` (boolean, required) - `codingAgents` (list of enum, optional) — Coding agents the Sandbox can run as typed sessions. Non-empty adds the agent_session_* tools; empty or absent adds none. - Allowed values: `opencode` - `instanceType` (enum, optional) — Only standard-4 is supported on the hosted Agent Sandbox path; other sizes cannot be enabled. - Allowed values: `standard-1`, `standard-2`, `standard-3`, `standard-4` - `networkAccess` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandboxNetworkAccess, optional) - `persistence` (enum, optional) — Supported: ephemeral or conversation. Named remains parseable for stored configs but cannot be enabled. - Allowed values: `ephemeral`, `conversation`, `named` - `provider` (enum, optional) — Only runtype-sandbox is currently supported. Daytona is retained for stored-config parsing but rejected at authoring/execution. - Allowed values: `runtype-sandbox`, `daytona` - `secretEnv` (map from string to string, optional) - `setupCommands` (list of string, optional) - `sleepAfter` (enum, optional) - Allowed values: `5m`, `15m`, `30m`, `1h` - `ttl` (enum, optional) - Allowed values: `5m`, `1h`, `24h`, `unlimited` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTemporal - `elapsedThresholdSeconds` (integer, optional) - `groundNow` (boolean, optional) - `injectElapsed` (boolean, optional) - `timezone` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTenancyStrategy - `preset` (enum, required) - Allowed values: `internal`, `tenant-isolated`, `end-user-isolated` - `assuranceFloor` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTenancyStrategyAssuranceFloor, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTools - `approval` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApproval, optional) - `codeModeConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsCodeModeConfig, optional) - `intent` (enum, optional) - Allowed values: `mandatory`, `best-effort` - `maxToolCalls` (double, optional) - `mcpServers` (list of any, optional) - `perToolLimits` (map from string to V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsPerToolLimits, optional) - `runtimeTools` (list of any, optional) - `subagentConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsSubagentConfig, optional) - `toolCallStrategy` (enum, optional) - Allowed values: `auto`, `required`, `none` - `toolConfigs` (map from string to map from string to any, optional) - `toolIds` (list of string, optional) - `toolSearch` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsToolSearch, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoice - `directTools` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceDirectTools, optional) - `disclosure` (boolean, optional) - `elevenLabs` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceElevenLabs, optional) - `enabled` (boolean, optional) - `endpointing` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceEndpointing, optional) - `greeting` (string, optional) - `interruptionMode` (enum, optional) - Allowed values: `none`, `cancel`, `barge-in` - `language` (string, optional) - `provider` (string, optional) - `speech` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeech, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems0 - `description` (string, required) - `name` (string, required) - `parametersSchema` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItemsOneOf0ParametersSchema, required) - `annotations` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItemsOneOf0Annotations, optional) - `origin` (enum, optional) - Allowed values: `webmcp`, `sdk` - `pageOrigin` (string, optional) - `untrustedContentHint` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItems1 - `catalog` (enum, required) - Allowed values: `runtype-mcp` - `name` (string, required) - `origin` (enum, optional) - Allowed values: `webmcp` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContent - string - list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsToolCallsItems - `toolCallId` (string, required) - `toolName` (string, required) - `args` (map from string to any, optional, default: {}) - `providerOptions` (map from string to any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsToolResultsItems - `toolCallId` (string, required) — Must answer a toolCalls entry issued earlier. - `toolName` (string, required) - `providerOptions` (map from string to any, optional) - `result` (any, optional) — Whatever the tool returned. ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsLocalInference - `backend` (enum, required) - Allowed values: `ollama` - `model` (string, required) - `sessionId` (string, required) - `capabilityRevision` (string, optional) - `surface` (enum, optional) - Allowed values: `playground`, `flows`, `agents` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsResumeFrom - `executionId` (string, required) - `iteration` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0OptionsUpsertOptions - `allowOverwriteExternalChanges` (boolean, optional, default: false) - `createVersionOnChange` (boolean, optional, default: true) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentAdvisor - `model` (string, required) - `systemPrompt` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentArtifacts - `enabled` (boolean, required) - `types` (list of enum, required) - Allowed values: `markdown`, `component` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentBusyMessageRouting - `classifierModel` (string, optional) - `mode` (enum, optional) - Allowed values: `enforced`, `off` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentClaudeManagedConfig - `anthropicAgentId` (string, optional) - `anthropicAgentVersion` (integer, optional) - `anthropicEnvironmentId` (string, optional) - `autoDelete` (boolean, optional) - `model` (string, optional) - `setupMode` (enum, optional) - Allowed values: `create`, `connect` - `systemPrompt` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentDurability - `forced` (enum, optional) - Allowed values: `durable`, `in_process` - `maxBudgetMs` (integer, optional, nullable) - `watchLeaseMs` (integer, optional, nullable) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandling - `onError` (enum, required) - Allowed values: `fail`, `continue`, `fallback` - `fallbacks` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems, optional) - `triggers` (list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingTriggersItems, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentLoopConfig - `enableReflection` (boolean, optional) - `maxCost` (double, optional) - `maxTurns` (integer, optional) - `reflectionInterval` (integer, optional) - `treatLengthCutoffAsFailure` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentMemory - `enabled` (boolean, required) - `injectSummary` (boolean, optional) - `pointerScope` (enum, optional) - Allowed values: `shared`, `alias`, `version` - `profileTemplate` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentReasoning - boolean - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentReasoning1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandbox - `enabled` (boolean, required) - `codingAgents` (list of enum, optional) — Coding agents the Sandbox can run as typed sessions. Non-empty adds the agent_session_* tools; empty or absent adds none. - Allowed values: `opencode` - `instanceType` (enum, optional) — Only standard-4 is supported on the hosted Agent Sandbox path; other sizes cannot be enabled. - Allowed values: `standard-1`, `standard-2`, `standard-3`, `standard-4` - `networkAccess` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandboxNetworkAccess, optional) - `persistence` (enum, optional) — Supported: ephemeral or conversation. Named remains parseable for stored configs but cannot be enabled. - Allowed values: `ephemeral`, `conversation`, `named` - `provider` (enum, optional) — Only runtype-sandbox is currently supported. Daytona is retained for stored-config parsing but rejected at authoring/execution. - Allowed values: `runtype-sandbox`, `daytona` - `secretEnv` (map from string to string, optional) - `setupCommands` (list of string, optional) - `sleepAfter` (enum, optional) - Allowed values: `5m`, `15m`, `30m`, `1h` - `ttl` (enum, optional) - Allowed values: `5m`, `1h`, `24h`, `unlimited` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTemporal - `elapsedThresholdSeconds` (integer, optional) - `groundNow` (boolean, optional) - `injectElapsed` (boolean, optional) - `timezone` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTenancyStrategy - `preset` (enum, required) - Allowed values: `internal`, `tenant-isolated`, `end-user-isolated` - `assuranceFloor` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTenancyStrategyAssuranceFloor, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTools - `approval` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApproval, optional) - `codeModeConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsCodeModeConfig, optional) - `intent` (enum, optional) - Allowed values: `mandatory`, `best-effort` - `maxToolCalls` (double, optional) - `mcpServers` (list of any, optional) - `perToolLimits` (map from string to V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsPerToolLimits, optional) - `runtimeTools` (list of any, optional) - `subagentConfig` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsSubagentConfig, optional) - `toolCallStrategy` (enum, optional) - Allowed values: `auto`, `required`, `none` - `toolConfigs` (map from string to map from string to any, optional) - `toolIds` (list of string, optional) - `toolSearch` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsToolSearch, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoice - `directTools` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceDirectTools, optional) - `disclosure` (boolean, optional) - `elevenLabs` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceElevenLabs, optional) - `enabled` (boolean, optional) - `endpointing` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceEndpointing, optional) - `greeting` (string, optional) - `interruptionMode` (enum, optional) - Allowed values: `none`, `cancel`, `barge-in` - `language` (string, optional) - `provider` (string, optional) - `speech` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeech, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems0 - `description` (string, required) - `name` (string, required) - `parametersSchema` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItemsOneOf0ParametersSchema, required) - `annotations` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItemsOneOf0Annotations, optional) - `origin` (enum, optional) - Allowed values: `webmcp`, `sdk` - `pageOrigin` (string, optional) - `untrustedContentHint` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItems1 - `catalog` (enum, required) - Allowed values: `runtype-mcp` - `name` (string, required) - `origin` (enum, optional) - Allowed values: `webmcp` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContent - string - list of V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsToolCallsItems - `toolCallId` (string, required) - `toolName` (string, required) - `args` (map from string to any, optional, default: {}) - `providerOptions` (map from string to any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsToolResultsItems - `toolCallId` (string, required) — Must answer a toolCalls entry issued earlier. - `toolName` (string, required) - `providerOptions` (map from string to any, optional) - `result` (any, optional) — Whatever the tool returned. ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsLocalInference - `backend` (enum, required) - Allowed values: `ollama` - `model` (string, required) - `sessionId` (string, required) - `capabilityRevision` (string, optional) - `surface` (enum, optional) - Allowed values: `playground`, `flows`, `agents` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsResumeFrom - `executionId` (string, required) - `iteration` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1OptionsUpsertOptions - `allowOverwriteExternalChanges` (boolean, optional, default: false) - `createVersionOnChange` (boolean, optional, default: true) ### ExecutionStreamEventOneOf2Error1 - `code` (string, required) - `message` (string, required) - `details` (map from string to any, optional) ### ExecutionStreamEventOneOf4EstimatedContextBreakdownCategories - `chars` (double, required) - `estimatedTokens` (double, required) ### ExecutionStreamEventOneOf4FallbackAttemptsItems - `attempt` (double, required) - `success` (boolean, required) - `type` (enum, required) - Allowed values: `retry`, `model`, `message`, `flow` - `error` (string, optional) - `model` (string, optional) ### ExecutionStreamEventOneOf8FallbackAttemptsItems - `attempt` (double, required) - `success` (boolean, required) - `type` (enum, required) - Allowed values: `retry`, `model`, `message`, `flow` - `error` (string, optional) - `model` (string, optional) ### ExecutionStreamEventOneOf33ElicitationRequestsItems - `message` (string, required) - `mode` (enum, required) - Allowed values: `form`, `url` - `name` (string, required) - `requestedSchema` (map from string to any, optional) - `url` (string, optional) ### ExecutionStreamEventOneOf34Error1 - `code` (string, required) - `message` (string, required) - `details` (map from string to any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems1 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems2 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingTriggersItems - `type` (enum, required) - Allowed values: `error`, `empty-output` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentReasoning1 - `enabled` (boolean, required) - `budgetTokens` (integer, optional) - `effort` (string, optional) - `includeThoughts` (boolean, optional) - `reasoningEffort` (enum, optional) - Allowed values: `minimal`, `low`, `medium`, `high`, `xhigh`, `max` - `reasoningSummary` (enum, optional) - Allowed values: `auto`, `detailed` - `thinkingBudget` (integer, optional) - `thinkingLevel` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandboxNetworkAccess - enum - Allowed values: `none`, `essentials`, `open` - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandboxNetworkAccess1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentTenancyStrategyAssuranceFloor - `endUser` (enum, optional) - Allowed values: `asserted`, `verified` - `tenant` (enum, optional) - Allowed values: `asserted`, `verified` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApproval - `require` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApprovalRequire, required) - `choices` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApprovalChoices, optional) - `requestReason` (boolean, optional) - `timeout` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsCodeModeConfig - `toolPool` (list of string, required) - `description` (string, optional) - `timeoutMs` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsPerToolLimits - `maxCalls` (double, optional) - `required` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsSubagentConfig - `toolPool` (list of string, required) - `allowNesting` (boolean, optional) - `defaultExecutionMode` (enum, optional) - Allowed values: `attached`, `detached` - `defaultMaxTurns` (integer, optional) - `defaultModel` (string, optional) - `defaultNotify` (enum, optional) - Allowed values: `none`, `narrate`, `react` - `defaultTimeoutMs` (integer, optional) - `detachedMaxBudgetMs` (integer, optional) - `detachedNoProgressBudgetMs` (integer, optional) - `executionModes` (list of enum, optional) - Allowed values: `attached`, `detached` - `maxSpawnsPerRun` (integer, optional) - `maxTurnsLimit` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsToolSearch - `alwaysLoaded` (list of string, optional) - `enabled` (boolean, optional) - `threshold` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceDirectTools - `enabled` (boolean, optional) - `model` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceElevenLabs - `modelId` (string, optional) - `similarity` (double, optional) - `stability` (double, optional) - `voiceId` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceEndpointing - `strategy` (enum, required) - Allowed values: `provider_vad`, `server_vad`, `client_commit`, `manual` - `silenceMs` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeech - `mode` (enum, required) - Allowed values: `pipeline`, `speech_to_speech`, `provider_managed` - `synthesizer` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechSynthesizer, required) - `transcriber` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechTranscriber, required) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItemsOneOf0ParametersSchema - `type` (enum, required) - Allowed values: `object` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0ClientToolsItemsOneOf0Annotations - `consequentialHint` (boolean, optional) - `debugging` (boolean, optional) - `destructiveHint` (boolean, optional) - `idempotentHint` (boolean, optional) - `openWorldHint` (boolean, optional) - `readOnlyHint` (boolean, optional) - `untrustedContentHint` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items1 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items2 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items3 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems1 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems2 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingTriggersItems - `type` (enum, required) - Allowed values: `error`, `empty-output` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentReasoning1 - `enabled` (boolean, required) - `budgetTokens` (integer, optional) - `effort` (string, optional) - `includeThoughts` (boolean, optional) - `reasoningEffort` (enum, optional) - Allowed values: `minimal`, `low`, `medium`, `high`, `xhigh`, `max` - `reasoningSummary` (enum, optional) - Allowed values: `auto`, `detailed` - `thinkingBudget` (integer, optional) - `thinkingLevel` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandboxNetworkAccess - enum - Allowed values: `none`, `essentials`, `open` - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandboxNetworkAccess1 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentTenancyStrategyAssuranceFloor - `endUser` (enum, optional) - Allowed values: `asserted`, `verified` - `tenant` (enum, optional) - Allowed values: `asserted`, `verified` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApproval - `require` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApprovalRequire, required) - `choices` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApprovalChoices, optional) - `requestReason` (boolean, optional) - `timeout` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsCodeModeConfig - `toolPool` (list of string, required) - `description` (string, optional) - `timeoutMs` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsPerToolLimits - `maxCalls` (double, optional) - `required` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsSubagentConfig - `toolPool` (list of string, required) - `allowNesting` (boolean, optional) - `defaultExecutionMode` (enum, optional) - Allowed values: `attached`, `detached` - `defaultMaxTurns` (integer, optional) - `defaultModel` (string, optional) - `defaultNotify` (enum, optional) - Allowed values: `none`, `narrate`, `react` - `defaultTimeoutMs` (integer, optional) - `detachedMaxBudgetMs` (integer, optional) - `detachedNoProgressBudgetMs` (integer, optional) - `executionModes` (list of enum, optional) - Allowed values: `attached`, `detached` - `maxSpawnsPerRun` (integer, optional) - `maxTurnsLimit` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsToolSearch - `alwaysLoaded` (list of string, optional) - `enabled` (boolean, optional) - `threshold` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceDirectTools - `enabled` (boolean, optional) - `model` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceElevenLabs - `modelId` (string, optional) - `similarity` (double, optional) - `stability` (double, optional) - `voiceId` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceEndpointing - `strategy` (enum, required) - Allowed values: `provider_vad`, `server_vad`, `client_commit`, `manual` - `silenceMs` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeech - `mode` (enum, required) - Allowed values: `pipeline`, `speech_to_speech`, `provider_managed` - `synthesizer` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechSynthesizer, required) - `transcriber` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechTranscriber, required) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItemsOneOf0ParametersSchema - `type` (enum, required) - Allowed values: `object` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1ClientToolsItemsOneOf0Annotations - `consequentialHint` (boolean, optional) - `debugging` (boolean, optional) - `destructiveHint` (boolean, optional) - `idempotentHint` (boolean, optional) - `openWorldHint` (boolean, optional) - `readOnlyHint` (boolean, optional) - `untrustedContentHint` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items0 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items1 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items2 - V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items3 ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems0 - `type` (enum, required) - Allowed values: `retry` - `delay` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems1 - `model` (string, required) - `type` (enum, required) - Allowed values: `model` - `delay` (integer, optional) - `maxTokens` (integer, optional) - `temperature` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentErrorHandlingFallbacksItems2 - `message` (string, required) - `type` (enum, required) - Allowed values: `message` - `delay` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentSandboxNetworkAccess1 - `allow` (list of string, optional) - `profile` (enum, optional) - Allowed values: `none`, `essentials`, `open` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApprovalRequire - list of string - boolean ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentToolsApprovalChoices - `alwaysAllow` (boolean, optional) - `alwaysDeny` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechSynthesizer - `provider` (string, required) - `model` (string, optional) - `settings` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechSynthesizerSettings, optional) - `voiceId` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechTranscriber - `provider` (string, required) - `model` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items0 - `text` (string, required) - `type` (enum, required) - Allowed values: `text` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items1 - `image` (string, required) - `type` (enum, required) - Allowed values: `image` - `mimeType` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items2 - `data` (string, required) - `filename` (string, required) - `mimeType` (string, required) - `type` (enum, required) - Allowed values: `file` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0MessagesItemsContentOneOf1Items3 - `text` (string, required) - `type` (enum, required) - Allowed values: `reasoning` - `providerOptions` (map from string to any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems0 - `type` (enum, required) - Allowed values: `retry` - `delay` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems1 - `model` (string, required) - `type` (enum, required) - Allowed values: `model` - `delay` (integer, optional) - `maxTokens` (integer, optional) - `temperature` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentErrorHandlingFallbacksItems2 - `message` (string, required) - `type` (enum, required) - Allowed values: `message` - `delay` (integer, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentSandboxNetworkAccess1 - `allow` (list of string, optional) - `profile` (enum, optional) - Allowed values: `none`, `essentials`, `open` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApprovalRequire - list of string - boolean ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentToolsApprovalChoices - `alwaysAllow` (boolean, optional) - `alwaysDeny` (boolean, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechSynthesizer - `provider` (string, required) - `model` (string, optional) - `settings` (V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechSynthesizerSettings, optional) - `voiceId` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechTranscriber - `provider` (string, required) - `model` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items0 - `text` (string, required) - `type` (enum, required) - Allowed values: `text` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items1 - `image` (string, required) - `type` (enum, required) - Allowed values: `image` - `mimeType` (string, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items2 - `data` (string, required) - `filename` (string, required) - `mimeType` (string, required) - `type` (enum, required) - Allowed values: `file` ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1MessagesItemsContentOneOf1Items3 - `text` (string, required) - `type` (enum, required) - Allowed values: `reasoning` - `providerOptions` (map from string to any, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf0AgentVoiceSpeechSynthesizerSettings - `similarity` (double, optional) - `stability` (double, optional) ### V1DispatchPostRequestBodyContentApplicationJsonSchemaOneOf1AgentVoiceSpeechSynthesizerSettings - `similarity` (double, optional) - `stability` (double, optional) ## Examples ### Dispatch - Auto Append Metadata Example **Request** ```json { "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": [ "Product A", "Product B", "Product C" ], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } } ``` **SDK Code** ```python Dispatch - Auto Append Metadata Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": True, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": True, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": ["Product A", "Product B", "Product C"], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Auto Append Metadata Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Sales Analysis","steps":[{"config":{"model":"gpt-4","outputVariable":"sales_analysis","responseFormat":"markdown","userPrompt":"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}."},"enabled":true,"id":"analyze-sales","name":"Analyze Sales Performance","order":1,"type":"prompt"}]},"options":{"autoAppendMetadata":true,"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"growth_rate":"18%","quarter":"Q4 2024","region":"North America","sales_team":"Team Alpha","top_products":["Product A","Product B","Product C"],"total_revenue":"$2.5M"},"name":"Q4 Sales Report","type":"report"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Auto Append Metadata Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Auto Append Metadata Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Auto Append Metadata Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}") .asString(); ``` ```php Dispatch - Auto Append Metadata Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": [ "Product A", "Product B", "Product C" ], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Auto Append Metadata Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Auto Append Metadata Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Sales Analysis", "steps": [ [ "config": [ "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." ], "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" ] ] ], "options": [ "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": ["Product A", "Product B", "Product C"], "total_revenue": "$2.5M" ], "name": "Q4 Sales Report", "type": "report" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Auto Append Metadata Example **Request** ```json { "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": [ "Product A", "Product B", "Product C" ], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } } ``` **SDK Code** ```python Dispatch - Auto Append Metadata Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": True, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": True, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": ["Product A", "Product B", "Product C"], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Auto Append Metadata Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Sales Analysis","steps":[{"config":{"model":"gpt-4","outputVariable":"sales_analysis","responseFormat":"markdown","userPrompt":"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}."},"enabled":true,"id":"analyze-sales","name":"Analyze Sales Performance","order":1,"type":"prompt"}]},"options":{"autoAppendMetadata":true,"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"growth_rate":"18%","quarter":"Q4 2024","region":"North America","sales_team":"Team Alpha","top_products":["Product A","Product B","Product C"],"total_revenue":"$2.5M"},"name":"Q4 Sales Report","type":"report"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Auto Append Metadata Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Auto Append Metadata Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Auto Append Metadata Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}") .asString(); ``` ```php Dispatch - Auto Append Metadata Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Sales Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." }, "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" } ] }, "options": { "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": [ "Product A", "Product B", "Product C" ], "total_revenue": "$2.5M" }, "name": "Q4 Sales Report", "type": "report" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Auto Append Metadata Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Sales Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"sales_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}.\"\n },\n \"enabled\": true,\n \"id\": \"analyze-sales\",\n \"name\": \"Analyze Sales Performance\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"autoAppendMetadata\": true,\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"growth_rate\": \"18%\",\n \"quarter\": \"Q4 2024\",\n \"region\": \"North America\",\n \"sales_team\": \"Team Alpha\",\n \"top_products\": [\n \"Product A\",\n \"Product B\",\n \"Product C\"\n ],\n \"total_revenue\": \"$2.5M\"\n },\n \"name\": \"Q4 Sales Report\",\n \"type\": \"report\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Auto Append Metadata Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Sales Analysis", "steps": [ [ "config": [ "model": "gpt-4", "outputVariable": "sales_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the sales performance for {{_record.metadata.quarter}} in {{_record.metadata.region}}." ], "enabled": true, "id": "analyze-sales", "name": "Analyze Sales Performance", "order": 1, "type": "prompt" ] ] ], "options": [ "autoAppendMetadata": true, "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "growth_rate": "18%", "quarter": "Q4 2024", "region": "North America", "sales_team": "Team Alpha", "top_products": ["Product A", "Product B", "Product C"], "total_revenue": "$2.5M" ], "name": "Q4 Sales Report", "type": "report" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Complex Flow Example **Request** ```json { "flow": { "description": "Multi-step analysis with different response formats", "name": "Comprehensive Document Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "financial_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health." }, "enabled": true, "id": "financial-analysis", "name": "Financial Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "market_position", "responseFormat": "json", "userPrompt": "Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks." }, "enabled": true, "id": "market-position", "name": "Market Position JSON", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}." }, "enabled": true, "id": "executive-summary", "name": "Executive Summary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "product_analysis", "responseFormat": "html", "userPrompt": "Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential." }, "enabled": true, "id": "product-analysis", "name": "Product Analysis HTML", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "ceo_statement": "This year marked significant growth in our AI division...", "company": "GlobalTech Inc", "employees": 15000, "growth": "23%", "key_products": [ "Cloud Platform", "AI Suite", "Security Tools" ], "markets": [ "North America", "Europe", "Asia" ], "revenue": "$5.2B", "year": 2024 }, "name": "Annual Report 2024", "type": "document" } } ``` **SDK Code** ```python Dispatch - Complex Flow Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "Multi-step analysis with different response formats", "name": "Comprehensive Document Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "financial_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health." }, "enabled": True, "id": "financial-analysis", "name": "Financial Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "market_position", "responseFormat": "json", "userPrompt": "Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks." }, "enabled": True, "id": "market-position", "name": "Market Position JSON", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}." }, "enabled": True, "id": "executive-summary", "name": "Executive Summary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "product_analysis", "responseFormat": "html", "userPrompt": "Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential." }, "enabled": True, "id": "product-analysis", "name": "Product Analysis HTML", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": True }, "record": { "metadata": { "ceo_statement": "This year marked significant growth in our AI division...", "company": "GlobalTech Inc", "employees": 15000, "growth": "23%", "key_products": ["Cloud Platform", "AI Suite", "Security Tools"], "markets": ["North America", "Europe", "Asia"], "revenue": "$5.2B", "year": 2024 }, "name": "Annual Report 2024", "type": "document" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Complex Flow Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"Multi-step analysis with different response formats","name":"Comprehensive Document Analysis","steps":[{"config":{"model":"gpt-4","outputVariable":"financial_analysis","responseFormat":"markdown","userPrompt":"Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health."},"enabled":true,"id":"financial-analysis","name":"Financial Analysis","order":1,"type":"prompt"},{"config":{"model":"gpt-4","outputVariable":"market_position","responseFormat":"json","userPrompt":"Create a structured analysis of {{_record.metadata.company}}\'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks."},"enabled":true,"id":"market-position","name":"Market Position JSON","order":2,"type":"prompt"},{"config":{"model":"gpt-3.5-turbo","outputVariable":"executive_summary","responseFormat":"text","userPrompt":"Based on the CEO statement: \'{{_record.metadata.ceo_statement}}\' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}."},"enabled":true,"id":"executive-summary","name":"Executive Summary","order":3,"type":"prompt"},{"config":{"model":"gpt-4","outputVariable":"product_analysis","responseFormat":"html","userPrompt":"Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential."},"enabled":true,"id":"product-analysis","name":"Product Analysis HTML","order":4,"type":"prompt"}]},"options":{"flowMode":"create","recordMode":"create","streamResponse":true},"record":{"metadata":{"ceo_statement":"This year marked significant growth in our AI division...","company":"GlobalTech Inc","employees":15000,"growth":"23%","key_products":["Cloud Platform","AI Suite","Security Tools"],"markets":["North America","Europe","Asia"],"revenue":"$5.2B","year":2024},"name":"Annual Report 2024","type":"document"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Complex Flow Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"Multi-step analysis with different response formats\",\n \"name\": \"Comprehensive Document Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"financial_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health.\"\n },\n \"enabled\": true,\n \"id\": \"financial-analysis\",\n \"name\": \"Financial Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"market_position\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks.\"\n },\n \"enabled\": true,\n \"id\": \"market-position\",\n \"name\": \"Market Position JSON\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"executive-summary\",\n \"name\": \"Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"product_analysis\",\n \"responseFormat\": \"html\",\n \"userPrompt\": \"Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential.\"\n },\n \"enabled\": true,\n \"id\": \"product-analysis\",\n \"name\": \"Product Analysis HTML\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"ceo_statement\": \"This year marked significant growth in our AI division...\",\n \"company\": \"GlobalTech Inc\",\n \"employees\": 15000,\n \"growth\": \"23%\",\n \"key_products\": [\n \"Cloud Platform\",\n \"AI Suite\",\n \"Security Tools\"\n ],\n \"markets\": [\n \"North America\",\n \"Europe\",\n \"Asia\"\n ],\n \"revenue\": \"$5.2B\",\n \"year\": 2024\n },\n \"name\": \"Annual Report 2024\",\n \"type\": \"document\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Complex Flow Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"Multi-step analysis with different response formats\",\n \"name\": \"Comprehensive Document Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"financial_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health.\"\n },\n \"enabled\": true,\n \"id\": \"financial-analysis\",\n \"name\": \"Financial Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"market_position\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks.\"\n },\n \"enabled\": true,\n \"id\": \"market-position\",\n \"name\": \"Market Position JSON\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"executive-summary\",\n \"name\": \"Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"product_analysis\",\n \"responseFormat\": \"html\",\n \"userPrompt\": \"Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential.\"\n },\n \"enabled\": true,\n \"id\": \"product-analysis\",\n \"name\": \"Product Analysis HTML\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"ceo_statement\": \"This year marked significant growth in our AI division...\",\n \"company\": \"GlobalTech Inc\",\n \"employees\": 15000,\n \"growth\": \"23%\",\n \"key_products\": [\n \"Cloud Platform\",\n \"AI Suite\",\n \"Security Tools\"\n ],\n \"markets\": [\n \"North America\",\n \"Europe\",\n \"Asia\"\n ],\n \"revenue\": \"$5.2B\",\n \"year\": 2024\n },\n \"name\": \"Annual Report 2024\",\n \"type\": \"document\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Complex Flow Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"Multi-step analysis with different response formats\",\n \"name\": \"Comprehensive Document Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"financial_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health.\"\n },\n \"enabled\": true,\n \"id\": \"financial-analysis\",\n \"name\": \"Financial Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"market_position\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks.\"\n },\n \"enabled\": true,\n \"id\": \"market-position\",\n \"name\": \"Market Position JSON\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"executive-summary\",\n \"name\": \"Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"product_analysis\",\n \"responseFormat\": \"html\",\n \"userPrompt\": \"Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential.\"\n },\n \"enabled\": true,\n \"id\": \"product-analysis\",\n \"name\": \"Product Analysis HTML\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"ceo_statement\": \"This year marked significant growth in our AI division...\",\n \"company\": \"GlobalTech Inc\",\n \"employees\": 15000,\n \"growth\": \"23%\",\n \"key_products\": [\n \"Cloud Platform\",\n \"AI Suite\",\n \"Security Tools\"\n ],\n \"markets\": [\n \"North America\",\n \"Europe\",\n \"Asia\"\n ],\n \"revenue\": \"$5.2B\",\n \"year\": 2024\n },\n \"name\": \"Annual Report 2024\",\n \"type\": \"document\"\n }\n}") .asString(); ``` ```php Dispatch - Complex Flow Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "Multi-step analysis with different response formats", "name": "Comprehensive Document Analysis", "steps": [ { "config": { "model": "gpt-4", "outputVariable": "financial_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health." }, "enabled": true, "id": "financial-analysis", "name": "Financial Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "market_position", "responseFormat": "json", "userPrompt": "Create a structured analysis of {{_record.metadata.company}}\'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks." }, "enabled": true, "id": "market-position", "name": "Market Position JSON", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Based on the CEO statement: \'{{_record.metadata.ceo_statement}}\' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}." }, "enabled": true, "id": "executive-summary", "name": "Executive Summary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4", "outputVariable": "product_analysis", "responseFormat": "html", "userPrompt": "Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential." }, "enabled": true, "id": "product-analysis", "name": "Product Analysis HTML", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "ceo_statement": "This year marked significant growth in our AI division...", "company": "GlobalTech Inc", "employees": 15000, "growth": "23%", "key_products": [ "Cloud Platform", "AI Suite", "Security Tools" ], "markets": [ "North America", "Europe", "Asia" ], "revenue": "$5.2B", "year": 2024 }, "name": "Annual Report 2024", "type": "document" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Complex Flow Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"Multi-step analysis with different response formats\",\n \"name\": \"Comprehensive Document Analysis\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"financial_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health.\"\n },\n \"enabled\": true,\n \"id\": \"financial-analysis\",\n \"name\": \"Financial Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"market_position\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks.\"\n },\n \"enabled\": true,\n \"id\": \"market-position\",\n \"name\": \"Market Position JSON\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"executive-summary\",\n \"name\": \"Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4\",\n \"outputVariable\": \"product_analysis\",\n \"responseFormat\": \"html\",\n \"userPrompt\": \"Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential.\"\n },\n \"enabled\": true,\n \"id\": \"product-analysis\",\n \"name\": \"Product Analysis HTML\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"ceo_statement\": \"This year marked significant growth in our AI division...\",\n \"company\": \"GlobalTech Inc\",\n \"employees\": 15000,\n \"growth\": \"23%\",\n \"key_products\": [\n \"Cloud Platform\",\n \"AI Suite\",\n \"Security Tools\"\n ],\n \"markets\": [\n \"North America\",\n \"Europe\",\n \"Asia\"\n ],\n \"revenue\": \"$5.2B\",\n \"year\": 2024\n },\n \"name\": \"Annual Report 2024\",\n \"type\": \"document\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Complex Flow Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "Multi-step analysis with different response formats", "name": "Comprehensive Document Analysis", "steps": [ [ "config": [ "model": "gpt-4", "outputVariable": "financial_analysis", "responseFormat": "markdown", "userPrompt": "Analyze the financial performance of {{_record.metadata.company}} with revenue of {{_record.metadata.revenue}} and growth rate of {{_record.metadata.growth}}. Document: {{_record.name}}. Flow: {{_flow.name}} (ID: {{_flow.id}}). Provide insights on financial health." ], "enabled": true, "id": "financial-analysis", "name": "Financial Analysis", "order": 1, "type": "prompt" ], [ "config": [ "model": "gpt-4", "outputVariable": "market_position", "responseFormat": "json", "userPrompt": "Create a structured analysis of {{_record.metadata.company}}'s market position. Markets: {{_record.metadata.markets}}. Execution ID: {{_execution.id}}. Return as JSON with fields: market_share, competitive_advantages, growth_opportunities, risks." ], "enabled": true, "id": "market-position", "name": "Market Position JSON", "order": 2, "type": "prompt" ], [ "config": [ "model": "gpt-3.5-turbo", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Based on the CEO statement: '{{_record.metadata.ceo_statement}}' and company metrics ({{_record.metadata.employees}} employees, {{_record.metadata.revenue}} revenue), write a brief executive summary for {{_record.name}}. Analyzed by user {{_user.id}} at {{_execution.timestamp}}." ], "enabled": true, "id": "executive-summary", "name": "Executive Summary", "order": 3, "type": "prompt" ], [ "config": [ "model": "gpt-4", "outputVariable": "product_analysis", "responseFormat": "html", "userPrompt": "Create an HTML report analyzing the key products: {{_record.metadata.key_products}} for {{_record.metadata.company}}. Include a table comparing features and market potential." ], "enabled": true, "id": "product-analysis", "name": "Product Analysis HTML", "order": 4, "type": "prompt" ] ] ], "options": [ "flowMode": "create", "recordMode": "create", "streamResponse": true ], "record": [ "metadata": [ "ceo_statement": "This year marked significant growth in our AI division...", "company": "GlobalTech Inc", "employees": 15000, "growth": "23%", "key_products": ["Cloud Platform", "AI Suite", "Security Tools"], "markets": ["North America", "Europe", "Asia"], "revenue": "$5.2B", "year": 2024 ], "name": "Annual Report 2024", "type": "document" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Context Steps Example **Request** ```json { "flow": { "description": "Comprehensive analysis using context steps", "name": "Repository Analysis Pipeline", "steps": [ { "config": { "http": { "headers": { "Accept": "application/vnd.github.raw+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}/readme" }, "outputVariable": "repo_content", "responseType": "text" }, "enabled": true, "id": "fetch-repo", "name": "Fetch Repository README", "type": "fetch-url" }, { "config": { "outputVariable": "file_analysis", "script": "// Analyze repository content\nconst content = repo_content || ''\nconst lines = content.split('\\n')\nconst tsFiles = lines.filter(line => line.includes('.ts')).length\nconst jsFiles = lines.filter(line => line.includes('.js')).length\n\n// Extract key metrics\nconst metrics = {\n total_lines: lines.length,\n typescript_files: tsFiles,\n javascript_files: jsFiles,\n has_readme: content.toLowerCase().includes('readme'),\n content_size: content.length,\n analysis_timestamp: new Date().toISOString()\n}\n\nreturn {\n repository: _record.metadata.repository,\n owner: _record.metadata.owner,\n metrics: metrics,\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\n}" }, "enabled": true, "id": "transform-files", "name": "Transform Repository Data", "type": "transform-data" }, { "config": { "http": { "headers": { "Accept": "application/vnd.github.v3+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}" }, "outputVariable": "github_stats", "responseMapping": { "created_at": "created_at", "forks": "forks_count", "issues": "open_issues_count", "language": "language", "size": "size", "stars": "stargazers_count", "updated_at": "updated_at" } }, "enabled": true, "id": "api-call-github", "name": "Fetch GitHub Repository Stats", "type": "api-call" }, { "config": { "valueTemplate": "Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}", "variableName": "analysis_context" }, "enabled": true, "id": "set-analysis-context", "name": "Set Analysis Context", "type": "set-variable" }, { "config": { "contentField": "summary", "includeMetadata": [ "metrics", "owner" ], "nameTemplate": "{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}", "outputVariable": "creation_results", "pathField": "repository", "recordType": "repository-analysis", "repositoryUrl": "https://github.com/{{_record.metadata.repository}}", "sourceVariable": "file_analysis" }, "enabled": true, "id": "create-analysis-records", "name": "Create Analysis Records", "type": "create-records" }, { "config": { "errorHandling": { "onError": "continue" }, "from": "analysis@runtype.com", "html": "

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

", "outputVariable": "email_result", "subject": "Repository Analysis Complete: {{_record.metadata.repository}}", "text": "Repository Analysis Complete\n\nRepository: {{_record.metadata.repository}}\nOwner: {{_record.metadata.owner}}\nStars: {{github_stats.stars}}\nLanguage: {{github_stats.language}}\nSummary: {{file_analysis.summary}}\n\nAnalysis Context: {{analysis_context}}\n\nAnalysis completed by Runtype on {{_execution.timestamp}}", "to": "developer@example.com" }, "enabled": true, "id": "send-notification", "name": "Send Analysis Notification", "type": "send-email" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "analysis_date": "2024-07-28", "language": "TypeScript", "owner": "Microsoft", "repository": "microsoft/TypeScript", "stars": 100000 }, "name": "GitHub Repository Analysis", "type": "repository" } } ``` **SDK Code** ```python Dispatch - Context Steps Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "Comprehensive analysis using context steps", "name": "Repository Analysis Pipeline", "steps": [ { "config": { "http": { "headers": { "Accept": "application/vnd.github.raw+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}/readme" }, "outputVariable": "repo_content", "responseType": "text" }, "enabled": True, "id": "fetch-repo", "name": "Fetch Repository README", "type": "fetch-url" }, { "config": { "outputVariable": "file_analysis", "script": "// Analyze repository content const content = repo_content || '' const lines = content.split('\n') const tsFiles = lines.filter(line => line.includes('.ts')).length const jsFiles = lines.filter(line => line.includes('.js')).length // Extract key metrics const metrics = { total_lines: lines.length, typescript_files: tsFiles, javascript_files: jsFiles, has_readme: content.toLowerCase().includes('readme'), content_size: content.length, analysis_timestamp: new Date().toISOString() } return { repository: _record.metadata.repository, owner: _record.metadata.owner, metrics: metrics, summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines` }" }, "enabled": True, "id": "transform-files", "name": "Transform Repository Data", "type": "transform-data" }, { "config": { "http": { "headers": { "Accept": "application/vnd.github.v3+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}" }, "outputVariable": "github_stats", "responseMapping": { "created_at": "created_at", "forks": "forks_count", "issues": "open_issues_count", "language": "language", "size": "size", "stars": "stargazers_count", "updated_at": "updated_at" } }, "enabled": True, "id": "api-call-github", "name": "Fetch GitHub Repository Stats", "type": "api-call" }, { "config": { "valueTemplate": "Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}", "variableName": "analysis_context" }, "enabled": True, "id": "set-analysis-context", "name": "Set Analysis Context", "type": "set-variable" }, { "config": { "contentField": "summary", "includeMetadata": ["metrics", "owner"], "nameTemplate": "{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}", "outputVariable": "creation_results", "pathField": "repository", "recordType": "repository-analysis", "repositoryUrl": "https://github.com/{{_record.metadata.repository}}", "sourceVariable": "file_analysis" }, "enabled": True, "id": "create-analysis-records", "name": "Create Analysis Records", "type": "create-records" }, { "config": { "errorHandling": { "onError": "continue" }, "from": "analysis@runtype.com", "html": "

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

", "outputVariable": "email_result", "subject": "Repository Analysis Complete: {{_record.metadata.repository}}", "text": "Repository Analysis Complete Repository: {{_record.metadata.repository}} Owner: {{_record.metadata.owner}} Stars: {{github_stats.stars}} Language: {{github_stats.language}} Summary: {{file_analysis.summary}} Analysis Context: {{analysis_context}} Analysis completed by Runtype on {{_execution.timestamp}}", "to": "developer@example.com" }, "enabled": True, "id": "send-notification", "name": "Send Analysis Notification", "type": "send-email" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": True }, "record": { "metadata": { "analysis_date": "2024-07-28", "language": "TypeScript", "owner": "Microsoft", "repository": "microsoft/TypeScript", "stars": 100000 }, "name": "GitHub Repository Analysis", "type": "repository" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Context Steps Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"Comprehensive analysis using context steps","name":"Repository Analysis Pipeline","steps":[{"config":{"http":{"headers":{"Accept":"application/vnd.github.raw+json","User-Agent":"Runtype-Analysis"},"method":"GET","url":"https://api.github.com/repos/{{_record.metadata.repository}}/readme"},"outputVariable":"repo_content","responseType":"text"},"enabled":true,"id":"fetch-repo","name":"Fetch Repository README","type":"fetch-url"},{"config":{"outputVariable":"file_analysis","script":"// Analyze repository content\nconst content = repo_content || \'\'\nconst lines = content.split(\'\\n\')\nconst tsFiles = lines.filter(line => line.includes(\'.ts\')).length\nconst jsFiles = lines.filter(line => line.includes(\'.js\')).length\n\n// Extract key metrics\nconst metrics = {\n total_lines: lines.length,\n typescript_files: tsFiles,\n javascript_files: jsFiles,\n has_readme: content.toLowerCase().includes(\'readme\'),\n content_size: content.length,\n analysis_timestamp: new Date().toISOString()\n}\n\nreturn {\n repository: _record.metadata.repository,\n owner: _record.metadata.owner,\n metrics: metrics,\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\n}"},"enabled":true,"id":"transform-files","name":"Transform Repository Data","type":"transform-data"},{"config":{"http":{"headers":{"Accept":"application/vnd.github.v3+json","User-Agent":"Runtype-Analysis"},"method":"GET","url":"https://api.github.com/repos/{{_record.metadata.repository}}"},"outputVariable":"github_stats","responseMapping":{"created_at":"created_at","forks":"forks_count","issues":"open_issues_count","language":"language","size":"size","stars":"stargazers_count","updated_at":"updated_at"}},"enabled":true,"id":"api-call-github","name":"Fetch GitHub Repository Stats","type":"api-call"},{"config":{"valueTemplate":"Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}","variableName":"analysis_context"},"enabled":true,"id":"set-analysis-context","name":"Set Analysis Context","type":"set-variable"},{"config":{"contentField":"summary","includeMetadata":["metrics","owner"],"nameTemplate":"{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}","outputVariable":"creation_results","pathField":"repository","recordType":"repository-analysis","repositoryUrl":"https://github.com/{{_record.metadata.repository}}","sourceVariable":"file_analysis"},"enabled":true,"id":"create-analysis-records","name":"Create Analysis Records","type":"create-records"},{"config":{"errorHandling":{"onError":"continue"},"from":"analysis@runtype.com","html":"

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

","outputVariable":"email_result","subject":"Repository Analysis Complete: {{_record.metadata.repository}}","text":"Repository Analysis Complete\n\nRepository: {{_record.metadata.repository}}\nOwner: {{_record.metadata.owner}}\nStars: {{github_stats.stars}}\nLanguage: {{github_stats.language}}\nSummary: {{file_analysis.summary}}\n\nAnalysis Context: {{analysis_context}}\n\nAnalysis completed by Runtype on {{_execution.timestamp}}","to":"developer@example.com"},"enabled":true,"id":"send-notification","name":"Send Analysis Notification","type":"send-email"}]},"options":{"flowMode":"create","recordMode":"create","streamResponse":true},"record":{"metadata":{"analysis_date":"2024-07-28","language":"TypeScript","owner":"Microsoft","repository":"microsoft/TypeScript","stars":100000},"name":"GitHub Repository Analysis","type":"repository"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Context Steps Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"Comprehensive analysis using context steps\",\n \"name\": \"Repository Analysis Pipeline\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.raw+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}/readme\"\n },\n \"outputVariable\": \"repo_content\",\n \"responseType\": \"text\"\n },\n \"enabled\": true,\n \"id\": \"fetch-repo\",\n \"name\": \"Fetch Repository README\",\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"outputVariable\": \"file_analysis\",\n \"script\": \"// Analyze repository content\\nconst content = repo_content || ''\\nconst lines = content.split('\\\\n')\\nconst tsFiles = lines.filter(line => line.includes('.ts')).length\\nconst jsFiles = lines.filter(line => line.includes('.js')).length\\n\\n// Extract key metrics\\nconst metrics = {\\n total_lines: lines.length,\\n typescript_files: tsFiles,\\n javascript_files: jsFiles,\\n has_readme: content.toLowerCase().includes('readme'),\\n content_size: content.length,\\n analysis_timestamp: new Date().toISOString()\\n}\\n\\nreturn {\\n repository: _record.metadata.repository,\\n owner: _record.metadata.owner,\\n metrics: metrics,\\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\\n}\"\n },\n \"enabled\": true,\n \"id\": \"transform-files\",\n \"name\": \"Transform Repository Data\",\n \"type\": \"transform-data\"\n },\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.v3+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}\"\n },\n \"outputVariable\": \"github_stats\",\n \"responseMapping\": {\n \"created_at\": \"created_at\",\n \"forks\": \"forks_count\",\n \"issues\": \"open_issues_count\",\n \"language\": \"language\",\n \"size\": \"size\",\n \"stars\": \"stargazers_count\",\n \"updated_at\": \"updated_at\"\n }\n },\n \"enabled\": true,\n \"id\": \"api-call-github\",\n \"name\": \"Fetch GitHub Repository Stats\",\n \"type\": \"api-call\"\n },\n {\n \"config\": {\n \"valueTemplate\": \"Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}\",\n \"variableName\": \"analysis_context\"\n },\n \"enabled\": true,\n \"id\": \"set-analysis-context\",\n \"name\": \"Set Analysis Context\",\n \"type\": \"set-variable\"\n },\n {\n \"config\": {\n \"contentField\": \"summary\",\n \"includeMetadata\": [\n \"metrics\",\n \"owner\"\n ],\n \"nameTemplate\": \"{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}\",\n \"outputVariable\": \"creation_results\",\n \"pathField\": \"repository\",\n \"recordType\": \"repository-analysis\",\n \"repositoryUrl\": \"https://github.com/{{_record.metadata.repository}}\",\n \"sourceVariable\": \"file_analysis\"\n },\n \"enabled\": true,\n \"id\": \"create-analysis-records\",\n \"name\": \"Create Analysis Records\",\n \"type\": \"create-records\"\n },\n {\n \"config\": {\n \"errorHandling\": {\n \"onError\": \"continue\"\n },\n \"from\": \"analysis@runtype.com\",\n \"html\": \"

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

\",\n \"outputVariable\": \"email_result\",\n \"subject\": \"Repository Analysis Complete: {{_record.metadata.repository}}\",\n \"text\": \"Repository Analysis Complete\\n\\nRepository: {{_record.metadata.repository}}\\nOwner: {{_record.metadata.owner}}\\nStars: {{github_stats.stars}}\\nLanguage: {{github_stats.language}}\\nSummary: {{file_analysis.summary}}\\n\\nAnalysis Context: {{analysis_context}}\\n\\nAnalysis completed by Runtype on {{_execution.timestamp}}\",\n \"to\": \"developer@example.com\"\n },\n \"enabled\": true,\n \"id\": \"send-notification\",\n \"name\": \"Send Analysis Notification\",\n \"type\": \"send-email\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"analysis_date\": \"2024-07-28\",\n \"language\": \"TypeScript\",\n \"owner\": \"Microsoft\",\n \"repository\": \"microsoft/TypeScript\",\n \"stars\": 100000\n },\n \"name\": \"GitHub Repository Analysis\",\n \"type\": \"repository\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Context Steps Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"Comprehensive analysis using context steps\",\n \"name\": \"Repository Analysis Pipeline\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.raw+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}/readme\"\n },\n \"outputVariable\": \"repo_content\",\n \"responseType\": \"text\"\n },\n \"enabled\": true,\n \"id\": \"fetch-repo\",\n \"name\": \"Fetch Repository README\",\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"outputVariable\": \"file_analysis\",\n \"script\": \"// Analyze repository content\\nconst content = repo_content || ''\\nconst lines = content.split('\\\\n')\\nconst tsFiles = lines.filter(line => line.includes('.ts')).length\\nconst jsFiles = lines.filter(line => line.includes('.js')).length\\n\\n// Extract key metrics\\nconst metrics = {\\n total_lines: lines.length,\\n typescript_files: tsFiles,\\n javascript_files: jsFiles,\\n has_readme: content.toLowerCase().includes('readme'),\\n content_size: content.length,\\n analysis_timestamp: new Date().toISOString()\\n}\\n\\nreturn {\\n repository: _record.metadata.repository,\\n owner: _record.metadata.owner,\\n metrics: metrics,\\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\\n}\"\n },\n \"enabled\": true,\n \"id\": \"transform-files\",\n \"name\": \"Transform Repository Data\",\n \"type\": \"transform-data\"\n },\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.v3+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}\"\n },\n \"outputVariable\": \"github_stats\",\n \"responseMapping\": {\n \"created_at\": \"created_at\",\n \"forks\": \"forks_count\",\n \"issues\": \"open_issues_count\",\n \"language\": \"language\",\n \"size\": \"size\",\n \"stars\": \"stargazers_count\",\n \"updated_at\": \"updated_at\"\n }\n },\n \"enabled\": true,\n \"id\": \"api-call-github\",\n \"name\": \"Fetch GitHub Repository Stats\",\n \"type\": \"api-call\"\n },\n {\n \"config\": {\n \"valueTemplate\": \"Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}\",\n \"variableName\": \"analysis_context\"\n },\n \"enabled\": true,\n \"id\": \"set-analysis-context\",\n \"name\": \"Set Analysis Context\",\n \"type\": \"set-variable\"\n },\n {\n \"config\": {\n \"contentField\": \"summary\",\n \"includeMetadata\": [\n \"metrics\",\n \"owner\"\n ],\n \"nameTemplate\": \"{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}\",\n \"outputVariable\": \"creation_results\",\n \"pathField\": \"repository\",\n \"recordType\": \"repository-analysis\",\n \"repositoryUrl\": \"https://github.com/{{_record.metadata.repository}}\",\n \"sourceVariable\": \"file_analysis\"\n },\n \"enabled\": true,\n \"id\": \"create-analysis-records\",\n \"name\": \"Create Analysis Records\",\n \"type\": \"create-records\"\n },\n {\n \"config\": {\n \"errorHandling\": {\n \"onError\": \"continue\"\n },\n \"from\": \"analysis@runtype.com\",\n \"html\": \"

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

\",\n \"outputVariable\": \"email_result\",\n \"subject\": \"Repository Analysis Complete: {{_record.metadata.repository}}\",\n \"text\": \"Repository Analysis Complete\\n\\nRepository: {{_record.metadata.repository}}\\nOwner: {{_record.metadata.owner}}\\nStars: {{github_stats.stars}}\\nLanguage: {{github_stats.language}}\\nSummary: {{file_analysis.summary}}\\n\\nAnalysis Context: {{analysis_context}}\\n\\nAnalysis completed by Runtype on {{_execution.timestamp}}\",\n \"to\": \"developer@example.com\"\n },\n \"enabled\": true,\n \"id\": \"send-notification\",\n \"name\": \"Send Analysis Notification\",\n \"type\": \"send-email\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"analysis_date\": \"2024-07-28\",\n \"language\": \"TypeScript\",\n \"owner\": \"Microsoft\",\n \"repository\": \"microsoft/TypeScript\",\n \"stars\": 100000\n },\n \"name\": \"GitHub Repository Analysis\",\n \"type\": \"repository\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Context Steps Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"Comprehensive analysis using context steps\",\n \"name\": \"Repository Analysis Pipeline\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.raw+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}/readme\"\n },\n \"outputVariable\": \"repo_content\",\n \"responseType\": \"text\"\n },\n \"enabled\": true,\n \"id\": \"fetch-repo\",\n \"name\": \"Fetch Repository README\",\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"outputVariable\": \"file_analysis\",\n \"script\": \"// Analyze repository content\\nconst content = repo_content || ''\\nconst lines = content.split('\\\\n')\\nconst tsFiles = lines.filter(line => line.includes('.ts')).length\\nconst jsFiles = lines.filter(line => line.includes('.js')).length\\n\\n// Extract key metrics\\nconst metrics = {\\n total_lines: lines.length,\\n typescript_files: tsFiles,\\n javascript_files: jsFiles,\\n has_readme: content.toLowerCase().includes('readme'),\\n content_size: content.length,\\n analysis_timestamp: new Date().toISOString()\\n}\\n\\nreturn {\\n repository: _record.metadata.repository,\\n owner: _record.metadata.owner,\\n metrics: metrics,\\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\\n}\"\n },\n \"enabled\": true,\n \"id\": \"transform-files\",\n \"name\": \"Transform Repository Data\",\n \"type\": \"transform-data\"\n },\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.v3+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}\"\n },\n \"outputVariable\": \"github_stats\",\n \"responseMapping\": {\n \"created_at\": \"created_at\",\n \"forks\": \"forks_count\",\n \"issues\": \"open_issues_count\",\n \"language\": \"language\",\n \"size\": \"size\",\n \"stars\": \"stargazers_count\",\n \"updated_at\": \"updated_at\"\n }\n },\n \"enabled\": true,\n \"id\": \"api-call-github\",\n \"name\": \"Fetch GitHub Repository Stats\",\n \"type\": \"api-call\"\n },\n {\n \"config\": {\n \"valueTemplate\": \"Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}\",\n \"variableName\": \"analysis_context\"\n },\n \"enabled\": true,\n \"id\": \"set-analysis-context\",\n \"name\": \"Set Analysis Context\",\n \"type\": \"set-variable\"\n },\n {\n \"config\": {\n \"contentField\": \"summary\",\n \"includeMetadata\": [\n \"metrics\",\n \"owner\"\n ],\n \"nameTemplate\": \"{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}\",\n \"outputVariable\": \"creation_results\",\n \"pathField\": \"repository\",\n \"recordType\": \"repository-analysis\",\n \"repositoryUrl\": \"https://github.com/{{_record.metadata.repository}}\",\n \"sourceVariable\": \"file_analysis\"\n },\n \"enabled\": true,\n \"id\": \"create-analysis-records\",\n \"name\": \"Create Analysis Records\",\n \"type\": \"create-records\"\n },\n {\n \"config\": {\n \"errorHandling\": {\n \"onError\": \"continue\"\n },\n \"from\": \"analysis@runtype.com\",\n \"html\": \"

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

\",\n \"outputVariable\": \"email_result\",\n \"subject\": \"Repository Analysis Complete: {{_record.metadata.repository}}\",\n \"text\": \"Repository Analysis Complete\\n\\nRepository: {{_record.metadata.repository}}\\nOwner: {{_record.metadata.owner}}\\nStars: {{github_stats.stars}}\\nLanguage: {{github_stats.language}}\\nSummary: {{file_analysis.summary}}\\n\\nAnalysis Context: {{analysis_context}}\\n\\nAnalysis completed by Runtype on {{_execution.timestamp}}\",\n \"to\": \"developer@example.com\"\n },\n \"enabled\": true,\n \"id\": \"send-notification\",\n \"name\": \"Send Analysis Notification\",\n \"type\": \"send-email\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"analysis_date\": \"2024-07-28\",\n \"language\": \"TypeScript\",\n \"owner\": \"Microsoft\",\n \"repository\": \"microsoft/TypeScript\",\n \"stars\": 100000\n },\n \"name\": \"GitHub Repository Analysis\",\n \"type\": \"repository\"\n }\n}") .asString(); ``` ```php Dispatch - Context Steps Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "Comprehensive analysis using context steps", "name": "Repository Analysis Pipeline", "steps": [ { "config": { "http": { "headers": { "Accept": "application/vnd.github.raw+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}/readme" }, "outputVariable": "repo_content", "responseType": "text" }, "enabled": true, "id": "fetch-repo", "name": "Fetch Repository README", "type": "fetch-url" }, { "config": { "outputVariable": "file_analysis", "script": "// Analyze repository content\\nconst content = repo_content || \'\'\\nconst lines = content.split(\'\\\\n\')\\nconst tsFiles = lines.filter(line => line.includes(\'.ts\')).length\\nconst jsFiles = lines.filter(line => line.includes(\'.js\')).length\\n\\n// Extract key metrics\\nconst metrics = {\\n total_lines: lines.length,\\n typescript_files: tsFiles,\\n javascript_files: jsFiles,\\n has_readme: content.toLowerCase().includes(\'readme\'),\\n content_size: content.length,\\n analysis_timestamp: new Date().toISOString()\\n}\\n\\nreturn {\\n repository: _record.metadata.repository,\\n owner: _record.metadata.owner,\\n metrics: metrics,\\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\\n}" }, "enabled": true, "id": "transform-files", "name": "Transform Repository Data", "type": "transform-data" }, { "config": { "http": { "headers": { "Accept": "application/vnd.github.v3+json", "User-Agent": "Runtype-Analysis" }, "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}" }, "outputVariable": "github_stats", "responseMapping": { "created_at": "created_at", "forks": "forks_count", "issues": "open_issues_count", "language": "language", "size": "size", "stars": "stargazers_count", "updated_at": "updated_at" } }, "enabled": true, "id": "api-call-github", "name": "Fetch GitHub Repository Stats", "type": "api-call" }, { "config": { "valueTemplate": "Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}", "variableName": "analysis_context" }, "enabled": true, "id": "set-analysis-context", "name": "Set Analysis Context", "type": "set-variable" }, { "config": { "contentField": "summary", "includeMetadata": [ "metrics", "owner" ], "nameTemplate": "{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}", "outputVariable": "creation_results", "pathField": "repository", "recordType": "repository-analysis", "repositoryUrl": "https://github.com/{{_record.metadata.repository}}", "sourceVariable": "file_analysis" }, "enabled": true, "id": "create-analysis-records", "name": "Create Analysis Records", "type": "create-records" }, { "config": { "errorHandling": { "onError": "continue" }, "from": "analysis@runtype.com", "html": "

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

", "outputVariable": "email_result", "subject": "Repository Analysis Complete: {{_record.metadata.repository}}", "text": "Repository Analysis Complete\\n\\nRepository: {{_record.metadata.repository}}\\nOwner: {{_record.metadata.owner}}\\nStars: {{github_stats.stars}}\\nLanguage: {{github_stats.language}}\\nSummary: {{file_analysis.summary}}\\n\\nAnalysis Context: {{analysis_context}}\\n\\nAnalysis completed by Runtype on {{_execution.timestamp}}", "to": "developer@example.com" }, "enabled": true, "id": "send-notification", "name": "Send Analysis Notification", "type": "send-email" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "analysis_date": "2024-07-28", "language": "TypeScript", "owner": "Microsoft", "repository": "microsoft/TypeScript", "stars": 100000 }, "name": "GitHub Repository Analysis", "type": "repository" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Context Steps Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"Comprehensive analysis using context steps\",\n \"name\": \"Repository Analysis Pipeline\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.raw+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}/readme\"\n },\n \"outputVariable\": \"repo_content\",\n \"responseType\": \"text\"\n },\n \"enabled\": true,\n \"id\": \"fetch-repo\",\n \"name\": \"Fetch Repository README\",\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"outputVariable\": \"file_analysis\",\n \"script\": \"// Analyze repository content\\nconst content = repo_content || ''\\nconst lines = content.split('\\\\n')\\nconst tsFiles = lines.filter(line => line.includes('.ts')).length\\nconst jsFiles = lines.filter(line => line.includes('.js')).length\\n\\n// Extract key metrics\\nconst metrics = {\\n total_lines: lines.length,\\n typescript_files: tsFiles,\\n javascript_files: jsFiles,\\n has_readme: content.toLowerCase().includes('readme'),\\n content_size: content.length,\\n analysis_timestamp: new Date().toISOString()\\n}\\n\\nreturn {\\n repository: _record.metadata.repository,\\n owner: _record.metadata.owner,\\n metrics: metrics,\\n summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines`\\n}\"\n },\n \"enabled\": true,\n \"id\": \"transform-files\",\n \"name\": \"Transform Repository Data\",\n \"type\": \"transform-data\"\n },\n {\n \"config\": {\n \"http\": {\n \"headers\": {\n \"Accept\": \"application/vnd.github.v3+json\",\n \"User-Agent\": \"Runtype-Analysis\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.github.com/repos/{{_record.metadata.repository}}\"\n },\n \"outputVariable\": \"github_stats\",\n \"responseMapping\": {\n \"created_at\": \"created_at\",\n \"forks\": \"forks_count\",\n \"issues\": \"open_issues_count\",\n \"language\": \"language\",\n \"size\": \"size\",\n \"stars\": \"stargazers_count\",\n \"updated_at\": \"updated_at\"\n }\n },\n \"enabled\": true,\n \"id\": \"api-call-github\",\n \"name\": \"Fetch GitHub Repository Stats\",\n \"type\": \"api-call\"\n },\n {\n \"config\": {\n \"valueTemplate\": \"Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}\",\n \"variableName\": \"analysis_context\"\n },\n \"enabled\": true,\n \"id\": \"set-analysis-context\",\n \"name\": \"Set Analysis Context\",\n \"type\": \"set-variable\"\n },\n {\n \"config\": {\n \"contentField\": \"summary\",\n \"includeMetadata\": [\n \"metrics\",\n \"owner\"\n ],\n \"nameTemplate\": \"{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}\",\n \"outputVariable\": \"creation_results\",\n \"pathField\": \"repository\",\n \"recordType\": \"repository-analysis\",\n \"repositoryUrl\": \"https://github.com/{{_record.metadata.repository}}\",\n \"sourceVariable\": \"file_analysis\"\n },\n \"enabled\": true,\n \"id\": \"create-analysis-records\",\n \"name\": \"Create Analysis Records\",\n \"type\": \"create-records\"\n },\n {\n \"config\": {\n \"errorHandling\": {\n \"onError\": \"continue\"\n },\n \"from\": \"analysis@runtype.com\",\n \"html\": \"

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

\",\n \"outputVariable\": \"email_result\",\n \"subject\": \"Repository Analysis Complete: {{_record.metadata.repository}}\",\n \"text\": \"Repository Analysis Complete\\n\\nRepository: {{_record.metadata.repository}}\\nOwner: {{_record.metadata.owner}}\\nStars: {{github_stats.stars}}\\nLanguage: {{github_stats.language}}\\nSummary: {{file_analysis.summary}}\\n\\nAnalysis Context: {{analysis_context}}\\n\\nAnalysis completed by Runtype on {{_execution.timestamp}}\",\n \"to\": \"developer@example.com\"\n },\n \"enabled\": true,\n \"id\": \"send-notification\",\n \"name\": \"Send Analysis Notification\",\n \"type\": \"send-email\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"analysis_date\": \"2024-07-28\",\n \"language\": \"TypeScript\",\n \"owner\": \"Microsoft\",\n \"repository\": \"microsoft/TypeScript\",\n \"stars\": 100000\n },\n \"name\": \"GitHub Repository Analysis\",\n \"type\": \"repository\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Context Steps Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "Comprehensive analysis using context steps", "name": "Repository Analysis Pipeline", "steps": [ [ "config": [ "http": [ "headers": [ "Accept": "application/vnd.github.raw+json", "User-Agent": "Runtype-Analysis" ], "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}/readme" ], "outputVariable": "repo_content", "responseType": "text" ], "enabled": true, "id": "fetch-repo", "name": "Fetch Repository README", "type": "fetch-url" ], [ "config": [ "outputVariable": "file_analysis", "script": "// Analyze repository content const content = repo_content || '' const lines = content.split('\n') const tsFiles = lines.filter(line => line.includes('.ts')).length const jsFiles = lines.filter(line => line.includes('.js')).length // Extract key metrics const metrics = { total_lines: lines.length, typescript_files: tsFiles, javascript_files: jsFiles, has_readme: content.toLowerCase().includes('readme'), content_size: content.length, analysis_timestamp: new Date().toISOString() } return { repository: _record.metadata.repository, owner: _record.metadata.owner, metrics: metrics, summary: `Found ${tsFiles + jsFiles} source files (${tsFiles} TS, ${jsFiles} JS) in ${lines.length} total lines` }" ], "enabled": true, "id": "transform-files", "name": "Transform Repository Data", "type": "transform-data" ], [ "config": [ "http": [ "headers": [ "Accept": "application/vnd.github.v3+json", "User-Agent": "Runtype-Analysis" ], "method": "GET", "url": "https://api.github.com/repos/{{_record.metadata.repository}}" ], "outputVariable": "github_stats", "responseMapping": [ "created_at": "created_at", "forks": "forks_count", "issues": "open_issues_count", "language": "language", "size": "size", "stars": "stargazers_count", "updated_at": "updated_at" ] ], "enabled": true, "id": "api-call-github", "name": "Fetch GitHub Repository Stats", "type": "api-call" ], [ "config": [ "valueTemplate": "Repository: {{_record.metadata.repository}} | Owner: {{_record.metadata.owner}} | Analysis Date: {{_record.metadata.analysis_date}} | User: {{_user.id}} | Flow: {{_flow.name}}", "variableName": "analysis_context" ], "enabled": true, "id": "set-analysis-context", "name": "Set Analysis Context", "type": "set-variable" ], [ "config": [ "contentField": "summary", "includeMetadata": ["metrics", "owner"], "nameTemplate": "{{_record.metadata.repository}}-analysis-{{_execution.timestamp}}", "outputVariable": "creation_results", "pathField": "repository", "recordType": "repository-analysis", "repositoryUrl": "https://github.com/{{_record.metadata.repository}}", "sourceVariable": "file_analysis" ], "enabled": true, "id": "create-analysis-records", "name": "Create Analysis Records", "type": "create-records" ], [ "config": [ "errorHandling": ["onError": "continue"], "from": "analysis@runtype.com", "html": "

Repository Analysis Complete

Repository: {{_record.metadata.repository}}

Owner: {{_record.metadata.owner}}

Stars: {{github_stats.stars}}

Language: {{github_stats.language}}

Summary: {{file_analysis.summary}}

Analysis Context: {{analysis_context}}

Analysis completed by Runtype on {{_execution.timestamp}}

", "outputVariable": "email_result", "subject": "Repository Analysis Complete: {{_record.metadata.repository}}", "text": "Repository Analysis Complete Repository: {{_record.metadata.repository}} Owner: {{_record.metadata.owner}} Stars: {{github_stats.stars}} Language: {{github_stats.language}} Summary: {{file_analysis.summary}} Analysis Context: {{analysis_context}} Analysis completed by Runtype on {{_execution.timestamp}}", "to": "developer@example.com" ], "enabled": true, "id": "send-notification", "name": "Send Analysis Notification", "type": "send-email" ] ] ], "options": [ "flowMode": "create", "recordMode": "create", "streamResponse": true ], "record": [ "metadata": [ "analysis_date": "2024-07-28", "language": "TypeScript", "owner": "Microsoft", "repository": "microsoft/TypeScript", "stars": 100000 ], "name": "GitHub Repository Analysis", "type": "repository" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Create New Record and Flow **Request** ```json { "flow": { "description": "Analyze company information and generate insights", "name": "Company Research Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "company_analysis", "responseFormat": "markdown", "userPrompt": "Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}." }, "enabled": true, "id": "extract-company-info", "name": "Extract Company Info", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}" }, "enabled": true, "id": "generate-summary", "name": "Generate Executive Summary", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "competitor_analysis", "responseFormat": "json", "userPrompt": "List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}." }, "enabled": true, "id": "competitor-analysis", "name": "Competitor Analysis", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "description": "Leading provider of cloud-based solutions", "employees": "50-100", "founded": "2015", "industry": "Technology", "website": "https://techcorp.example.com" }, "name": "TechCorp Solutions", "type": "company" } } ``` **SDK Code** ```python Dispatch - Create New Record and Flow import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "Analyze company information and generate insights", "name": "Company Research Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "company_analysis", "responseFormat": "markdown", "userPrompt": "Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}." }, "enabled": True, "id": "extract-company-info", "name": "Extract Company Info", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}" }, "enabled": True, "id": "generate-summary", "name": "Generate Executive Summary", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "competitor_analysis", "responseFormat": "json", "userPrompt": "List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}." }, "enabled": True, "id": "competitor-analysis", "name": "Competitor Analysis", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": True }, "record": { "metadata": { "description": "Leading provider of cloud-based solutions", "employees": "50-100", "founded": "2015", "industry": "Technology", "website": "https://techcorp.example.com" }, "name": "TechCorp Solutions", "type": "company" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Create New Record and Flow const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"Analyze company information and generate insights","name":"Company Research Flow","steps":[{"config":{"model":"gemini-1.5-flash","outputVariable":"company_analysis","responseFormat":"markdown","userPrompt":"Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}."},"enabled":true,"id":"extract-company-info","name":"Extract Company Info","order":1,"type":"prompt"},{"config":{"model":"google/gemma-4-26b-a4b-it","outputVariable":"executive_summary","responseFormat":"text","userPrompt":"Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}"},"enabled":true,"id":"generate-summary","name":"Generate Executive Summary","order":2,"type":"prompt"},{"config":{"model":"gemini-1.5-flash","outputVariable":"competitor_analysis","responseFormat":"json","userPrompt":"List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}."},"enabled":true,"id":"competitor-analysis","name":"Competitor Analysis","order":3,"type":"prompt"}]},"options":{"flowMode":"create","recordMode":"create","streamResponse":true},"record":{"metadata":{"description":"Leading provider of cloud-based solutions","employees":"50-100","founded":"2015","industry":"Technology","website":"https://techcorp.example.com"},"name":"TechCorp Solutions","type":"company"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Create New Record and Flow package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"Analyze company information and generate insights\",\n \"name\": \"Company Research Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"company_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"extract-company-info\",\n \"name\": \"Extract Company Info\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}\"\n },\n \"enabled\": true,\n \"id\": \"generate-summary\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"competitor_analysis\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"competitor-analysis\",\n \"name\": \"Competitor Analysis\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"Leading provider of cloud-based solutions\",\n \"employees\": \"50-100\",\n \"founded\": \"2015\",\n \"industry\": \"Technology\",\n \"website\": \"https://techcorp.example.com\"\n },\n \"name\": \"TechCorp Solutions\",\n \"type\": \"company\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Create New Record and Flow require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"Analyze company information and generate insights\",\n \"name\": \"Company Research Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"company_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"extract-company-info\",\n \"name\": \"Extract Company Info\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}\"\n },\n \"enabled\": true,\n \"id\": \"generate-summary\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"competitor_analysis\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"competitor-analysis\",\n \"name\": \"Competitor Analysis\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"Leading provider of cloud-based solutions\",\n \"employees\": \"50-100\",\n \"founded\": \"2015\",\n \"industry\": \"Technology\",\n \"website\": \"https://techcorp.example.com\"\n },\n \"name\": \"TechCorp Solutions\",\n \"type\": \"company\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Create New Record and Flow import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"Analyze company information and generate insights\",\n \"name\": \"Company Research Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"company_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"extract-company-info\",\n \"name\": \"Extract Company Info\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}\"\n },\n \"enabled\": true,\n \"id\": \"generate-summary\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"competitor_analysis\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"competitor-analysis\",\n \"name\": \"Competitor Analysis\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"Leading provider of cloud-based solutions\",\n \"employees\": \"50-100\",\n \"founded\": \"2015\",\n \"industry\": \"Technology\",\n \"website\": \"https://techcorp.example.com\"\n },\n \"name\": \"TechCorp Solutions\",\n \"type\": \"company\"\n }\n}") .asString(); ``` ```php Dispatch - Create New Record and Flow request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "Analyze company information and generate insights", "name": "Company Research Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "company_analysis", "responseFormat": "markdown", "userPrompt": "Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}." }, "enabled": true, "id": "extract-company-info", "name": "Extract Company Info", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}" }, "enabled": true, "id": "generate-summary", "name": "Generate Executive Summary", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "competitor_analysis", "responseFormat": "json", "userPrompt": "List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}." }, "enabled": true, "id": "competitor-analysis", "name": "Competitor Analysis", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "description": "Leading provider of cloud-based solutions", "employees": "50-100", "founded": "2015", "industry": "Technology", "website": "https://techcorp.example.com" }, "name": "TechCorp Solutions", "type": "company" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Create New Record and Flow using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"Analyze company information and generate insights\",\n \"name\": \"Company Research Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"company_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}.\"\n },\n \"enabled\": true,\n \"id\": \"extract-company-info\",\n \"name\": \"Extract Company Info\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}\"\n },\n \"enabled\": true,\n \"id\": \"generate-summary\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"competitor_analysis\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"competitor-analysis\",\n \"name\": \"Competitor Analysis\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"Leading provider of cloud-based solutions\",\n \"employees\": \"50-100\",\n \"founded\": \"2015\",\n \"industry\": \"Technology\",\n \"website\": \"https://techcorp.example.com\"\n },\n \"name\": \"TechCorp Solutions\",\n \"type\": \"company\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Create New Record and Flow import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "Analyze company information and generate insights", "name": "Company Research Flow", "steps": [ [ "config": [ "model": "gemini-1.5-flash", "outputVariable": "company_analysis", "responseFormat": "markdown", "userPrompt": "Based on the company {{_record.name}} in the {{_record.metadata.industry}} industry, founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees, provide a comprehensive analysis of their potential market position and growth opportunities. Website: {{_record.metadata.website}}. This analysis is for flow: {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}}." ], "enabled": true, "id": "extract-company-info", "name": "Extract Company Info", "order": 1, "type": "prompt" ], [ "config": [ "model": "google/gemma-4-26b-a4b-it", "outputVariable": "executive_summary", "responseFormat": "text", "userPrompt": "Create a concise executive summary for {{_record.name}} based on the following description: {{_record.metadata.description}}. Include key business metrics and strategic recommendations. Execution ID: {{_execution.id}}" ], "enabled": true, "id": "generate-summary", "name": "Generate Executive Summary", "order": 2, "type": "prompt" ], [ "config": [ "model": "gemini-1.5-flash", "outputVariable": "competitor_analysis", "responseFormat": "json", "userPrompt": "List potential competitors for {{_record.name}} in the {{_record.metadata.industry}} industry and provide a brief comparison of their market positioning. Analysis performed by user {{_user.id}} using flow {{_flow.name}}." ], "enabled": true, "id": "competitor-analysis", "name": "Competitor Analysis", "order": 3, "type": "prompt" ] ] ], "options": [ "flowMode": "create", "recordMode": "create", "streamResponse": true ], "record": [ "metadata": [ "description": "Leading provider of cloud-based solutions", "employees": "50-100", "founded": "2015", "industry": "Technology", "website": "https://techcorp.example.com" ], "name": "TechCorp Solutions", "type": "company" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Create Record Only **Request** ```json { "flow": { "id": "flow_01jv0000000000000000000003" }, "options": { "flowMode": "existing", "recordMode": "create" }, "record": { "metadata": { "email": "customer@example.com", "status": "active", "tier": "premium" }, "name": "Sample Customer", "type": "customer" } } ``` **SDK Code** ```python Dispatch - Create Record Only import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "id": "flow_01jv0000000000000000000003" }, "options": { "flowMode": "existing", "recordMode": "create" }, "record": { "metadata": { "email": "customer@example.com", "status": "active", "tier": "premium" }, "name": "Sample Customer", "type": "customer" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Create Record Only const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"id":"flow_01jv0000000000000000000003"},"options":{"flowMode":"existing","recordMode":"create"},"record":{"metadata":{"email":"customer@example.com","status":"active","tier":"premium"},"name":"Sample Customer","type":"customer"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Create Record Only package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000003\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"create\"\n },\n \"record\": {\n \"metadata\": {\n \"email\": \"customer@example.com\",\n \"status\": \"active\",\n \"tier\": \"premium\"\n },\n \"name\": \"Sample Customer\",\n \"type\": \"customer\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Create Record Only require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000003\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"create\"\n },\n \"record\": {\n \"metadata\": {\n \"email\": \"customer@example.com\",\n \"status\": \"active\",\n \"tier\": \"premium\"\n },\n \"name\": \"Sample Customer\",\n \"type\": \"customer\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Create Record Only import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000003\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"create\"\n },\n \"record\": {\n \"metadata\": {\n \"email\": \"customer@example.com\",\n \"status\": \"active\",\n \"tier\": \"premium\"\n },\n \"name\": \"Sample Customer\",\n \"type\": \"customer\"\n }\n}") .asString(); ``` ```php Dispatch - Create Record Only request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "id": "flow_01jv0000000000000000000003" }, "options": { "flowMode": "existing", "recordMode": "create" }, "record": { "metadata": { "email": "customer@example.com", "status": "active", "tier": "premium" }, "name": "Sample Customer", "type": "customer" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Create Record Only using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000003\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"create\"\n },\n \"record\": {\n \"metadata\": {\n \"email\": \"customer@example.com\",\n \"status\": \"active\",\n \"tier\": \"premium\"\n },\n \"name\": \"Sample Customer\",\n \"type\": \"customer\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Create Record Only import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": ["id": "flow_01jv0000000000000000000003"], "options": [ "flowMode": "existing", "recordMode": "create" ], "record": [ "metadata": [ "email": "customer@example.com", "status": "active", "tier": "premium" ], "name": "Sample Customer", "type": "customer" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Test Error Tracking **Request** ```json { "flow": { "name": "Error Tracking Test Flow", "steps": [ { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result1", "userPrompt": "Say 'Success' and nothing else" }, "name": "Valid Step", "type": "prompt" }, { "config": { "model": "this-model-does-not-exist", "outputVariable": "result2", "userPrompt": "This will fail due to invalid model" }, "name": "Invalid Model Step", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result3", "userPrompt": "This step should not run because previous step failed" }, "name": "Should Not Execute", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "name": "Error Test Record", "type": "test" } } ``` **SDK Code** ```python Dispatch - Test Error Tracking import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Error Tracking Test Flow", "steps": [ { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result1", "userPrompt": "Say 'Success' and nothing else" }, "name": "Valid Step", "type": "prompt" }, { "config": { "model": "this-model-does-not-exist", "outputVariable": "result2", "userPrompt": "This will fail due to invalid model" }, "name": "Invalid Model Step", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result3", "userPrompt": "This step should not run because previous step failed" }, "name": "Should Not Execute", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": True, "streamResponse": True }, "record": { "name": "Error Test Record", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Test Error Tracking const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Error Tracking Test Flow","steps":[{"config":{"model":"gpt-3.5-turbo","outputVariable":"result1","userPrompt":"Say \'Success\' and nothing else"},"name":"Valid Step","type":"prompt"},{"config":{"model":"this-model-does-not-exist","outputVariable":"result2","userPrompt":"This will fail due to invalid model"},"name":"Invalid Model Step","type":"prompt"},{"config":{"model":"gpt-3.5-turbo","outputVariable":"result3","userPrompt":"This step should not run because previous step failed"},"name":"Should Not Execute","type":"prompt"}]},"options":{"flowMode":"virtual","recordMode":"virtual","storeResults":true,"streamResponse":true},"record":{"name":"Error Test Record","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Test Error Tracking package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Error Tracking Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result1\",\n \"userPrompt\": \"Say 'Success' and nothing else\"\n },\n \"name\": \"Valid Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"this-model-does-not-exist\",\n \"outputVariable\": \"result2\",\n \"userPrompt\": \"This will fail due to invalid model\"\n },\n \"name\": \"Invalid Model Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result3\",\n \"userPrompt\": \"This step should not run because previous step failed\"\n },\n \"name\": \"Should Not Execute\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Error Test Record\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Test Error Tracking require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Error Tracking Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result1\",\n \"userPrompt\": \"Say 'Success' and nothing else\"\n },\n \"name\": \"Valid Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"this-model-does-not-exist\",\n \"outputVariable\": \"result2\",\n \"userPrompt\": \"This will fail due to invalid model\"\n },\n \"name\": \"Invalid Model Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result3\",\n \"userPrompt\": \"This step should not run because previous step failed\"\n },\n \"name\": \"Should Not Execute\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Error Test Record\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Test Error Tracking import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Error Tracking Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result1\",\n \"userPrompt\": \"Say 'Success' and nothing else\"\n },\n \"name\": \"Valid Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"this-model-does-not-exist\",\n \"outputVariable\": \"result2\",\n \"userPrompt\": \"This will fail due to invalid model\"\n },\n \"name\": \"Invalid Model Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result3\",\n \"userPrompt\": \"This step should not run because previous step failed\"\n },\n \"name\": \"Should Not Execute\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Error Test Record\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Test Error Tracking request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Error Tracking Test Flow", "steps": [ { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result1", "userPrompt": "Say \'Success\' and nothing else" }, "name": "Valid Step", "type": "prompt" }, { "config": { "model": "this-model-does-not-exist", "outputVariable": "result2", "userPrompt": "This will fail due to invalid model" }, "name": "Invalid Model Step", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "result3", "userPrompt": "This step should not run because previous step failed" }, "name": "Should Not Execute", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "name": "Error Test Record", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Test Error Tracking using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Error Tracking Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result1\",\n \"userPrompt\": \"Say 'Success' and nothing else\"\n },\n \"name\": \"Valid Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"this-model-does-not-exist\",\n \"outputVariable\": \"result2\",\n \"userPrompt\": \"This will fail due to invalid model\"\n },\n \"name\": \"Invalid Model Step\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"result3\",\n \"userPrompt\": \"This step should not run because previous step failed\"\n },\n \"name\": \"Should Not Execute\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Error Test Record\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Test Error Tracking import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Error Tracking Test Flow", "steps": [ [ "config": [ "model": "gpt-3.5-turbo", "outputVariable": "result1", "userPrompt": "Say 'Success' and nothing else" ], "name": "Valid Step", "type": "prompt" ], [ "config": [ "model": "this-model-does-not-exist", "outputVariable": "result2", "userPrompt": "This will fail due to invalid model" ], "name": "Invalid Model Step", "type": "prompt" ], [ "config": [ "model": "gpt-3.5-turbo", "outputVariable": "result3", "userPrompt": "This step should not run because previous step failed" ], "name": "Should Not Execute", "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true ], "record": [ "name": "Error Test Record", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Execution Modes Overview **Request** ```json { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "existing", "streamResponse": true }, "record": { "id": "record_01k9yn1f1ff23a3thz255974ew" } } ``` **SDK Code** ```python Dispatch - Execution Modes Overview import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "existing", "streamResponse": True }, "record": { "id": "record_01k9yn1f1ff23a3thz255974ew" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Execution Modes Overview const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"id":"flow_01k9pfvrswf6d8rgm1kzcsxbcd"},"options":{"flowMode":"existing","recordMode":"existing","streamResponse":true},"record":{"id":"record_01k9yn1f1ff23a3thz255974ew"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Execution Modes Overview package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01k9yn1f1ff23a3thz255974ew\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Execution Modes Overview require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01k9yn1f1ff23a3thz255974ew\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Execution Modes Overview import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01k9yn1f1ff23a3thz255974ew\"\n }\n}") .asString(); ``` ```php Dispatch - Execution Modes Overview request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "existing", "streamResponse": true }, "record": { "id": "record_01k9yn1f1ff23a3thz255974ew" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Execution Modes Overview using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01k9yn1f1ff23a3thz255974ew\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Execution Modes Overview import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": ["id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd"], "options": [ "flowMode": "existing", "recordMode": "existing", "streamResponse": true ], "record": ["id": "record_01k9yn1f1ff23a3thz255974ew"] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Use Existing Record and Flow **Request** ```json { "flow": { "id": "flow_01jv0000000000000000000002" }, "options": { "flowMode": "existing", "modelOverride": "gpt-4-turbo", "recordMode": "existing", "streamResponse": true }, "record": { "id": "record_01jv0000000000000000000001" } } ``` **SDK Code** ```python Dispatch - Use Existing Record and Flow import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "id": "flow_01jv0000000000000000000002" }, "options": { "flowMode": "existing", "modelOverride": "gpt-4-turbo", "recordMode": "existing", "streamResponse": True }, "record": { "id": "record_01jv0000000000000000000001" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Use Existing Record and Flow const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"id":"flow_01jv0000000000000000000002"},"options":{"flowMode":"existing","modelOverride":"gpt-4-turbo","recordMode":"existing","streamResponse":true},"record":{"id":"record_01jv0000000000000000000001"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Use Existing Record and Flow package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000002\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"modelOverride\": \"gpt-4-turbo\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01jv0000000000000000000001\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Use Existing Record and Flow require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000002\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"modelOverride\": \"gpt-4-turbo\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01jv0000000000000000000001\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Use Existing Record and Flow import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000002\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"modelOverride\": \"gpt-4-turbo\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01jv0000000000000000000001\"\n }\n}") .asString(); ``` ```php Dispatch - Use Existing Record and Flow request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "id": "flow_01jv0000000000000000000002" }, "options": { "flowMode": "existing", "modelOverride": "gpt-4-turbo", "recordMode": "existing", "streamResponse": true }, "record": { "id": "record_01jv0000000000000000000001" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Use Existing Record and Flow using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"id\": \"flow_01jv0000000000000000000002\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"modelOverride\": \"gpt-4-turbo\",\n \"recordMode\": \"existing\",\n \"streamResponse\": true\n },\n \"record\": {\n \"id\": \"record_01jv0000000000000000000001\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Use Existing Record and Flow import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": ["id": "flow_01jv0000000000000000000002"], "options": [ "flowMode": "existing", "modelOverride": "gpt-4-turbo", "recordMode": "existing", "streamResponse": true ], "record": ["id": "record_01jv0000000000000000000001"] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Image Input Example **Request** ```json { "flow": { "name": "Vision Analysis Flow", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "analysis_result", "responseFormat": "json", "systemPrompt": "You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility." }, "enabled": true, "name": "Analyze Image", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...", "type": "image" }, { "text": "Please analyze this dashboard screenshot and provide feedback on:\n1. Visual hierarchy\n2. Color usage\n3. Layout and spacing\n4. Potential accessibility issues\n5. Suggestions for improvement", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "context": "UI design feedback", "task": "analyze_screenshot" }, "name": "Image Analysis Request", "type": "vision_task" } } ``` **SDK Code** ```python Dispatch - Image Input Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Vision Analysis Flow", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "analysis_result", "responseFormat": "json", "systemPrompt": "You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility." }, "enabled": True, "name": "Analyze Image", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...", "type": "image" }, { "text": "Please analyze this dashboard screenshot and provide feedback on: 1. Visual hierarchy 2. Color usage 3. Layout and spacing 4. Potential accessibility issues 5. Suggestions for improvement", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "context": "UI design feedback", "task": "analyze_screenshot" }, "name": "Image Analysis Request", "type": "vision_task" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Image Input Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Vision Analysis Flow","steps":[{"config":{"model":"claude-sonnet-4-5","outputVariable":"analysis_result","responseFormat":"json","systemPrompt":"You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility."},"enabled":true,"name":"Analyze Image","order":0,"type":"prompt"}]},"messages":[{"content":[{"image":"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...","type":"image"},{"text":"Please analyze this dashboard screenshot and provide feedback on:\n1. Visual hierarchy\n2. Color usage\n3. Layout and spacing\n4. Potential accessibility issues\n5. Suggestions for improvement","type":"text"}],"role":"user"}],"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"context":"UI design feedback","task":"analyze_screenshot"},"name":"Image Analysis Request","type":"vision_task"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Image Input Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Vision Analysis Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"analysis_result\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility.\"\n },\n \"enabled\": true,\n \"name\": \"Analyze Image\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Please analyze this dashboard screenshot and provide feedback on:\\n1. Visual hierarchy\\n2. Color usage\\n3. Layout and spacing\\n4. Potential accessibility issues\\n5. Suggestions for improvement\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"context\": \"UI design feedback\",\n \"task\": \"analyze_screenshot\"\n },\n \"name\": \"Image Analysis Request\",\n \"type\": \"vision_task\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Image Input Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Vision Analysis Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"analysis_result\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility.\"\n },\n \"enabled\": true,\n \"name\": \"Analyze Image\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Please analyze this dashboard screenshot and provide feedback on:\\n1. Visual hierarchy\\n2. Color usage\\n3. Layout and spacing\\n4. Potential accessibility issues\\n5. Suggestions for improvement\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"context\": \"UI design feedback\",\n \"task\": \"analyze_screenshot\"\n },\n \"name\": \"Image Analysis Request\",\n \"type\": \"vision_task\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Image Input Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Vision Analysis Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"analysis_result\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility.\"\n },\n \"enabled\": true,\n \"name\": \"Analyze Image\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Please analyze this dashboard screenshot and provide feedback on:\\n1. Visual hierarchy\\n2. Color usage\\n3. Layout and spacing\\n4. Potential accessibility issues\\n5. Suggestions for improvement\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"context\": \"UI design feedback\",\n \"task\": \"analyze_screenshot\"\n },\n \"name\": \"Image Analysis Request\",\n \"type\": \"vision_task\"\n }\n}") .asString(); ``` ```php Dispatch - Image Input Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Vision Analysis Flow", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "analysis_result", "responseFormat": "json", "systemPrompt": "You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility." }, "enabled": true, "name": "Analyze Image", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...", "type": "image" }, { "text": "Please analyze this dashboard screenshot and provide feedback on:\\n1. Visual hierarchy\\n2. Color usage\\n3. Layout and spacing\\n4. Potential accessibility issues\\n5. Suggestions for improvement", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "context": "UI design feedback", "task": "analyze_screenshot" }, "name": "Image Analysis Request", "type": "vision_task" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Image Input Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Vision Analysis Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"analysis_result\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility.\"\n },\n \"enabled\": true,\n \"name\": \"Analyze Image\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Please analyze this dashboard screenshot and provide feedback on:\\n1. Visual hierarchy\\n2. Color usage\\n3. Layout and spacing\\n4. Potential accessibility issues\\n5. Suggestions for improvement\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"context\": \"UI design feedback\",\n \"task\": \"analyze_screenshot\"\n },\n \"name\": \"Image Analysis Request\",\n \"type\": \"vision_task\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Image Input Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Vision Analysis Flow", "steps": [ [ "config": [ "model": "claude-sonnet-4-5", "outputVariable": "analysis_result", "responseFormat": "json", "systemPrompt": "You are a UI/UX expert. Analyze screenshots and provide detailed feedback on design, usability, and accessibility." ], "enabled": true, "name": "Analyze Image", "order": 0, "type": "prompt" ] ] ], "messages": [ [ "content": [ [ "image": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMCwsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/...", "type": "image" ], [ "text": "Please analyze this dashboard screenshot and provide feedback on: 1. Visual hierarchy 2. Color usage 3. Layout and spacing 4. Potential accessibility issues 5. Suggestions for improvement", "type": "text" ] ], "role": "user" ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "context": "UI design feedback", "task": "analyze_screenshot" ], "name": "Image Analysis Request", "type": "vision_task" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Image URL Example **Request** ```json { "flow": { "name": "Product Image Analyzer", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "productDescription", "responseFormat": "json", "systemPrompt": "You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings." }, "enabled": true, "name": "Generate Product Description", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800", "type": "image" }, { "text": "Generate a product description for this item. Include:\n1. A catchy title (max 60 chars)\n2. A detailed description (150-200 words)\n3. Key features (bullet points)\n4. Suggested tags for SEO\n\nReturn as JSON with fields: title, description, features, tags", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "category": "electronics", "product_id": "SKU-12345" }, "name": "Analyze Product Image", "type": "product_analysis" } } ``` **SDK Code** ```python Dispatch - Image URL Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Product Image Analyzer", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "productDescription", "responseFormat": "json", "systemPrompt": "You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings." }, "enabled": True, "name": "Generate Product Description", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800", "type": "image" }, { "text": "Generate a product description for this item. Include: 1. A catchy title (max 60 chars) 2. A detailed description (150-200 words) 3. Key features (bullet points) 4. Suggested tags for SEO Return as JSON with fields: title, description, features, tags", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "category": "electronics", "product_id": "SKU-12345" }, "name": "Analyze Product Image", "type": "product_analysis" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Image URL Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Product Image Analyzer","steps":[{"config":{"model":"claude-sonnet-4-5","outputVariable":"productDescription","responseFormat":"json","systemPrompt":"You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings."},"enabled":true,"name":"Generate Product Description","order":0,"type":"prompt"}]},"messages":[{"content":[{"image":"https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800","type":"image"},{"text":"Generate a product description for this item. Include:\n1. A catchy title (max 60 chars)\n2. A detailed description (150-200 words)\n3. Key features (bullet points)\n4. Suggested tags for SEO\n\nReturn as JSON with fields: title, description, features, tags","type":"text"}],"role":"user"}],"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"category":"electronics","product_id":"SKU-12345"},"name":"Analyze Product Image","type":"product_analysis"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Image URL Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Product Image Analyzer\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"productDescription\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Product Description\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Generate a product description for this item. Include:\\n1. A catchy title (max 60 chars)\\n2. A detailed description (150-200 words)\\n3. Key features (bullet points)\\n4. Suggested tags for SEO\\n\\nReturn as JSON with fields: title, description, features, tags\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"category\": \"electronics\",\n \"product_id\": \"SKU-12345\"\n },\n \"name\": \"Analyze Product Image\",\n \"type\": \"product_analysis\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Image URL Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Product Image Analyzer\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"productDescription\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Product Description\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Generate a product description for this item. Include:\\n1. A catchy title (max 60 chars)\\n2. A detailed description (150-200 words)\\n3. Key features (bullet points)\\n4. Suggested tags for SEO\\n\\nReturn as JSON with fields: title, description, features, tags\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"category\": \"electronics\",\n \"product_id\": \"SKU-12345\"\n },\n \"name\": \"Analyze Product Image\",\n \"type\": \"product_analysis\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Image URL Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Product Image Analyzer\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"productDescription\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Product Description\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Generate a product description for this item. Include:\\n1. A catchy title (max 60 chars)\\n2. A detailed description (150-200 words)\\n3. Key features (bullet points)\\n4. Suggested tags for SEO\\n\\nReturn as JSON with fields: title, description, features, tags\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"category\": \"electronics\",\n \"product_id\": \"SKU-12345\"\n },\n \"name\": \"Analyze Product Image\",\n \"type\": \"product_analysis\"\n }\n}") .asString(); ``` ```php Dispatch - Image URL Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Product Image Analyzer", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "productDescription", "responseFormat": "json", "systemPrompt": "You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings." }, "enabled": true, "name": "Generate Product Description", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800", "type": "image" }, { "text": "Generate a product description for this item. Include:\\n1. A catchy title (max 60 chars)\\n2. A detailed description (150-200 words)\\n3. Key features (bullet points)\\n4. Suggested tags for SEO\\n\\nReturn as JSON with fields: title, description, features, tags", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "category": "electronics", "product_id": "SKU-12345" }, "name": "Analyze Product Image", "type": "product_analysis" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Image URL Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Product Image Analyzer\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"productDescription\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Product Description\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Generate a product description for this item. Include:\\n1. A catchy title (max 60 chars)\\n2. A detailed description (150-200 words)\\n3. Key features (bullet points)\\n4. Suggested tags for SEO\\n\\nReturn as JSON with fields: title, description, features, tags\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"category\": \"electronics\",\n \"product_id\": \"SKU-12345\"\n },\n \"name\": \"Analyze Product Image\",\n \"type\": \"product_analysis\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Image URL Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Product Image Analyzer", "steps": [ [ "config": [ "model": "claude-sonnet-4-5", "outputVariable": "productDescription", "responseFormat": "json", "systemPrompt": "You are a product copywriter. Analyze product images and generate compelling descriptions for e-commerce listings." ], "enabled": true, "name": "Generate Product Description", "order": 0, "type": "prompt" ] ] ], "messages": [ [ "content": [ [ "image": "https://images.unsplash.com/photo-1523275335684-37898b6baf30?w=800", "type": "image" ], [ "text": "Generate a product description for this item. Include: 1. A catchy title (max 60 chars) 2. A detailed description (150-200 words) 3. Key features (bullet points) 4. Suggested tags for SEO Return as JSON with fields: title, description, features, tags", "type": "text" ] ], "role": "user" ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "category": "electronics", "product_id": "SKU-12345" ], "name": "Analyze Product Image", "type": "product_analysis" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Input Variables Example **Request** ```json { "flow": { "name": "Customer Report Generator", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "report", "responseFormat": "markdown", "userPrompt": "Create a detailed report for {{customerName}} about {{topic}}.\n\nKey metrics:\n- Revenue: ${{revenue}}\n- Growth Rate: {{growthRate}}\n- Products: {{products}}\n\nProvide insights and recommendations." }, "enabled": true, "id": "generate-report", "name": "Generate Report", "order": 1, "type": "prompt" } ] }, "inputs": { "customerName": "Acme Corporation", "growthRate": "18%", "products": [ "Widget Pro", "Widget Enterprise", "Widget Cloud" ], "revenue": 2500000, "topic": "Q4 Sales Analysis" }, "options": { "flowMode": "virtual", "streamResponse": true } } ``` **SDK Code** ```python Dispatch - Input Variables Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Customer Report Generator", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "report", "responseFormat": "markdown", "userPrompt": "Create a detailed report for {{customerName}} about {{topic}}. Key metrics: - Revenue: ${{revenue}} - Growth Rate: {{growthRate}} - Products: {{products}} Provide insights and recommendations." }, "enabled": True, "id": "generate-report", "name": "Generate Report", "order": 1, "type": "prompt" } ] }, "inputs": { "customerName": "Acme Corporation", "growthRate": "18%", "products": ["Widget Pro", "Widget Enterprise", "Widget Cloud"], "revenue": 2500000, "topic": "Q4 Sales Analysis" }, "options": { "flowMode": "virtual", "streamResponse": True } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Input Variables Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Customer Report Generator","steps":[{"config":{"model":"gpt-4o-mini","outputVariable":"report","responseFormat":"markdown","userPrompt":"Create a detailed report for {{customerName}} about {{topic}}.\n\nKey metrics:\n- Revenue: ${{revenue}}\n- Growth Rate: {{growthRate}}\n- Products: {{products}}\n\nProvide insights and recommendations."},"enabled":true,"id":"generate-report","name":"Generate Report","order":1,"type":"prompt"}]},"inputs":{"customerName":"Acme Corporation","growthRate":"18%","products":["Widget Pro","Widget Enterprise","Widget Cloud"],"revenue":2500000,"topic":"Q4 Sales Analysis"},"options":{"flowMode":"virtual","streamResponse":true}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Input Variables Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Customer Report Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"report\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Create a detailed report for {{customerName}} about {{topic}}.\\n\\nKey metrics:\\n- Revenue: ${{revenue}}\\n- Growth Rate: {{growthRate}}\\n- Products: {{products}}\\n\\nProvide insights and recommendations.\"\n },\n \"enabled\": true,\n \"id\": \"generate-report\",\n \"name\": \"Generate Report\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"inputs\": {\n \"customerName\": \"Acme Corporation\",\n \"growthRate\": \"18%\",\n \"products\": [\n \"Widget Pro\",\n \"Widget Enterprise\",\n \"Widget Cloud\"\n ],\n \"revenue\": 2500000,\n \"topic\": \"Q4 Sales Analysis\"\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Input Variables Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Customer Report Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"report\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Create a detailed report for {{customerName}} about {{topic}}.\\n\\nKey metrics:\\n- Revenue: ${{revenue}}\\n- Growth Rate: {{growthRate}}\\n- Products: {{products}}\\n\\nProvide insights and recommendations.\"\n },\n \"enabled\": true,\n \"id\": \"generate-report\",\n \"name\": \"Generate Report\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"inputs\": {\n \"customerName\": \"Acme Corporation\",\n \"growthRate\": \"18%\",\n \"products\": [\n \"Widget Pro\",\n \"Widget Enterprise\",\n \"Widget Cloud\"\n ],\n \"revenue\": 2500000,\n \"topic\": \"Q4 Sales Analysis\"\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Input Variables Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Customer Report Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"report\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Create a detailed report for {{customerName}} about {{topic}}.\\n\\nKey metrics:\\n- Revenue: ${{revenue}}\\n- Growth Rate: {{growthRate}}\\n- Products: {{products}}\\n\\nProvide insights and recommendations.\"\n },\n \"enabled\": true,\n \"id\": \"generate-report\",\n \"name\": \"Generate Report\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"inputs\": {\n \"customerName\": \"Acme Corporation\",\n \"growthRate\": \"18%\",\n \"products\": [\n \"Widget Pro\",\n \"Widget Enterprise\",\n \"Widget Cloud\"\n ],\n \"revenue\": 2500000,\n \"topic\": \"Q4 Sales Analysis\"\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") .asString(); ``` ```php Dispatch - Input Variables Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Customer Report Generator", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "report", "responseFormat": "markdown", "userPrompt": "Create a detailed report for {{customerName}} about {{topic}}.\\n\\nKey metrics:\\n- Revenue: ${{revenue}}\\n- Growth Rate: {{growthRate}}\\n- Products: {{products}}\\n\\nProvide insights and recommendations." }, "enabled": true, "id": "generate-report", "name": "Generate Report", "order": 1, "type": "prompt" } ] }, "inputs": { "customerName": "Acme Corporation", "growthRate": "18%", "products": [ "Widget Pro", "Widget Enterprise", "Widget Cloud" ], "revenue": 2500000, "topic": "Q4 Sales Analysis" }, "options": { "flowMode": "virtual", "streamResponse": true } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Input Variables Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Customer Report Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"report\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Create a detailed report for {{customerName}} about {{topic}}.\\n\\nKey metrics:\\n- Revenue: ${{revenue}}\\n- Growth Rate: {{growthRate}}\\n- Products: {{products}}\\n\\nProvide insights and recommendations.\"\n },\n \"enabled\": true,\n \"id\": \"generate-report\",\n \"name\": \"Generate Report\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"inputs\": {\n \"customerName\": \"Acme Corporation\",\n \"growthRate\": \"18%\",\n \"products\": [\n \"Widget Pro\",\n \"Widget Enterprise\",\n \"Widget Cloud\"\n ],\n \"revenue\": 2500000,\n \"topic\": \"Q4 Sales Analysis\"\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Input Variables Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Customer Report Generator", "steps": [ [ "config": [ "model": "gpt-4o-mini", "outputVariable": "report", "responseFormat": "markdown", "userPrompt": "Create a detailed report for {{customerName}} about {{topic}}. Key metrics: - Revenue: ${{revenue}} - Growth Rate: {{growthRate}} - Products: {{products}} Provide insights and recommendations." ], "enabled": true, "id": "generate-report", "name": "Generate Report", "order": 1, "type": "prompt" ] ] ], "inputs": [ "customerName": "Acme Corporation", "growthRate": "18%", "products": ["Widget Pro", "Widget Enterprise", "Widget Cloud"], "revenue": 2500000, "topic": "Q4 Sales Analysis" ], "options": [ "flowMode": "virtual", "streamResponse": true ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Marketing Demo Request **Request** ```json { "flow": { "description": "AI-powered company analysis and market insights", "name": "Company Intelligence Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "market_analysis", "responseFormat": "markdown", "userPrompt": "Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "market-analysis", "name": "Market Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "competitive_intel", "responseFormat": "text", "userPrompt": "Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "competitive-intel", "name": "Competitive Intelligence", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "recommendations", "responseFormat": "markdown", "userPrompt": "Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "recommendations", "name": "Business Recommendations", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "description": "World's largest home improvement retailer offering construction products, tools, and services", "employees": "500,000+", "founded": "1978", "industry": "Home Improvement Retail", "location": "Atlanta, GA", "stockSymbol": "HD", "website": "https://www.homedepot.com" }, "name": "The Home Depot", "type": "retail_corporation" } } ``` **SDK Code** ```python Dispatch - Marketing Demo Request import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "AI-powered company analysis and market insights", "name": "Company Intelligence Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "market_analysis", "responseFormat": "markdown", "userPrompt": "Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs." }, "enabled": True, "id": "market-analysis", "name": "Market Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "competitive_intel", "responseFormat": "text", "userPrompt": "Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs." }, "enabled": True, "id": "competitive-intel", "name": "Competitive Intelligence", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "recommendations", "responseFormat": "markdown", "userPrompt": "Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs." }, "enabled": True, "id": "recommendations", "name": "Business Recommendations", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": True }, "record": { "metadata": { "description": "World's largest home improvement retailer offering construction products, tools, and services", "employees": "500,000+", "founded": "1978", "industry": "Home Improvement Retail", "location": "Atlanta, GA", "stockSymbol": "HD", "website": "https://www.homedepot.com" }, "name": "The Home Depot", "type": "retail_corporation" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Marketing Demo Request const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"AI-powered company analysis and market insights","name":"Company Intelligence Flow","steps":[{"config":{"model":"gemini-1.5-flash","outputVariable":"market_analysis","responseFormat":"markdown","userPrompt":"Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs."},"enabled":true,"id":"market-analysis","name":"Market Analysis","order":1,"type":"prompt"},{"config":{"model":"google/gemma-4-26b-a4b-it","outputVariable":"competitive_intel","responseFormat":"text","userPrompt":"Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs."},"enabled":true,"id":"competitive-intel","name":"Competitive Intelligence","order":2,"type":"prompt"},{"config":{"model":"gemini-1.5-flash","outputVariable":"recommendations","responseFormat":"markdown","userPrompt":"Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs."},"enabled":true,"id":"recommendations","name":"Business Recommendations","order":3,"type":"prompt"}]},"options":{"flowMode":"create","recordMode":"create","streamResponse":true},"record":{"metadata":{"description":"World\'s largest home improvement retailer offering construction products, tools, and services","employees":"500,000+","founded":"1978","industry":"Home Improvement Retail","location":"Atlanta, GA","stockSymbol":"HD","website":"https://www.homedepot.com"},"name":"The Home Depot","type":"retail_corporation"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Marketing Demo Request package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"AI-powered company analysis and market insights\",\n \"name\": \"Company Intelligence Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"market_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"market-analysis\",\n \"name\": \"Market Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"competitive_intel\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"competitive-intel\",\n \"name\": \"Competitive Intelligence\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"recommendations\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"recommendations\",\n \"name\": \"Business Recommendations\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"World's largest home improvement retailer offering construction products, tools, and services\",\n \"employees\": \"500,000+\",\n \"founded\": \"1978\",\n \"industry\": \"Home Improvement Retail\",\n \"location\": \"Atlanta, GA\",\n \"stockSymbol\": \"HD\",\n \"website\": \"https://www.homedepot.com\"\n },\n \"name\": \"The Home Depot\",\n \"type\": \"retail_corporation\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Marketing Demo Request require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"AI-powered company analysis and market insights\",\n \"name\": \"Company Intelligence Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"market_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"market-analysis\",\n \"name\": \"Market Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"competitive_intel\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"competitive-intel\",\n \"name\": \"Competitive Intelligence\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"recommendations\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"recommendations\",\n \"name\": \"Business Recommendations\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"World's largest home improvement retailer offering construction products, tools, and services\",\n \"employees\": \"500,000+\",\n \"founded\": \"1978\",\n \"industry\": \"Home Improvement Retail\",\n \"location\": \"Atlanta, GA\",\n \"stockSymbol\": \"HD\",\n \"website\": \"https://www.homedepot.com\"\n },\n \"name\": \"The Home Depot\",\n \"type\": \"retail_corporation\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Marketing Demo Request import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"AI-powered company analysis and market insights\",\n \"name\": \"Company Intelligence Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"market_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"market-analysis\",\n \"name\": \"Market Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"competitive_intel\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"competitive-intel\",\n \"name\": \"Competitive Intelligence\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"recommendations\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"recommendations\",\n \"name\": \"Business Recommendations\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"World's largest home improvement retailer offering construction products, tools, and services\",\n \"employees\": \"500,000+\",\n \"founded\": \"1978\",\n \"industry\": \"Home Improvement Retail\",\n \"location\": \"Atlanta, GA\",\n \"stockSymbol\": \"HD\",\n \"website\": \"https://www.homedepot.com\"\n },\n \"name\": \"The Home Depot\",\n \"type\": \"retail_corporation\"\n }\n}") .asString(); ``` ```php Dispatch - Marketing Demo Request request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "AI-powered company analysis and market insights", "name": "Company Intelligence Flow", "steps": [ { "config": { "model": "gemini-1.5-flash", "outputVariable": "market_analysis", "responseFormat": "markdown", "userPrompt": "Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "market-analysis", "name": "Market Analysis", "order": 1, "type": "prompt" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "outputVariable": "competitive_intel", "responseFormat": "text", "userPrompt": "Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "competitive-intel", "name": "Competitive Intelligence", "order": 2, "type": "prompt" }, { "config": { "model": "gemini-1.5-flash", "outputVariable": "recommendations", "responseFormat": "markdown", "userPrompt": "Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs." }, "enabled": true, "id": "recommendations", "name": "Business Recommendations", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "metadata": { "description": "World\'s largest home improvement retailer offering construction products, tools, and services", "employees": "500,000+", "founded": "1978", "industry": "Home Improvement Retail", "location": "Atlanta, GA", "stockSymbol": "HD", "website": "https://www.homedepot.com" }, "name": "The Home Depot", "type": "retail_corporation" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Marketing Demo Request using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"AI-powered company analysis and market insights\",\n \"name\": \"Company Intelligence Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"market_analysis\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"market-analysis\",\n \"name\": \"Market Analysis\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"outputVariable\": \"competitive_intel\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"competitive-intel\",\n \"name\": \"Competitive Intelligence\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gemini-1.5-flash\",\n \"outputVariable\": \"recommendations\",\n \"responseFormat\": \"markdown\",\n \"userPrompt\": \"Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs.\"\n },\n \"enabled\": true,\n \"id\": \"recommendations\",\n \"name\": \"Business Recommendations\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"description\": \"World's largest home improvement retailer offering construction products, tools, and services\",\n \"employees\": \"500,000+\",\n \"founded\": \"1978\",\n \"industry\": \"Home Improvement Retail\",\n \"location\": \"Atlanta, GA\",\n \"stockSymbol\": \"HD\",\n \"website\": \"https://www.homedepot.com\"\n },\n \"name\": \"The Home Depot\",\n \"type\": \"retail_corporation\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Marketing Demo Request import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "AI-powered company analysis and market insights", "name": "Company Intelligence Flow", "steps": [ [ "config": [ "model": "gemini-1.5-flash", "outputVariable": "market_analysis", "responseFormat": "markdown", "userPrompt": "Analyze {{_record.name}} in the {{_record.metadata.industry}} industry. Founded in {{_record.metadata.founded}} with {{_record.metadata.employees}} employees. Provide market position insights and growth opportunities. Website: {{_record.metadata.website}}. Keep it to 2-3 paragraphs." ], "enabled": true, "id": "market-analysis", "name": "Market Analysis", "order": 1, "type": "prompt" ], [ "config": [ "model": "google/gemma-4-26b-a4b-it", "outputVariable": "competitive_intel", "responseFormat": "text", "userPrompt": "Research competitive landscape for {{_record.name}} ({{_record.metadata.description}}). Stock: {{_record.metadata.stockSymbol}}. Identify key competitors and differentiation strategies. Keep it to 2-3 paragraphs." ], "enabled": true, "id": "competitive-intel", "name": "Competitive Intelligence", "order": 2, "type": "prompt" ], [ "config": [ "model": "gemini-1.5-flash", "outputVariable": "recommendations", "responseFormat": "markdown", "userPrompt": "Generate strategic recommendations for {{_record.name}} based on their {{_record.metadata.industry}} focus and {{_record.metadata.employees}} team size. Location: {{_record.metadata.location}}. Include specific actionable insights. Keep it to 2-3 paragraphs." ], "enabled": true, "id": "recommendations", "name": "Business Recommendations", "order": 3, "type": "prompt" ] ] ], "options": [ "flowMode": "create", "recordMode": "create", "streamResponse": true ], "record": [ "metadata": [ "description": "World's largest home improvement retailer offering construction products, tools, and services", "employees": "500,000+", "founded": "1978", "industry": "Home Improvement Retail", "location": "Atlanta, GA", "stockSymbol": "HD", "website": "https://www.homedepot.com" ], "name": "The Home Depot", "type": "retail_corporation" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Messages Array Example **Request** ```json { "flow": { "name": "Support Assistant", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "assistant_response", "responseFormat": "text" }, "enabled": true, "name": "AI Assistant Response", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": "You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.", "role": "system" }, { "content": "I've been charged twice this month for my subscription. Can you help me understand what happened?", "role": "user" }, { "content": "I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?", "role": "assistant" }, { "content": "Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.", "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "customer_id": "customer_12345", "issue_type": "billing", "subscription": "enterprise" }, "name": "Customer Support Chat", "type": "conversation" } } ``` **SDK Code** ```python Dispatch - Messages Array Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Support Assistant", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "assistant_response", "responseFormat": "text" }, "enabled": True, "name": "AI Assistant Response", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": "You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.", "role": "system" }, { "content": "I've been charged twice this month for my subscription. Can you help me understand what happened?", "role": "user" }, { "content": "I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?", "role": "assistant" }, { "content": "Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.", "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "customer_id": "customer_12345", "issue_type": "billing", "subscription": "enterprise" }, "name": "Customer Support Chat", "type": "conversation" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Messages Array Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Support Assistant","steps":[{"config":{"model":"gpt-4o-mini","outputVariable":"assistant_response","responseFormat":"text"},"enabled":true,"name":"AI Assistant Response","order":0,"type":"prompt"}]},"messages":[{"content":"You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.","role":"system"},{"content":"I\'ve been charged twice this month for my subscription. Can you help me understand what happened?","role":"user"},{"content":"I sincerely apologize for the billing error. Let me look into this right away. I can see you\'re on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?","role":"assistant"},{"content":"Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.","role":"user"}],"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"customer_id":"customer_12345","issue_type":"billing","subscription":"enterprise"},"name":"Customer Support Chat","type":"conversation"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Messages Array Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Support Assistant\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"assistant_response\",\n \"responseFormat\": \"text\"\n },\n \"enabled\": true,\n \"name\": \"AI Assistant Response\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.\",\n \"role\": \"system\"\n },\n {\n \"content\": \"I've been charged twice this month for my subscription. Can you help me understand what happened?\",\n \"role\": \"user\"\n },\n {\n \"content\": \"I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?\",\n \"role\": \"assistant\"\n },\n {\n \"content\": \"Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"customer_id\": \"customer_12345\",\n \"issue_type\": \"billing\",\n \"subscription\": \"enterprise\"\n },\n \"name\": \"Customer Support Chat\",\n \"type\": \"conversation\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Messages Array Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Support Assistant\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"assistant_response\",\n \"responseFormat\": \"text\"\n },\n \"enabled\": true,\n \"name\": \"AI Assistant Response\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.\",\n \"role\": \"system\"\n },\n {\n \"content\": \"I've been charged twice this month for my subscription. Can you help me understand what happened?\",\n \"role\": \"user\"\n },\n {\n \"content\": \"I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?\",\n \"role\": \"assistant\"\n },\n {\n \"content\": \"Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"customer_id\": \"customer_12345\",\n \"issue_type\": \"billing\",\n \"subscription\": \"enterprise\"\n },\n \"name\": \"Customer Support Chat\",\n \"type\": \"conversation\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Messages Array Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Support Assistant\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"assistant_response\",\n \"responseFormat\": \"text\"\n },\n \"enabled\": true,\n \"name\": \"AI Assistant Response\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.\",\n \"role\": \"system\"\n },\n {\n \"content\": \"I've been charged twice this month for my subscription. Can you help me understand what happened?\",\n \"role\": \"user\"\n },\n {\n \"content\": \"I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?\",\n \"role\": \"assistant\"\n },\n {\n \"content\": \"Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"customer_id\": \"customer_12345\",\n \"issue_type\": \"billing\",\n \"subscription\": \"enterprise\"\n },\n \"name\": \"Customer Support Chat\",\n \"type\": \"conversation\"\n }\n}") .asString(); ``` ```php Dispatch - Messages Array Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Support Assistant", "steps": [ { "config": { "model": "gpt-4o-mini", "outputVariable": "assistant_response", "responseFormat": "text" }, "enabled": true, "name": "AI Assistant Response", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": "You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.", "role": "system" }, { "content": "I\'ve been charged twice this month for my subscription. Can you help me understand what happened?", "role": "user" }, { "content": "I sincerely apologize for the billing error. Let me look into this right away. I can see you\'re on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?", "role": "assistant" }, { "content": "Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.", "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "customer_id": "customer_12345", "issue_type": "billing", "subscription": "enterprise" }, "name": "Customer Support Chat", "type": "conversation" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Messages Array Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Support Assistant\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"assistant_response\",\n \"responseFormat\": \"text\"\n },\n \"enabled\": true,\n \"name\": \"AI Assistant Response\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.\",\n \"role\": \"system\"\n },\n {\n \"content\": \"I've been charged twice this month for my subscription. Can you help me understand what happened?\",\n \"role\": \"user\"\n },\n {\n \"content\": \"I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?\",\n \"role\": \"assistant\"\n },\n {\n \"content\": \"Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"customer_id\": \"customer_12345\",\n \"issue_type\": \"billing\",\n \"subscription\": \"enterprise\"\n },\n \"name\": \"Customer Support Chat\",\n \"type\": \"conversation\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Messages Array Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Support Assistant", "steps": [ [ "config": [ "model": "gpt-4o-mini", "outputVariable": "assistant_response", "responseFormat": "text" ], "enabled": true, "name": "AI Assistant Response", "order": 0, "type": "prompt" ] ] ], "messages": [ [ "content": "You are a helpful customer support assistant for a SaaS company. Be professional, empathetic, and solution-oriented.", "role": "system" ], [ "content": "I've been charged twice this month for my subscription. Can you help me understand what happened?", "role": "user" ], [ "content": "I sincerely apologize for the billing error. Let me look into this right away. I can see you're on our Enterprise plan. Can you provide the dates of both charges so I can verify them in our system?", "role": "assistant" ], [ "content": "Yes, I was charged on the 1st and then again on the 15th. Both charges were for $299.", "role": "user" ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "customer_id": "customer_12345", "issue_type": "billing", "subscription": "enterprise" ], "name": "Customer Support Chat", "type": "conversation" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Minimal Example **Request** ```json { "flow": { "name": "Simple Test Flow", "steps": [ { "config": { "frequencyPenalty": 0.2, "model": "gpt-3.5-turbo", "outputVariable": "response", "presencePenalty": -0.1, "seed": 123, "topK": 40, "topP": 0.9, "userPrompt": "Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}." }, "enabled": true, "id": "test-prompt", "name": "Test Prompt", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "name": "Quick Test", "type": "test" } } ``` **SDK Code** ```python Dispatch - Minimal Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Simple Test Flow", "steps": [ { "config": { "frequencyPenalty": 0.2, "model": "gpt-3.5-turbo", "outputVariable": "response", "presencePenalty": -0.1, "seed": 123, "topK": 40, "topP": 0.9, "userPrompt": "Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}." }, "enabled": True, "id": "test-prompt", "name": "Test Prompt", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": True }, "record": { "name": "Quick Test", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Minimal Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Simple Test Flow","steps":[{"config":{"frequencyPenalty":0.2,"model":"gpt-3.5-turbo","outputVariable":"response","presencePenalty":-0.1,"seed":123,"topK":40,"topP":0.9,"userPrompt":"Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}."},"enabled":true,"id":"test-prompt","name":"Test Prompt","order":1,"type":"prompt"}]},"options":{"flowMode":"create","recordMode":"create","streamResponse":true},"record":{"name":"Quick Test","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Minimal Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Simple Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"frequencyPenalty\": 0.2,\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"response\",\n \"presencePenalty\": -0.1,\n \"seed\": 123,\n \"topK\": 40,\n \"topP\": 0.9,\n \"userPrompt\": \"Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}.\"\n },\n \"enabled\": true,\n \"id\": \"test-prompt\",\n \"name\": \"Test Prompt\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Quick Test\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Minimal Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Simple Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"frequencyPenalty\": 0.2,\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"response\",\n \"presencePenalty\": -0.1,\n \"seed\": 123,\n \"topK\": 40,\n \"topP\": 0.9,\n \"userPrompt\": \"Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}.\"\n },\n \"enabled\": true,\n \"id\": \"test-prompt\",\n \"name\": \"Test Prompt\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Quick Test\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Minimal Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Simple Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"frequencyPenalty\": 0.2,\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"response\",\n \"presencePenalty\": -0.1,\n \"seed\": 123,\n \"topK\": 40,\n \"topP\": 0.9,\n \"userPrompt\": \"Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}.\"\n },\n \"enabled\": true,\n \"id\": \"test-prompt\",\n \"name\": \"Test Prompt\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Quick Test\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Minimal Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Simple Test Flow", "steps": [ { "config": { "frequencyPenalty": 0.2, "model": "gpt-3.5-turbo", "outputVariable": "response", "presencePenalty": -0.1, "seed": 123, "topK": 40, "topP": 0.9, "userPrompt": "Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}." }, "enabled": true, "id": "test-prompt", "name": "Test Prompt", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "create", "recordMode": "create", "streamResponse": true }, "record": { "name": "Quick Test", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Minimal Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Simple Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"frequencyPenalty\": 0.2,\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"response\",\n \"presencePenalty\": -0.1,\n \"seed\": 123,\n \"topK\": 40,\n \"topP\": 0.9,\n \"userPrompt\": \"Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}.\"\n },\n \"enabled\": true,\n \"id\": \"test-prompt\",\n \"name\": \"Test Prompt\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"create\",\n \"recordMode\": \"create\",\n \"streamResponse\": true\n },\n \"record\": {\n \"name\": \"Quick Test\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Minimal Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Simple Test Flow", "steps": [ [ "config": [ "frequencyPenalty": 0.2, "model": "gpt-3.5-turbo", "outputVariable": "response", "presencePenalty": -0.1, "seed": 123, "topK": 40, "topP": 0.9, "userPrompt": "Say hello to {{_record.name}}! This is flow {{_flow.name}} (ID: {{_flow.id}}) executed at {{_execution.timestamp}} by user {{_user.id}}." ], "enabled": true, "id": "test-prompt", "name": "Test Prompt", "order": 1, "type": "prompt" ] ] ], "options": [ "flowMode": "create", "recordMode": "create", "streamResponse": true ], "record": [ "name": "Quick Test", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Test Reasoning Capture **Request** ```json { "flow": { "name": "Reasoning Capture Test Flow", "steps": [ { "config": { "maxTokens": 2000, "model": "o3-mini", "outputVariable": "o3_analysis", "reasoning": true, "systemPrompt": "You are an expert problem solver. Think through problems step by step.", "temperature": 1, "userPrompt": "Solve this multi-step problem:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?\n3. Compare this to a simple interest calculation\n4. Provide a recommendation\n\nShow your reasoning process clearly." }, "name": "Complex Problem with o3-mini", "type": "prompt" }, { "config": { "maxTokens": 2000, "model": "gpt-5", "outputVariable": "gpt5_analysis", "reasoning": { "enabled": true, "reasoningEffort": "high", "reasoningSummary": "detailed" }, "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Analyze the same problem with detailed reasoning:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?" }, "name": "GPT-5 with Detailed Reasoning", "type": "prompt" }, { "config": { "maxTokens": 1000, "model": "gpt-4o", "outputVariable": "gpt4_analysis", "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Solve this multi-step problem:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?\n3. Compare this to a simple interest calculation\n4. Provide a recommendation" }, "name": "Standard Model Comparison", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "metadata": { "difficulty": "high", "problem_type": "complex_analysis" }, "name": "Reasoning Test Record", "type": "test" } } ``` **SDK Code** ```python Dispatch - Test Reasoning Capture import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Reasoning Capture Test Flow", "steps": [ { "config": { "maxTokens": 2000, "model": "o3-mini", "outputVariable": "o3_analysis", "reasoning": True, "systemPrompt": "You are an expert problem solver. Think through problems step by step.", "temperature": 1, "userPrompt": "Solve this multi-step problem: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power? 3. Compare this to a simple interest calculation 4. Provide a recommendation Show your reasoning process clearly." }, "name": "Complex Problem with o3-mini", "type": "prompt" }, { "config": { "maxTokens": 2000, "model": "gpt-5", "outputVariable": "gpt5_analysis", "reasoning": { "enabled": True, "reasoningEffort": "high", "reasoningSummary": "detailed" }, "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Analyze the same problem with detailed reasoning: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power?" }, "name": "GPT-5 with Detailed Reasoning", "type": "prompt" }, { "config": { "maxTokens": 1000, "model": "gpt-4o", "outputVariable": "gpt4_analysis", "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Solve this multi-step problem: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power? 3. Compare this to a simple interest calculation 4. Provide a recommendation" }, "name": "Standard Model Comparison", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": True, "streamResponse": True }, "record": { "metadata": { "difficulty": "high", "problem_type": "complex_analysis" }, "name": "Reasoning Test Record", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Test Reasoning Capture const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Reasoning Capture Test Flow","steps":[{"config":{"maxTokens":2000,"model":"o3-mini","outputVariable":"o3_analysis","reasoning":true,"systemPrompt":"You are an expert problem solver. Think through problems step by step.","temperature":1,"userPrompt":"Solve this multi-step problem:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?\n3. Compare this to a simple interest calculation\n4. Provide a recommendation\n\nShow your reasoning process clearly."},"name":"Complex Problem with o3-mini","type":"prompt"},{"config":{"maxTokens":2000,"model":"gpt-5","outputVariable":"gpt5_analysis","reasoning":{"enabled":true,"reasoningEffort":"high","reasoningSummary":"detailed"},"systemPrompt":"You are an expert problem solver.","temperature":0.7,"userPrompt":"Analyze the same problem with detailed reasoning:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?"},"name":"GPT-5 with Detailed Reasoning","type":"prompt"},{"config":{"maxTokens":1000,"model":"gpt-4o","outputVariable":"gpt4_analysis","systemPrompt":"You are an expert problem solver.","temperature":0.7,"userPrompt":"Solve this multi-step problem:\n\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\n2. If inflation is 2% per year, what is the real purchasing power?\n3. Compare this to a simple interest calculation\n4. Provide a recommendation"},"name":"Standard Model Comparison","type":"prompt"}]},"options":{"flowMode":"virtual","recordMode":"virtual","storeResults":true,"streamResponse":true},"record":{"metadata":{"difficulty":"high","problem_type":"complex_analysis"},"name":"Reasoning Test Record","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Test Reasoning Capture package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Reasoning Capture Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"o3-mini\",\n \"outputVariable\": \"o3_analysis\",\n \"reasoning\": true,\n \"systemPrompt\": \"You are an expert problem solver. Think through problems step by step.\",\n \"temperature\": 1,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\\n\\nShow your reasoning process clearly.\"\n },\n \"name\": \"Complex Problem with o3-mini\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"gpt-5\",\n \"outputVariable\": \"gpt5_analysis\",\n \"reasoning\": {\n \"enabled\": true,\n \"reasoningEffort\": \"high\",\n \"reasoningSummary\": \"detailed\"\n },\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the same problem with detailed reasoning:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\"\n },\n \"name\": \"GPT-5 with Detailed Reasoning\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 1000,\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"gpt4_analysis\",\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\"\n },\n \"name\": \"Standard Model Comparison\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"difficulty\": \"high\",\n \"problem_type\": \"complex_analysis\"\n },\n \"name\": \"Reasoning Test Record\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Test Reasoning Capture require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Reasoning Capture Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"o3-mini\",\n \"outputVariable\": \"o3_analysis\",\n \"reasoning\": true,\n \"systemPrompt\": \"You are an expert problem solver. Think through problems step by step.\",\n \"temperature\": 1,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\\n\\nShow your reasoning process clearly.\"\n },\n \"name\": \"Complex Problem with o3-mini\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"gpt-5\",\n \"outputVariable\": \"gpt5_analysis\",\n \"reasoning\": {\n \"enabled\": true,\n \"reasoningEffort\": \"high\",\n \"reasoningSummary\": \"detailed\"\n },\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the same problem with detailed reasoning:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\"\n },\n \"name\": \"GPT-5 with Detailed Reasoning\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 1000,\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"gpt4_analysis\",\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\"\n },\n \"name\": \"Standard Model Comparison\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"difficulty\": \"high\",\n \"problem_type\": \"complex_analysis\"\n },\n \"name\": \"Reasoning Test Record\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Test Reasoning Capture import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Reasoning Capture Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"o3-mini\",\n \"outputVariable\": \"o3_analysis\",\n \"reasoning\": true,\n \"systemPrompt\": \"You are an expert problem solver. Think through problems step by step.\",\n \"temperature\": 1,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\\n\\nShow your reasoning process clearly.\"\n },\n \"name\": \"Complex Problem with o3-mini\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"gpt-5\",\n \"outputVariable\": \"gpt5_analysis\",\n \"reasoning\": {\n \"enabled\": true,\n \"reasoningEffort\": \"high\",\n \"reasoningSummary\": \"detailed\"\n },\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the same problem with detailed reasoning:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\"\n },\n \"name\": \"GPT-5 with Detailed Reasoning\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 1000,\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"gpt4_analysis\",\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\"\n },\n \"name\": \"Standard Model Comparison\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"difficulty\": \"high\",\n \"problem_type\": \"complex_analysis\"\n },\n \"name\": \"Reasoning Test Record\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Test Reasoning Capture request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Reasoning Capture Test Flow", "steps": [ { "config": { "maxTokens": 2000, "model": "o3-mini", "outputVariable": "o3_analysis", "reasoning": true, "systemPrompt": "You are an expert problem solver. Think through problems step by step.", "temperature": 1, "userPrompt": "Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\\n\\nShow your reasoning process clearly." }, "name": "Complex Problem with o3-mini", "type": "prompt" }, { "config": { "maxTokens": 2000, "model": "gpt-5", "outputVariable": "gpt5_analysis", "reasoning": { "enabled": true, "reasoningEffort": "high", "reasoningSummary": "detailed" }, "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Analyze the same problem with detailed reasoning:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?" }, "name": "GPT-5 with Detailed Reasoning", "type": "prompt" }, { "config": { "maxTokens": 1000, "model": "gpt-4o", "outputVariable": "gpt4_analysis", "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation" }, "name": "Standard Model Comparison", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "metadata": { "difficulty": "high", "problem_type": "complex_analysis" }, "name": "Reasoning Test Record", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Test Reasoning Capture using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Reasoning Capture Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"o3-mini\",\n \"outputVariable\": \"o3_analysis\",\n \"reasoning\": true,\n \"systemPrompt\": \"You are an expert problem solver. Think through problems step by step.\",\n \"temperature\": 1,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\\n\\nShow your reasoning process clearly.\"\n },\n \"name\": \"Complex Problem with o3-mini\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 2000,\n \"model\": \"gpt-5\",\n \"outputVariable\": \"gpt5_analysis\",\n \"reasoning\": {\n \"enabled\": true,\n \"reasoningEffort\": \"high\",\n \"reasoningSummary\": \"detailed\"\n },\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the same problem with detailed reasoning:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\"\n },\n \"name\": \"GPT-5 with Detailed Reasoning\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"maxTokens\": 1000,\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"gpt4_analysis\",\n \"systemPrompt\": \"You are an expert problem solver.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Solve this multi-step problem:\\n\\n1. Calculate the compound interest on $10,000 at 5% annually for 3 years\\n2. If inflation is 2% per year, what is the real purchasing power?\\n3. Compare this to a simple interest calculation\\n4. Provide a recommendation\"\n },\n \"name\": \"Standard Model Comparison\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"difficulty\": \"high\",\n \"problem_type\": \"complex_analysis\"\n },\n \"name\": \"Reasoning Test Record\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Test Reasoning Capture import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Reasoning Capture Test Flow", "steps": [ [ "config": [ "maxTokens": 2000, "model": "o3-mini", "outputVariable": "o3_analysis", "reasoning": true, "systemPrompt": "You are an expert problem solver. Think through problems step by step.", "temperature": 1, "userPrompt": "Solve this multi-step problem: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power? 3. Compare this to a simple interest calculation 4. Provide a recommendation Show your reasoning process clearly." ], "name": "Complex Problem with o3-mini", "type": "prompt" ], [ "config": [ "maxTokens": 2000, "model": "gpt-5", "outputVariable": "gpt5_analysis", "reasoning": [ "enabled": true, "reasoningEffort": "high", "reasoningSummary": "detailed" ], "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Analyze the same problem with detailed reasoning: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power?" ], "name": "GPT-5 with Detailed Reasoning", "type": "prompt" ], [ "config": [ "maxTokens": 1000, "model": "gpt-4o", "outputVariable": "gpt4_analysis", "systemPrompt": "You are an expert problem solver.", "temperature": 0.7, "userPrompt": "Solve this multi-step problem: 1. Calculate the compound interest on $10,000 at 5% annually for 3 years 2. If inflation is 2% per year, what is the real purchasing power? 3. Compare this to a simple interest calculation 4. Provide a recommendation" ], "name": "Standard Model Comparison", "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true ], "record": [ "metadata": [ "difficulty": "high", "problem_type": "complex_analysis" ], "name": "Reasoning Test Record", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Runtime MCP Servers **Request** ```json { "flow": { "description": "Agent with access to multiple MCP servers for cross-platform automation", "name": "Multi-MCP Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.", "tools": { "maxToolCalls": 10, "mcpServers": [ { "auth": { "type": "none" }, "id": "context7", "name": "Context7 Documentation", "timeout": 30000, "transport": "streamable_http", "url": "https://mcp.context7.com/mcp" }, { "allowedTools": [ "create_page", "search_pages", "get_page" ], "auth": { "token": "YOUR_NOTION_MCP_TOKEN", "type": "bearer" }, "id": "custom_notion", "name": "Notion Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-notion-mcp-server.com/mcp" }, { "allowedTools": [ "send_message", "list_channels" ], "auth": { "headerName": "X-Slack-Token", "token": "YOUR_SLACK_BOT_TOKEN", "type": "api_key" }, "id": "custom_slack", "name": "Slack Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-slack-mcp-server.com/mcp" } ], "toolCallStrategy": "auto" }, "userPrompt": "You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}" }, "enabled": true, "id": "agent-step", "name": "Cross-Platform Agent", "order": 1, "type": "prompt" } ] }, "messages": [ { "content": "Look up the React documentation and summarize the key concepts", "role": "user" } ], "options": { "flowMode": "virtual", "streamResponse": true } } ``` **SDK Code** ```python Dispatch - Runtime MCP Servers import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "Agent with access to multiple MCP servers for cross-platform automation", "name": "Multi-MCP Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.", "tools": { "maxToolCalls": 10, "mcpServers": [ { "auth": { "type": "none" }, "id": "context7", "name": "Context7 Documentation", "timeout": 30000, "transport": "streamable_http", "url": "https://mcp.context7.com/mcp" }, { "allowedTools": ["create_page", "search_pages", "get_page"], "auth": { "token": "YOUR_NOTION_MCP_TOKEN", "type": "bearer" }, "id": "custom_notion", "name": "Notion Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-notion-mcp-server.com/mcp" }, { "allowedTools": ["send_message", "list_channels"], "auth": { "headerName": "X-Slack-Token", "token": "YOUR_SLACK_BOT_TOKEN", "type": "api_key" }, "id": "custom_slack", "name": "Slack Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-slack-mcp-server.com/mcp" } ], "toolCallStrategy": "auto" }, "userPrompt": "You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}" }, "enabled": True, "id": "agent-step", "name": "Cross-Platform Agent", "order": 1, "type": "prompt" } ] }, "messages": [ { "content": "Look up the React documentation and summarize the key concepts", "role": "user" } ], "options": { "flowMode": "virtual", "streamResponse": True } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Runtime MCP Servers const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"Agent with access to multiple MCP servers for cross-platform automation","name":"Multi-MCP Agent","steps":[{"config":{"model":"gpt-4o","outputVariable":"agent_response","systemPrompt":"You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.","tools":{"maxToolCalls":10,"mcpServers":[{"auth":{"type":"none"},"id":"context7","name":"Context7 Documentation","timeout":30000,"transport":"streamable_http","url":"https://mcp.context7.com/mcp"},{"allowedTools":["create_page","search_pages","get_page"],"auth":{"token":"YOUR_NOTION_MCP_TOKEN","type":"bearer"},"id":"custom_notion","name":"Notion Integration","timeout":30000,"transport":"streamable_http","url":"https://your-notion-mcp-server.com/mcp"},{"allowedTools":["send_message","list_channels"],"auth":{"headerName":"X-Slack-Token","token":"YOUR_SLACK_BOT_TOKEN","type":"api_key"},"id":"custom_slack","name":"Slack Integration","timeout":30000,"transport":"streamable_http","url":"https://your-slack-mcp-server.com/mcp"}],"toolCallStrategy":"auto"},"userPrompt":"You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}"},"enabled":true,"id":"agent-step","name":"Cross-Platform Agent","order":1,"type":"prompt"}]},"messages":[{"content":"Look up the React documentation and summarize the key concepts","role":"user"}],"options":{"flowMode":"virtual","streamResponse":true}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Runtime MCP Servers package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"Agent with access to multiple MCP servers for cross-platform automation\",\n \"name\": \"Multi-MCP Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.\",\n \"tools\": {\n \"maxToolCalls\": 10,\n \"mcpServers\": [\n {\n \"auth\": {\n \"type\": \"none\"\n },\n \"id\": \"context7\",\n \"name\": \"Context7 Documentation\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://mcp.context7.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"create_page\",\n \"search_pages\",\n \"get_page\"\n ],\n \"auth\": {\n \"token\": \"YOUR_NOTION_MCP_TOKEN\",\n \"type\": \"bearer\"\n },\n \"id\": \"custom_notion\",\n \"name\": \"Notion Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-notion-mcp-server.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"send_message\",\n \"list_channels\"\n ],\n \"auth\": {\n \"headerName\": \"X-Slack-Token\",\n \"token\": \"YOUR_SLACK_BOT_TOKEN\",\n \"type\": \"api_key\"\n },\n \"id\": \"custom_slack\",\n \"name\": \"Slack Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-slack-mcp-server.com/mcp\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n },\n \"userPrompt\": \"You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Cross-Platform Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"Look up the React documentation and summarize the key concepts\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Runtime MCP Servers require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"Agent with access to multiple MCP servers for cross-platform automation\",\n \"name\": \"Multi-MCP Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.\",\n \"tools\": {\n \"maxToolCalls\": 10,\n \"mcpServers\": [\n {\n \"auth\": {\n \"type\": \"none\"\n },\n \"id\": \"context7\",\n \"name\": \"Context7 Documentation\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://mcp.context7.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"create_page\",\n \"search_pages\",\n \"get_page\"\n ],\n \"auth\": {\n \"token\": \"YOUR_NOTION_MCP_TOKEN\",\n \"type\": \"bearer\"\n },\n \"id\": \"custom_notion\",\n \"name\": \"Notion Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-notion-mcp-server.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"send_message\",\n \"list_channels\"\n ],\n \"auth\": {\n \"headerName\": \"X-Slack-Token\",\n \"token\": \"YOUR_SLACK_BOT_TOKEN\",\n \"type\": \"api_key\"\n },\n \"id\": \"custom_slack\",\n \"name\": \"Slack Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-slack-mcp-server.com/mcp\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n },\n \"userPrompt\": \"You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Cross-Platform Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"Look up the React documentation and summarize the key concepts\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Runtime MCP Servers import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"Agent with access to multiple MCP servers for cross-platform automation\",\n \"name\": \"Multi-MCP Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.\",\n \"tools\": {\n \"maxToolCalls\": 10,\n \"mcpServers\": [\n {\n \"auth\": {\n \"type\": \"none\"\n },\n \"id\": \"context7\",\n \"name\": \"Context7 Documentation\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://mcp.context7.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"create_page\",\n \"search_pages\",\n \"get_page\"\n ],\n \"auth\": {\n \"token\": \"YOUR_NOTION_MCP_TOKEN\",\n \"type\": \"bearer\"\n },\n \"id\": \"custom_notion\",\n \"name\": \"Notion Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-notion-mcp-server.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"send_message\",\n \"list_channels\"\n ],\n \"auth\": {\n \"headerName\": \"X-Slack-Token\",\n \"token\": \"YOUR_SLACK_BOT_TOKEN\",\n \"type\": \"api_key\"\n },\n \"id\": \"custom_slack\",\n \"name\": \"Slack Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-slack-mcp-server.com/mcp\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n },\n \"userPrompt\": \"You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Cross-Platform Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"Look up the React documentation and summarize the key concepts\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") .asString(); ``` ```php Dispatch - Runtime MCP Servers request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "Agent with access to multiple MCP servers for cross-platform automation", "name": "Multi-MCP Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.", "tools": { "maxToolCalls": 10, "mcpServers": [ { "auth": { "type": "none" }, "id": "context7", "name": "Context7 Documentation", "timeout": 30000, "transport": "streamable_http", "url": "https://mcp.context7.com/mcp" }, { "allowedTools": [ "create_page", "search_pages", "get_page" ], "auth": { "token": "YOUR_NOTION_MCP_TOKEN", "type": "bearer" }, "id": "custom_notion", "name": "Notion Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-notion-mcp-server.com/mcp" }, { "allowedTools": [ "send_message", "list_channels" ], "auth": { "headerName": "X-Slack-Token", "token": "YOUR_SLACK_BOT_TOKEN", "type": "api_key" }, "id": "custom_slack", "name": "Slack Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-slack-mcp-server.com/mcp" } ], "toolCallStrategy": "auto" }, "userPrompt": "You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}" }, "enabled": true, "id": "agent-step", "name": "Cross-Platform Agent", "order": 1, "type": "prompt" } ] }, "messages": [ { "content": "Look up the React documentation and summarize the key concepts", "role": "user" } ], "options": { "flowMode": "virtual", "streamResponse": true } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Runtime MCP Servers using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"Agent with access to multiple MCP servers for cross-platform automation\",\n \"name\": \"Multi-MCP Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.\",\n \"tools\": {\n \"maxToolCalls\": 10,\n \"mcpServers\": [\n {\n \"auth\": {\n \"type\": \"none\"\n },\n \"id\": \"context7\",\n \"name\": \"Context7 Documentation\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://mcp.context7.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"create_page\",\n \"search_pages\",\n \"get_page\"\n ],\n \"auth\": {\n \"token\": \"YOUR_NOTION_MCP_TOKEN\",\n \"type\": \"bearer\"\n },\n \"id\": \"custom_notion\",\n \"name\": \"Notion Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-notion-mcp-server.com/mcp\"\n },\n {\n \"allowedTools\": [\n \"send_message\",\n \"list_channels\"\n ],\n \"auth\": {\n \"headerName\": \"X-Slack-Token\",\n \"token\": \"YOUR_SLACK_BOT_TOKEN\",\n \"type\": \"api_key\"\n },\n \"id\": \"custom_slack\",\n \"name\": \"Slack Integration\",\n \"timeout\": 30000,\n \"transport\": \"streamable_http\",\n \"url\": \"https://your-slack-mcp-server.com/mcp\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n },\n \"userPrompt\": \"You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Cross-Platform Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": \"Look up the React documentation and summarize the key concepts\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Runtime MCP Servers import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "Agent with access to multiple MCP servers for cross-platform automation", "name": "Multi-MCP Agent", "steps": [ [ "config": [ "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You have access to tools from multiple MCP servers. Use them appropriately to complete tasks across different platforms.", "tools": [ "maxToolCalls": 10, "mcpServers": [ [ "auth": ["type": "none"], "id": "context7", "name": "Context7 Documentation", "timeout": 30000, "transport": "streamable_http", "url": "https://mcp.context7.com/mcp" ], [ "allowedTools": ["create_page", "search_pages", "get_page"], "auth": [ "token": "YOUR_NOTION_MCP_TOKEN", "type": "bearer" ], "id": "custom_notion", "name": "Notion Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-notion-mcp-server.com/mcp" ], [ "allowedTools": ["send_message", "list_channels"], "auth": [ "headerName": "X-Slack-Token", "token": "YOUR_SLACK_BOT_TOKEN", "type": "api_key" ], "id": "custom_slack", "name": "Slack Integration", "timeout": 30000, "transport": "streamable_http", "url": "https://your-slack-mcp-server.com/mcp" ] ], "toolCallStrategy": "auto" ], "userPrompt": "You are a helpful assistant with access to multiple tools. Help the user with their request: {{userMessage}}" ], "enabled": true, "id": "agent-step", "name": "Cross-Platform Agent", "order": 1, "type": "prompt" ] ] ], "messages": [ [ "content": "Look up the React documentation and summarize the key concepts", "role": "user" ] ], "options": [ "flowMode": "virtual", "streamResponse": true ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Runtime Tools Example **Request** ```json { "flow": { "name": "AI Travel Assistant with Runtime Tools", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "weather_info", "text": "What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.", "tools": { "maxToolCalls": 5, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json" }, "method": "GET", "url": "https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY" }, "description": "Get current weather conditions for a city", "name": "get_weather", "parametersSchema": { "properties": { "city": { "description": "City name", "type": "string" }, "units": { "description": "Temperature units", "enum": [ "celsius", "fahrenheit" ], "type": "string" } }, "required": [ "city" ], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "weather-check", "name": "Get Weather Information", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "restaurants", "text": "Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json", "Authorization": "Bearer YOUR_YELP_API_KEY" }, "method": "GET", "url": "https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}" }, "description": "Search for restaurants by location and cuisine type", "name": "search_restaurants", "parametersSchema": { "properties": { "cuisine": { "description": "Type of cuisine", "type": "string" }, "location": { "description": "City or area to search", "type": "string" }, "price_range": { "description": "Price range", "enum": [ "budget", "moderate", "expensive" ], "type": "string" } }, "required": [ "location" ], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "restaurant-recommendations", "name": "Find Restaurant Recommendations", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "itinerary", "responseFormat": "markdown", "text": "Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.", "tools": { "maxToolCalls": 1, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "// Custom itinerary generation logic\nconst { destination, duration_days, interests, budget } = params;\n\nconst activities = {\n food: ['Visit local markets', 'Food tour', 'Cooking class'],\n technology: ['Tech museum', 'Innovation center', 'Electronics district'],\n culture: ['Historic temples', 'Traditional performances', 'Art galleries']\n};\n\nconst itinerary = [];\nfor (let day = 1; day <= duration_days; day++) {\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\n itinerary.push({\n day: day,\n activities: dayActivities,\n meals: ['Breakfast', 'Lunch', 'Dinner'],\n budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80'\n });\n}\n\nreturn {\n destination,\n total_days: duration_days,\n daily_plans: itinerary,\n estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}`\n};", "timeout": 5000 }, "description": "Generate a structured travel itinerary with activities and timing", "name": "generate_itinerary", "parametersSchema": { "properties": { "budget": { "description": "Budget level", "type": "string" }, "destination": { "description": "Travel destination", "type": "string" }, "duration_days": { "description": "Number of days", "type": "number" }, "interests": { "description": "Traveler interests", "items": { "type": "string" }, "type": "array" } }, "required": [ "destination", "duration_days" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "required" } }, "enabled": true, "id": "custom-itinerary", "name": "Generate Custom Itinerary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "travel_summary", "responseFormat": "json", "text": "Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.", "tools": { "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "const { weather, restaurants, itinerary, destination } = params;\n\nreturn {\n destination,\n summary: {\n weather_conditions: weather || 'Weather information pending',\n dining_options: restaurants || 'Restaurant recommendations pending',\n daily_itinerary: itinerary || 'Itinerary pending',\n booking_status: 'Ready for confirmation'\n },\n next_steps: [\n 'Review weather forecast',\n 'Make restaurant reservations',\n 'Book activities in advance',\n 'Arrange transportation'\n ],\n created_at: new Date().toISOString()\n};", "timeout": 3000 }, "description": "Format all travel information into a structured summary", "name": "format_travel_summary", "parametersSchema": { "properties": { "destination": { "type": "string" }, "itinerary": { "type": "string" }, "restaurants": { "type": "string" }, "weather": { "type": "string" } }, "required": [ "destination" ], "type": "object" }, "toolType": "custom" } ] } }, "enabled": true, "id": "booking-summary", "name": "Create Booking Summary", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "budget": "moderate", "destination": "Tokyo", "interests": [ "food", "technology", "culture" ], "travel_dates": "March 2025" }, "name": "Travel Planning Request", "type": "travel-query" } } ``` **SDK Code** ```python Dispatch - Runtime Tools Example import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "AI Travel Assistant with Runtime Tools", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "weather_info", "text": "What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.", "tools": { "maxToolCalls": 5, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json" }, "method": "GET", "url": "https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY" }, "description": "Get current weather conditions for a city", "name": "get_weather", "parametersSchema": { "properties": { "city": { "description": "City name", "type": "string" }, "units": { "description": "Temperature units", "enum": ["celsius", "fahrenheit"], "type": "string" } }, "required": ["city"], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": True, "id": "weather-check", "name": "Get Weather Information", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "restaurants", "text": "Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json", "Authorization": "Bearer YOUR_YELP_API_KEY" }, "method": "GET", "url": "https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}" }, "description": "Search for restaurants by location and cuisine type", "name": "search_restaurants", "parametersSchema": { "properties": { "cuisine": { "description": "Type of cuisine", "type": "string" }, "location": { "description": "City or area to search", "type": "string" }, "price_range": { "description": "Price range", "enum": ["budget", "moderate", "expensive"], "type": "string" } }, "required": ["location"], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": True, "id": "restaurant-recommendations", "name": "Find Restaurant Recommendations", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "itinerary", "responseFormat": "markdown", "text": "Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.", "tools": { "maxToolCalls": 1, "runtimeTools": [ { "config": { "allowedApis": ["console"], "code": "// Custom itinerary generation logic const { destination, duration_days, interests, budget } = params; const activities = { food: ['Visit local markets', 'Food tour', 'Cooking class'], technology: ['Tech museum', 'Innovation center', 'Electronics district'], culture: ['Historic temples', 'Traditional performances', 'Art galleries'] }; const itinerary = []; for (let day = 1; day <= duration_days; day++) { const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3); itinerary.push({ day: day, activities: dayActivities, meals: ['Breakfast', 'Lunch', 'Dinner'], budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80' }); } return { destination, total_days: duration_days, daily_plans: itinerary, estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}` };", "timeout": 5000 }, "description": "Generate a structured travel itinerary with activities and timing", "name": "generate_itinerary", "parametersSchema": { "properties": { "budget": { "description": "Budget level", "type": "string" }, "destination": { "description": "Travel destination", "type": "string" }, "duration_days": { "description": "Number of days", "type": "number" }, "interests": { "description": "Traveler interests", "items": { "type": "string" }, "type": "array" } }, "required": ["destination", "duration_days"], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "required" } }, "enabled": True, "id": "custom-itinerary", "name": "Generate Custom Itinerary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "travel_summary", "responseFormat": "json", "text": "Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.", "tools": { "runtimeTools": [ { "config": { "allowedApis": ["console"], "code": "const { weather, restaurants, itinerary, destination } = params; return { destination, summary: { weather_conditions: weather || 'Weather information pending', dining_options: restaurants || 'Restaurant recommendations pending', daily_itinerary: itinerary || 'Itinerary pending', booking_status: 'Ready for confirmation' }, next_steps: [ 'Review weather forecast', 'Make restaurant reservations', 'Book activities in advance', 'Arrange transportation' ], created_at: new Date().toISOString() };", "timeout": 3000 }, "description": "Format all travel information into a structured summary", "name": "format_travel_summary", "parametersSchema": { "properties": { "destination": { "type": "string" }, "itinerary": { "type": "string" }, "restaurants": { "type": "string" }, "weather": { "type": "string" } }, "required": ["destination"], "type": "object" }, "toolType": "custom" } ] } }, "enabled": True, "id": "booking-summary", "name": "Create Booking Summary", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "budget": "moderate", "destination": "Tokyo", "interests": ["food", "technology", "culture"], "travel_dates": "March 2025" }, "name": "Travel Planning Request", "type": "travel-query" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Runtime Tools Example const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"AI Travel Assistant with Runtime Tools","steps":[{"config":{"model":"gpt-4o","outputVariable":"weather_info","text":"What\'s the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.","tools":{"maxToolCalls":5,"runtimeTools":[{"config":{"headers":{"Accept":"application/json"},"method":"GET","url":"https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY"},"description":"Get current weather conditions for a city","name":"get_weather","parametersSchema":{"properties":{"city":{"description":"City name","type":"string"},"units":{"description":"Temperature units","enum":["celsius","fahrenheit"],"type":"string"}},"required":["city"],"type":"object"},"toolType":"external"}],"toolCallStrategy":"auto"}},"enabled":true,"id":"weather-check","name":"Get Weather Information","order":1,"type":"prompt"},{"config":{"model":"gpt-4o","outputVariable":"restaurants","text":"Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.","tools":{"maxToolCalls":3,"runtimeTools":[{"config":{"headers":{"Accept":"application/json","Authorization":"Bearer YOUR_YELP_API_KEY"},"method":"GET","url":"https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}"},"description":"Search for restaurants by location and cuisine type","name":"search_restaurants","parametersSchema":{"properties":{"cuisine":{"description":"Type of cuisine","type":"string"},"location":{"description":"City or area to search","type":"string"},"price_range":{"description":"Price range","enum":["budget","moderate","expensive"],"type":"string"}},"required":["location"],"type":"object"},"toolType":"external"}],"toolCallStrategy":"auto"}},"enabled":true,"id":"restaurant-recommendations","name":"Find Restaurant Recommendations","order":2,"type":"prompt"},{"config":{"model":"gpt-4o","outputVariable":"itinerary","responseFormat":"markdown","text":"Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.","tools":{"maxToolCalls":1,"runtimeTools":[{"config":{"allowedApis":["console"],"code":"// Custom itinerary generation logic\nconst { destination, duration_days, interests, budget } = params;\n\nconst activities = {\n food: [\'Visit local markets\', \'Food tour\', \'Cooking class\'],\n technology: [\'Tech museum\', \'Innovation center\', \'Electronics district\'],\n culture: [\'Historic temples\', \'Traditional performances\', \'Art galleries\']\n};\n\nconst itinerary = [];\nfor (let day = 1; day <= duration_days; day++) {\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\n itinerary.push({\n day: day,\n activities: dayActivities,\n meals: [\'Breakfast\', \'Lunch\', \'Dinner\'],\n budget_estimate: budget === \'moderate\' ? \'$100-150\' : budget === \'expensive\' ? \'$200+\' : \'$50-80\'\n });\n}\n\nreturn {\n destination,\n total_days: duration_days,\n daily_plans: itinerary,\n estimated_total_cost: budget === \'moderate\' ? `$${duration_days * 125}` : budget === \'expensive\' ? `$${duration_days * 250}` : `$${duration_days * 65}`\n};","timeout":5000},"description":"Generate a structured travel itinerary with activities and timing","name":"generate_itinerary","parametersSchema":{"properties":{"budget":{"description":"Budget level","type":"string"},"destination":{"description":"Travel destination","type":"string"},"duration_days":{"description":"Number of days","type":"number"},"interests":{"description":"Traveler interests","items":{"type":"string"},"type":"array"}},"required":["destination","duration_days"],"type":"object"},"toolType":"custom"}],"toolCallStrategy":"required"}},"enabled":true,"id":"custom-itinerary","name":"Generate Custom Itinerary","order":3,"type":"prompt"},{"config":{"model":"gpt-4o","outputVariable":"travel_summary","responseFormat":"json","text":"Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.","tools":{"runtimeTools":[{"config":{"allowedApis":["console"],"code":"const { weather, restaurants, itinerary, destination } = params;\n\nreturn {\n destination,\n summary: {\n weather_conditions: weather || \'Weather information pending\',\n dining_options: restaurants || \'Restaurant recommendations pending\',\n daily_itinerary: itinerary || \'Itinerary pending\',\n booking_status: \'Ready for confirmation\'\n },\n next_steps: [\n \'Review weather forecast\',\n \'Make restaurant reservations\',\n \'Book activities in advance\',\n \'Arrange transportation\'\n ],\n created_at: new Date().toISOString()\n};","timeout":3000},"description":"Format all travel information into a structured summary","name":"format_travel_summary","parametersSchema":{"properties":{"destination":{"type":"string"},"itinerary":{"type":"string"},"restaurants":{"type":"string"},"weather":{"type":"string"}},"required":["destination"],"type":"object"},"toolType":"custom"}]}},"enabled":true,"id":"booking-summary","name":"Create Booking Summary","order":4,"type":"prompt"}]},"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"budget":"moderate","destination":"Tokyo","interests":["food","technology","culture"],"travel_dates":"March 2025"},"name":"Travel Planning Request","type":"travel-query"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Runtime Tools Example package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"AI Travel Assistant with Runtime Tools\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"weather_info\",\n \"text\": \"What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY\"\n },\n \"description\": \"Get current weather conditions for a city\",\n \"name\": \"get_weather\",\n \"parametersSchema\": {\n \"properties\": {\n \"city\": {\n \"description\": \"City name\",\n \"type\": \"string\"\n },\n \"units\": {\n \"description\": \"Temperature units\",\n \"enum\": [\n \"celsius\",\n \"fahrenheit\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"city\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"weather-check\",\n \"name\": \"Get Weather Information\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"restaurants\",\n \"text\": \"Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_YELP_API_KEY\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}\"\n },\n \"description\": \"Search for restaurants by location and cuisine type\",\n \"name\": \"search_restaurants\",\n \"parametersSchema\": {\n \"properties\": {\n \"cuisine\": {\n \"description\": \"Type of cuisine\",\n \"type\": \"string\"\n },\n \"location\": {\n \"description\": \"City or area to search\",\n \"type\": \"string\"\n },\n \"price_range\": {\n \"description\": \"Price range\",\n \"enum\": [\n \"budget\",\n \"moderate\",\n \"expensive\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"location\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"restaurant-recommendations\",\n \"name\": \"Find Restaurant Recommendations\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"itinerary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 1,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"// Custom itinerary generation logic\\nconst { destination, duration_days, interests, budget } = params;\\n\\nconst activities = {\\n food: ['Visit local markets', 'Food tour', 'Cooking class'],\\n technology: ['Tech museum', 'Innovation center', 'Electronics district'],\\n culture: ['Historic temples', 'Traditional performances', 'Art galleries']\\n};\\n\\nconst itinerary = [];\\nfor (let day = 1; day <= duration_days; day++) {\\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\\n itinerary.push({\\n day: day,\\n activities: dayActivities,\\n meals: ['Breakfast', 'Lunch', 'Dinner'],\\n budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80'\\n });\\n}\\n\\nreturn {\\n destination,\\n total_days: duration_days,\\n daily_plans: itinerary,\\n estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}`\\n};\",\n \"timeout\": 5000\n },\n \"description\": \"Generate a structured travel itinerary with activities and timing\",\n \"name\": \"generate_itinerary\",\n \"parametersSchema\": {\n \"properties\": {\n \"budget\": {\n \"description\": \"Budget level\",\n \"type\": \"string\"\n },\n \"destination\": {\n \"description\": \"Travel destination\",\n \"type\": \"string\"\n },\n \"duration_days\": {\n \"description\": \"Number of days\",\n \"type\": \"number\"\n },\n \"interests\": {\n \"description\": \"Traveler interests\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"destination\",\n \"duration_days\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"required\"\n }\n },\n \"enabled\": true,\n \"id\": \"custom-itinerary\",\n \"name\": \"Generate Custom Itinerary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"travel_summary\",\n \"responseFormat\": \"json\",\n \"text\": \"Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.\",\n \"tools\": {\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"const { weather, restaurants, itinerary, destination } = params;\\n\\nreturn {\\n destination,\\n summary: {\\n weather_conditions: weather || 'Weather information pending',\\n dining_options: restaurants || 'Restaurant recommendations pending',\\n daily_itinerary: itinerary || 'Itinerary pending',\\n booking_status: 'Ready for confirmation'\\n },\\n next_steps: [\\n 'Review weather forecast',\\n 'Make restaurant reservations',\\n 'Book activities in advance',\\n 'Arrange transportation'\\n ],\\n created_at: new Date().toISOString()\\n};\",\n \"timeout\": 3000\n },\n \"description\": \"Format all travel information into a structured summary\",\n \"name\": \"format_travel_summary\",\n \"parametersSchema\": {\n \"properties\": {\n \"destination\": {\n \"type\": \"string\"\n },\n \"itinerary\": {\n \"type\": \"string\"\n },\n \"restaurants\": {\n \"type\": \"string\"\n },\n \"weather\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"destination\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ]\n }\n },\n \"enabled\": true,\n \"id\": \"booking-summary\",\n \"name\": \"Create Booking Summary\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"budget\": \"moderate\",\n \"destination\": \"Tokyo\",\n \"interests\": [\n \"food\",\n \"technology\",\n \"culture\"\n ],\n \"travel_dates\": \"March 2025\"\n },\n \"name\": \"Travel Planning Request\",\n \"type\": \"travel-query\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Runtime Tools Example require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"AI Travel Assistant with Runtime Tools\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"weather_info\",\n \"text\": \"What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY\"\n },\n \"description\": \"Get current weather conditions for a city\",\n \"name\": \"get_weather\",\n \"parametersSchema\": {\n \"properties\": {\n \"city\": {\n \"description\": \"City name\",\n \"type\": \"string\"\n },\n \"units\": {\n \"description\": \"Temperature units\",\n \"enum\": [\n \"celsius\",\n \"fahrenheit\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"city\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"weather-check\",\n \"name\": \"Get Weather Information\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"restaurants\",\n \"text\": \"Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_YELP_API_KEY\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}\"\n },\n \"description\": \"Search for restaurants by location and cuisine type\",\n \"name\": \"search_restaurants\",\n \"parametersSchema\": {\n \"properties\": {\n \"cuisine\": {\n \"description\": \"Type of cuisine\",\n \"type\": \"string\"\n },\n \"location\": {\n \"description\": \"City or area to search\",\n \"type\": \"string\"\n },\n \"price_range\": {\n \"description\": \"Price range\",\n \"enum\": [\n \"budget\",\n \"moderate\",\n \"expensive\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"location\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"restaurant-recommendations\",\n \"name\": \"Find Restaurant Recommendations\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"itinerary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 1,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"// Custom itinerary generation logic\\nconst { destination, duration_days, interests, budget } = params;\\n\\nconst activities = {\\n food: ['Visit local markets', 'Food tour', 'Cooking class'],\\n technology: ['Tech museum', 'Innovation center', 'Electronics district'],\\n culture: ['Historic temples', 'Traditional performances', 'Art galleries']\\n};\\n\\nconst itinerary = [];\\nfor (let day = 1; day <= duration_days; day++) {\\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\\n itinerary.push({\\n day: day,\\n activities: dayActivities,\\n meals: ['Breakfast', 'Lunch', 'Dinner'],\\n budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80'\\n });\\n}\\n\\nreturn {\\n destination,\\n total_days: duration_days,\\n daily_plans: itinerary,\\n estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}`\\n};\",\n \"timeout\": 5000\n },\n \"description\": \"Generate a structured travel itinerary with activities and timing\",\n \"name\": \"generate_itinerary\",\n \"parametersSchema\": {\n \"properties\": {\n \"budget\": {\n \"description\": \"Budget level\",\n \"type\": \"string\"\n },\n \"destination\": {\n \"description\": \"Travel destination\",\n \"type\": \"string\"\n },\n \"duration_days\": {\n \"description\": \"Number of days\",\n \"type\": \"number\"\n },\n \"interests\": {\n \"description\": \"Traveler interests\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"destination\",\n \"duration_days\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"required\"\n }\n },\n \"enabled\": true,\n \"id\": \"custom-itinerary\",\n \"name\": \"Generate Custom Itinerary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"travel_summary\",\n \"responseFormat\": \"json\",\n \"text\": \"Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.\",\n \"tools\": {\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"const { weather, restaurants, itinerary, destination } = params;\\n\\nreturn {\\n destination,\\n summary: {\\n weather_conditions: weather || 'Weather information pending',\\n dining_options: restaurants || 'Restaurant recommendations pending',\\n daily_itinerary: itinerary || 'Itinerary pending',\\n booking_status: 'Ready for confirmation'\\n },\\n next_steps: [\\n 'Review weather forecast',\\n 'Make restaurant reservations',\\n 'Book activities in advance',\\n 'Arrange transportation'\\n ],\\n created_at: new Date().toISOString()\\n};\",\n \"timeout\": 3000\n },\n \"description\": \"Format all travel information into a structured summary\",\n \"name\": \"format_travel_summary\",\n \"parametersSchema\": {\n \"properties\": {\n \"destination\": {\n \"type\": \"string\"\n },\n \"itinerary\": {\n \"type\": \"string\"\n },\n \"restaurants\": {\n \"type\": \"string\"\n },\n \"weather\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"destination\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ]\n }\n },\n \"enabled\": true,\n \"id\": \"booking-summary\",\n \"name\": \"Create Booking Summary\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"budget\": \"moderate\",\n \"destination\": \"Tokyo\",\n \"interests\": [\n \"food\",\n \"technology\",\n \"culture\"\n ],\n \"travel_dates\": \"March 2025\"\n },\n \"name\": \"Travel Planning Request\",\n \"type\": \"travel-query\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Runtime Tools Example import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"AI Travel Assistant with Runtime Tools\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"weather_info\",\n \"text\": \"What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY\"\n },\n \"description\": \"Get current weather conditions for a city\",\n \"name\": \"get_weather\",\n \"parametersSchema\": {\n \"properties\": {\n \"city\": {\n \"description\": \"City name\",\n \"type\": \"string\"\n },\n \"units\": {\n \"description\": \"Temperature units\",\n \"enum\": [\n \"celsius\",\n \"fahrenheit\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"city\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"weather-check\",\n \"name\": \"Get Weather Information\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"restaurants\",\n \"text\": \"Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_YELP_API_KEY\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}\"\n },\n \"description\": \"Search for restaurants by location and cuisine type\",\n \"name\": \"search_restaurants\",\n \"parametersSchema\": {\n \"properties\": {\n \"cuisine\": {\n \"description\": \"Type of cuisine\",\n \"type\": \"string\"\n },\n \"location\": {\n \"description\": \"City or area to search\",\n \"type\": \"string\"\n },\n \"price_range\": {\n \"description\": \"Price range\",\n \"enum\": [\n \"budget\",\n \"moderate\",\n \"expensive\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"location\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"restaurant-recommendations\",\n \"name\": \"Find Restaurant Recommendations\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"itinerary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 1,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"// Custom itinerary generation logic\\nconst { destination, duration_days, interests, budget } = params;\\n\\nconst activities = {\\n food: ['Visit local markets', 'Food tour', 'Cooking class'],\\n technology: ['Tech museum', 'Innovation center', 'Electronics district'],\\n culture: ['Historic temples', 'Traditional performances', 'Art galleries']\\n};\\n\\nconst itinerary = [];\\nfor (let day = 1; day <= duration_days; day++) {\\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\\n itinerary.push({\\n day: day,\\n activities: dayActivities,\\n meals: ['Breakfast', 'Lunch', 'Dinner'],\\n budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80'\\n });\\n}\\n\\nreturn {\\n destination,\\n total_days: duration_days,\\n daily_plans: itinerary,\\n estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}`\\n};\",\n \"timeout\": 5000\n },\n \"description\": \"Generate a structured travel itinerary with activities and timing\",\n \"name\": \"generate_itinerary\",\n \"parametersSchema\": {\n \"properties\": {\n \"budget\": {\n \"description\": \"Budget level\",\n \"type\": \"string\"\n },\n \"destination\": {\n \"description\": \"Travel destination\",\n \"type\": \"string\"\n },\n \"duration_days\": {\n \"description\": \"Number of days\",\n \"type\": \"number\"\n },\n \"interests\": {\n \"description\": \"Traveler interests\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"destination\",\n \"duration_days\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"required\"\n }\n },\n \"enabled\": true,\n \"id\": \"custom-itinerary\",\n \"name\": \"Generate Custom Itinerary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"travel_summary\",\n \"responseFormat\": \"json\",\n \"text\": \"Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.\",\n \"tools\": {\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"const { weather, restaurants, itinerary, destination } = params;\\n\\nreturn {\\n destination,\\n summary: {\\n weather_conditions: weather || 'Weather information pending',\\n dining_options: restaurants || 'Restaurant recommendations pending',\\n daily_itinerary: itinerary || 'Itinerary pending',\\n booking_status: 'Ready for confirmation'\\n },\\n next_steps: [\\n 'Review weather forecast',\\n 'Make restaurant reservations',\\n 'Book activities in advance',\\n 'Arrange transportation'\\n ],\\n created_at: new Date().toISOString()\\n};\",\n \"timeout\": 3000\n },\n \"description\": \"Format all travel information into a structured summary\",\n \"name\": \"format_travel_summary\",\n \"parametersSchema\": {\n \"properties\": {\n \"destination\": {\n \"type\": \"string\"\n },\n \"itinerary\": {\n \"type\": \"string\"\n },\n \"restaurants\": {\n \"type\": \"string\"\n },\n \"weather\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"destination\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ]\n }\n },\n \"enabled\": true,\n \"id\": \"booking-summary\",\n \"name\": \"Create Booking Summary\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"budget\": \"moderate\",\n \"destination\": \"Tokyo\",\n \"interests\": [\n \"food\",\n \"technology\",\n \"culture\"\n ],\n \"travel_dates\": \"March 2025\"\n },\n \"name\": \"Travel Planning Request\",\n \"type\": \"travel-query\"\n }\n}") .asString(); ``` ```php Dispatch - Runtime Tools Example request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "AI Travel Assistant with Runtime Tools", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "weather_info", "text": "What\'s the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.", "tools": { "maxToolCalls": 5, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json" }, "method": "GET", "url": "https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY" }, "description": "Get current weather conditions for a city", "name": "get_weather", "parametersSchema": { "properties": { "city": { "description": "City name", "type": "string" }, "units": { "description": "Temperature units", "enum": [ "celsius", "fahrenheit" ], "type": "string" } }, "required": [ "city" ], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "weather-check", "name": "Get Weather Information", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "restaurants", "text": "Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "headers": { "Accept": "application/json", "Authorization": "Bearer YOUR_YELP_API_KEY" }, "method": "GET", "url": "https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}" }, "description": "Search for restaurants by location and cuisine type", "name": "search_restaurants", "parametersSchema": { "properties": { "cuisine": { "description": "Type of cuisine", "type": "string" }, "location": { "description": "City or area to search", "type": "string" }, "price_range": { "description": "Price range", "enum": [ "budget", "moderate", "expensive" ], "type": "string" } }, "required": [ "location" ], "type": "object" }, "toolType": "external" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "restaurant-recommendations", "name": "Find Restaurant Recommendations", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "itinerary", "responseFormat": "markdown", "text": "Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.", "tools": { "maxToolCalls": 1, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "// Custom itinerary generation logic\\nconst { destination, duration_days, interests, budget } = params;\\n\\nconst activities = {\\n food: [\'Visit local markets\', \'Food tour\', \'Cooking class\'],\\n technology: [\'Tech museum\', \'Innovation center\', \'Electronics district\'],\\n culture: [\'Historic temples\', \'Traditional performances\', \'Art galleries\']\\n};\\n\\nconst itinerary = [];\\nfor (let day = 1; day <= duration_days; day++) {\\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\\n itinerary.push({\\n day: day,\\n activities: dayActivities,\\n meals: [\'Breakfast\', \'Lunch\', \'Dinner\'],\\n budget_estimate: budget === \'moderate\' ? \'$100-150\' : budget === \'expensive\' ? \'$200+\' : \'$50-80\'\\n });\\n}\\n\\nreturn {\\n destination,\\n total_days: duration_days,\\n daily_plans: itinerary,\\n estimated_total_cost: budget === \'moderate\' ? `$${duration_days * 125}` : budget === \'expensive\' ? `$${duration_days * 250}` : `$${duration_days * 65}`\\n};", "timeout": 5000 }, "description": "Generate a structured travel itinerary with activities and timing", "name": "generate_itinerary", "parametersSchema": { "properties": { "budget": { "description": "Budget level", "type": "string" }, "destination": { "description": "Travel destination", "type": "string" }, "duration_days": { "description": "Number of days", "type": "number" }, "interests": { "description": "Traveler interests", "items": { "type": "string" }, "type": "array" } }, "required": [ "destination", "duration_days" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "required" } }, "enabled": true, "id": "custom-itinerary", "name": "Generate Custom Itinerary", "order": 3, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "travel_summary", "responseFormat": "json", "text": "Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.", "tools": { "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "const { weather, restaurants, itinerary, destination } = params;\\n\\nreturn {\\n destination,\\n summary: {\\n weather_conditions: weather || \'Weather information pending\',\\n dining_options: restaurants || \'Restaurant recommendations pending\',\\n daily_itinerary: itinerary || \'Itinerary pending\',\\n booking_status: \'Ready for confirmation\'\\n },\\n next_steps: [\\n \'Review weather forecast\',\\n \'Make restaurant reservations\',\\n \'Book activities in advance\',\\n \'Arrange transportation\'\\n ],\\n created_at: new Date().toISOString()\\n};", "timeout": 3000 }, "description": "Format all travel information into a structured summary", "name": "format_travel_summary", "parametersSchema": { "properties": { "destination": { "type": "string" }, "itinerary": { "type": "string" }, "restaurants": { "type": "string" }, "weather": { "type": "string" } }, "required": [ "destination" ], "type": "object" }, "toolType": "custom" } ] } }, "enabled": true, "id": "booking-summary", "name": "Create Booking Summary", "order": 4, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "budget": "moderate", "destination": "Tokyo", "interests": [ "food", "technology", "culture" ], "travel_dates": "March 2025" }, "name": "Travel Planning Request", "type": "travel-query" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Runtime Tools Example using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"AI Travel Assistant with Runtime Tools\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"weather_info\",\n \"text\": \"What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY\"\n },\n \"description\": \"Get current weather conditions for a city\",\n \"name\": \"get_weather\",\n \"parametersSchema\": {\n \"properties\": {\n \"city\": {\n \"description\": \"City name\",\n \"type\": \"string\"\n },\n \"units\": {\n \"description\": \"Temperature units\",\n \"enum\": [\n \"celsius\",\n \"fahrenheit\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"city\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"weather-check\",\n \"name\": \"Get Weather Information\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"restaurants\",\n \"text\": \"Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"headers\": {\n \"Accept\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_YELP_API_KEY\"\n },\n \"method\": \"GET\",\n \"url\": \"https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}\"\n },\n \"description\": \"Search for restaurants by location and cuisine type\",\n \"name\": \"search_restaurants\",\n \"parametersSchema\": {\n \"properties\": {\n \"cuisine\": {\n \"description\": \"Type of cuisine\",\n \"type\": \"string\"\n },\n \"location\": {\n \"description\": \"City or area to search\",\n \"type\": \"string\"\n },\n \"price_range\": {\n \"description\": \"Price range\",\n \"enum\": [\n \"budget\",\n \"moderate\",\n \"expensive\"\n ],\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"location\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"external\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"restaurant-recommendations\",\n \"name\": \"Find Restaurant Recommendations\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"itinerary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 1,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"// Custom itinerary generation logic\\nconst { destination, duration_days, interests, budget } = params;\\n\\nconst activities = {\\n food: ['Visit local markets', 'Food tour', 'Cooking class'],\\n technology: ['Tech museum', 'Innovation center', 'Electronics district'],\\n culture: ['Historic temples', 'Traditional performances', 'Art galleries']\\n};\\n\\nconst itinerary = [];\\nfor (let day = 1; day <= duration_days; day++) {\\n const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3);\\n itinerary.push({\\n day: day,\\n activities: dayActivities,\\n meals: ['Breakfast', 'Lunch', 'Dinner'],\\n budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80'\\n });\\n}\\n\\nreturn {\\n destination,\\n total_days: duration_days,\\n daily_plans: itinerary,\\n estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}`\\n};\",\n \"timeout\": 5000\n },\n \"description\": \"Generate a structured travel itinerary with activities and timing\",\n \"name\": \"generate_itinerary\",\n \"parametersSchema\": {\n \"properties\": {\n \"budget\": {\n \"description\": \"Budget level\",\n \"type\": \"string\"\n },\n \"destination\": {\n \"description\": \"Travel destination\",\n \"type\": \"string\"\n },\n \"duration_days\": {\n \"description\": \"Number of days\",\n \"type\": \"number\"\n },\n \"interests\": {\n \"description\": \"Traveler interests\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"destination\",\n \"duration_days\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"required\"\n }\n },\n \"enabled\": true,\n \"id\": \"custom-itinerary\",\n \"name\": \"Generate Custom Itinerary\",\n \"order\": 3,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"travel_summary\",\n \"responseFormat\": \"json\",\n \"text\": \"Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.\",\n \"tools\": {\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"const { weather, restaurants, itinerary, destination } = params;\\n\\nreturn {\\n destination,\\n summary: {\\n weather_conditions: weather || 'Weather information pending',\\n dining_options: restaurants || 'Restaurant recommendations pending',\\n daily_itinerary: itinerary || 'Itinerary pending',\\n booking_status: 'Ready for confirmation'\\n },\\n next_steps: [\\n 'Review weather forecast',\\n 'Make restaurant reservations',\\n 'Book activities in advance',\\n 'Arrange transportation'\\n ],\\n created_at: new Date().toISOString()\\n};\",\n \"timeout\": 3000\n },\n \"description\": \"Format all travel information into a structured summary\",\n \"name\": \"format_travel_summary\",\n \"parametersSchema\": {\n \"properties\": {\n \"destination\": {\n \"type\": \"string\"\n },\n \"itinerary\": {\n \"type\": \"string\"\n },\n \"restaurants\": {\n \"type\": \"string\"\n },\n \"weather\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"destination\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ]\n }\n },\n \"enabled\": true,\n \"id\": \"booking-summary\",\n \"name\": \"Create Booking Summary\",\n \"order\": 4,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"budget\": \"moderate\",\n \"destination\": \"Tokyo\",\n \"interests\": [\n \"food\",\n \"technology\",\n \"culture\"\n ],\n \"travel_dates\": \"March 2025\"\n },\n \"name\": \"Travel Planning Request\",\n \"type\": \"travel-query\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Runtime Tools Example import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "AI Travel Assistant with Runtime Tools", "steps": [ [ "config": [ "model": "gpt-4o", "outputVariable": "weather_info", "text": "What's the weather like in {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}? Use the weather tool to get current conditions.", "tools": [ "maxToolCalls": 5, "runtimeTools": [ [ "config": [ "headers": ["Accept": "application/json"], "method": "GET", "url": "https://api.openweathermap.org/data/2.5/weather?q={{city}}&units={{units}}&appid=YOUR_API_KEY" ], "description": "Get current weather conditions for a city", "name": "get_weather", "parametersSchema": [ "properties": [ "city": [ "description": "City name", "type": "string" ], "units": [ "description": "Temperature units", "enum": ["celsius", "fahrenheit"], "type": "string" ] ], "required": ["city"], "type": "object" ], "toolType": "external" ] ], "toolCallStrategy": "auto" ] ], "enabled": true, "id": "weather-check", "name": "Get Weather Information", "order": 1, "type": "prompt" ], [ "config": [ "model": "gpt-4o", "outputVariable": "restaurants", "text": "Find top-rated restaurants in {{_record.metadata.destination}} that match my interests: {{_record.metadata.interests}}. Use the search tool to find real recommendations.", "tools": [ "maxToolCalls": 3, "runtimeTools": [ [ "config": [ "headers": [ "Accept": "application/json", "Authorization": "Bearer YOUR_YELP_API_KEY" ], "method": "GET", "url": "https://api.yelp.com/v3/businesses/search?location={{location}}&categories={{cuisine}}&price={{price_range}}" ], "description": "Search for restaurants by location and cuisine type", "name": "search_restaurants", "parametersSchema": [ "properties": [ "cuisine": [ "description": "Type of cuisine", "type": "string" ], "location": [ "description": "City or area to search", "type": "string" ], "price_range": [ "description": "Price range", "enum": ["budget", "moderate", "expensive"], "type": "string" ] ], "required": ["location"], "type": "object" ], "toolType": "external" ] ], "toolCallStrategy": "auto" ] ], "enabled": true, "id": "restaurant-recommendations", "name": "Find Restaurant Recommendations", "order": 2, "type": "prompt" ], [ "config": [ "model": "gpt-4o", "outputVariable": "itinerary", "responseFormat": "markdown", "text": "Create a detailed travel itinerary for {{_record.metadata.destination}} during {{_record.metadata.travel_dates}}. Budget: {{_record.metadata.budget}}. Use the itinerary generator tool.", "tools": [ "maxToolCalls": 1, "runtimeTools": [ [ "config": [ "allowedApis": ["console"], "code": "// Custom itinerary generation logic const { destination, duration_days, interests, budget } = params; const activities = { food: ['Visit local markets', 'Food tour', 'Cooking class'], technology: ['Tech museum', 'Innovation center', 'Electronics district'], culture: ['Historic temples', 'Traditional performances', 'Art galleries'] }; const itinerary = []; for (let day = 1; day <= duration_days; day++) { const dayActivities = interests.flatMap(interest => activities[interest] || []).slice(0, 3); itinerary.push({ day: day, activities: dayActivities, meals: ['Breakfast', 'Lunch', 'Dinner'], budget_estimate: budget === 'moderate' ? '$100-150' : budget === 'expensive' ? '$200+' : '$50-80' }); } return { destination, total_days: duration_days, daily_plans: itinerary, estimated_total_cost: budget === 'moderate' ? `$${duration_days * 125}` : budget === 'expensive' ? `$${duration_days * 250}` : `$${duration_days * 65}` };", "timeout": 5000 ], "description": "Generate a structured travel itinerary with activities and timing", "name": "generate_itinerary", "parametersSchema": [ "properties": [ "budget": [ "description": "Budget level", "type": "string" ], "destination": [ "description": "Travel destination", "type": "string" ], "duration_days": [ "description": "Number of days", "type": "number" ], "interests": [ "description": "Traveler interests", "items": ["type": "string"], "type": "array" ] ], "required": ["destination", "duration_days"], "type": "object" ], "toolType": "custom" ] ], "toolCallStrategy": "required" ] ], "enabled": true, "id": "custom-itinerary", "name": "Generate Custom Itinerary", "order": 3, "type": "prompt" ], [ "config": [ "model": "gpt-4o", "outputVariable": "travel_summary", "responseFormat": "json", "text": "Based on the weather info, restaurants, and itinerary, create a comprehensive travel summary for {{_record.name}}. Include weather: {{weather_info}}, dining: {{restaurants}}, and schedule: {{itinerary}}.", "tools": ["runtimeTools": [ [ "config": [ "allowedApis": ["console"], "code": "const { weather, restaurants, itinerary, destination } = params; return { destination, summary: { weather_conditions: weather || 'Weather information pending', dining_options: restaurants || 'Restaurant recommendations pending', daily_itinerary: itinerary || 'Itinerary pending', booking_status: 'Ready for confirmation' }, next_steps: [ 'Review weather forecast', 'Make restaurant reservations', 'Book activities in advance', 'Arrange transportation' ], created_at: new Date().toISOString() };", "timeout": 3000 ], "description": "Format all travel information into a structured summary", "name": "format_travel_summary", "parametersSchema": [ "properties": [ "destination": ["type": "string"], "itinerary": ["type": "string"], "restaurants": ["type": "string"], "weather": ["type": "string"] ], "required": ["destination"], "type": "object" ], "toolType": "custom" ] ]] ], "enabled": true, "id": "booking-summary", "name": "Create Booking Summary", "order": 4, "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "budget": "moderate", "destination": "Tokyo", "interests": ["food", "technology", "culture"], "travel_dates": "March 2025" ], "name": "Travel Planning Request", "type": "travel-query" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Runtime Tools Daytona Python **Request** ```json { "flow": { "name": "Python Data Analysis with Daytona", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "analysis_result", "text": "Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "import json\nimport statistics\n\n# Use sample_data parameter if provided, otherwise use default sample data\nif 'sample_data' not in dir() or not sample_data:\n sample_data = [\n {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25},\n {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30},\n {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28},\n {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32},\n {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29}\n ]\n\n# Calculate statistics for each metric\nresults = {\n 'dataset': dataset_name,\n 'metrics_analyzed': metrics,\n 'statistics': {},\n 'total_records': len(sample_data)\n}\n\nfor metric in metrics:\n values = [item[metric] for item in sample_data if metric in item]\n if values:\n results['statistics'][metric] = {\n 'mean': round(statistics.mean(values), 2),\n 'median': round(statistics.median(values), 2),\n 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\n 'min': values[0] if len(values) == 1 else min(values),\n 'max': values[0] if len(values) == 1 else max(values),\n 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\n }\n\n# Calculate correlations (simplified)\nif 'revenue' in results['statistics'] and 'units_sold' in results['statistics']:\n results['insights'] = {\n 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2),\n 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2)\n }\n\nprint(json.dumps(results, indent=2))", "language": "python", "sandboxProvider": "daytona", "timeout": 15000 }, "description": "Perform statistical analysis on sales data using Python with numpy and pandas", "name": "analyze_sales_data", "parametersSchema": { "properties": { "dataset_name": { "description": "Name of the dataset to analyze", "type": "string" }, "metrics": { "description": "List of metrics to calculate", "items": { "type": "string" }, "type": "array" }, "sample_data": { "description": "Sample data points", "items": { "properties": { "profit_margin": { "type": "number" }, "revenue": { "type": "number" }, "units_sold": { "type": "number" } }, "type": "object" }, "type": "array" } }, "required": [ "dataset_name", "metrics" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "python-analysis", "name": "Analyze Sales Data with Python", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "viz_config", "text": "Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.", "tools": { "maxToolCalls": 2, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "interface ChartDataPoint {\n label: string;\n value: number;\n}\n\ninterface ChartConfig {\n type: string;\n data: {\n labels: string[];\n datasets: Array<{\n label: string;\n data: number[];\n backgroundColor?: string[];\n borderColor?: string;\n borderWidth?: number;\n }>;\n };\n options: {\n responsive: boolean;\n plugins: {\n title: {\n display: boolean;\n text: string;\n };\n legend: {\n display: boolean;\n };\n };\n };\n}\n\n// Extract labels and values from data points\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\n\n// Generate color palette\nconst colors = [\n 'rgba(255, 99, 132, 0.8)',\n 'rgba(54, 162, 235, 0.8)',\n 'rgba(255, 206, 86, 0.8)',\n 'rgba(75, 192, 192, 0.8)',\n 'rgba(153, 102, 255, 0.8)'\n];\n\n// Build Chart.js configuration\nconst config: ChartConfig = {\n type: chart_type,\n data: {\n labels: labels,\n datasets: [{\n label: title,\n data: values,\n backgroundColor: colors.slice(0, values.length),\n borderColor: 'rgba(0, 0, 0, 0.1)',\n borderWidth: 1\n }]\n },\n options: {\n responsive: true,\n plugins: {\n title: {\n display: true,\n text: title\n },\n legend: {\n display: chart_type === 'pie' || chart_type === 'radar'\n }\n }\n }\n};\n\nconsole.log(JSON.stringify(config, null, 2));", "language": "typescript", "sandboxProvider": "daytona", "timeout": 10000 }, "description": "Generate Chart.js configuration using TypeScript for data visualization", "name": "generate_chart_config", "parametersSchema": { "properties": { "chart_type": { "description": "Type of chart to generate", "enum": [ "bar", "line", "pie", "radar" ], "type": "string" }, "data_points": { "description": "Data points for the chart", "items": { "properties": { "label": { "type": "string" }, "value": { "type": "number" } }, "type": "object" }, "type": "array" }, "title": { "description": "Chart title", "type": "string" } }, "required": [ "chart_type", "data_points", "title" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "typescript-visualization", "name": "Generate Visualization Config with TypeScript", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "executive_summary", "responseFormat": "markdown", "text": "Create an executive summary report based on:\n- Analysis: {{analysis_result}}\n- Visualization: {{viz_config}}\n\nInclude key insights, trends, and recommendations for {{_record.name}}." }, "enabled": true, "id": "summary-report", "name": "Generate Executive Summary", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "dataset": "sales_2024", "date_range": "Q1 2024", "metrics": [ "revenue", "units_sold", "profit_margin" ] }, "name": "Data Analysis Request", "type": "analysis" } } ``` **SDK Code** ```python Dispatch - Runtime Tools Daytona Python import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Python Data Analysis with Daytona", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "analysis_result", "text": "Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "allowedApis": ["console"], "code": "import json import statistics # Use sample_data parameter if provided, otherwise use default sample data if 'sample_data' not in dir() or not sample_data: sample_data = [ {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25}, {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30}, {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28}, {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32}, {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29} ] # Calculate statistics for each metric results = { 'dataset': dataset_name, 'metrics_analyzed': metrics, 'statistics': {}, 'total_records': len(sample_data) } for metric in metrics: values = [item[metric] for item in sample_data if metric in item] if values: results['statistics'][metric] = { 'mean': round(statistics.mean(values), 2), 'median': round(statistics.median(values), 2), 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0, 'min': values[0] if len(values) == 1 else min(values), 'max': values[0] if len(values) == 1 else max(values), 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values) } # Calculate correlations (simplified) if 'revenue' in results['statistics'] and 'units_sold' in results['statistics']: results['insights'] = { 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2), 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2) } print(json.dumps(results, indent=2))", "language": "python", "sandboxProvider": "daytona", "timeout": 15000 }, "description": "Perform statistical analysis on sales data using Python with numpy and pandas", "name": "analyze_sales_data", "parametersSchema": { "properties": { "dataset_name": { "description": "Name of the dataset to analyze", "type": "string" }, "metrics": { "description": "List of metrics to calculate", "items": { "type": "string" }, "type": "array" }, "sample_data": { "description": "Sample data points", "items": { "properties": { "profit_margin": { "type": "number" }, "revenue": { "type": "number" }, "units_sold": { "type": "number" } }, "type": "object" }, "type": "array" } }, "required": ["dataset_name", "metrics"], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": True, "id": "python-analysis", "name": "Analyze Sales Data with Python", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "viz_config", "text": "Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.", "tools": { "maxToolCalls": 2, "runtimeTools": [ { "config": { "allowedApis": ["console"], "code": "interface ChartDataPoint { label: string; value: number; } interface ChartConfig { type: string; data: { labels: string[]; datasets: Array<{ label: string; data: number[]; backgroundColor?: string[]; borderColor?: string; borderWidth?: number; }>; }; options: { responsive: boolean; plugins: { title: { display: boolean; text: string; }; legend: { display: boolean; }; }; }; } // Extract labels and values from data points const labels = data_points.map((dp: ChartDataPoint) => dp.label); const values = data_points.map((dp: ChartDataPoint) => dp.value); // Generate color palette const colors = [ 'rgba(255, 99, 132, 0.8)', 'rgba(54, 162, 235, 0.8)', 'rgba(255, 206, 86, 0.8)', 'rgba(75, 192, 192, 0.8)', 'rgba(153, 102, 255, 0.8)' ]; // Build Chart.js configuration const config: ChartConfig = { type: chart_type, data: { labels: labels, datasets: [{ label: title, data: values, backgroundColor: colors.slice(0, values.length), borderColor: 'rgba(0, 0, 0, 0.1)', borderWidth: 1 }] }, options: { responsive: true, plugins: { title: { display: true, text: title }, legend: { display: chart_type === 'pie' || chart_type === 'radar' } } } }; console.log(JSON.stringify(config, null, 2));", "language": "typescript", "sandboxProvider": "daytona", "timeout": 10000 }, "description": "Generate Chart.js configuration using TypeScript for data visualization", "name": "generate_chart_config", "parametersSchema": { "properties": { "chart_type": { "description": "Type of chart to generate", "enum": ["bar", "line", "pie", "radar"], "type": "string" }, "data_points": { "description": "Data points for the chart", "items": { "properties": { "label": { "type": "string" }, "value": { "type": "number" } }, "type": "object" }, "type": "array" }, "title": { "description": "Chart title", "type": "string" } }, "required": ["chart_type", "data_points", "title"], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": True, "id": "typescript-visualization", "name": "Generate Visualization Config with TypeScript", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "executive_summary", "responseFormat": "markdown", "text": "Create an executive summary report based on: - Analysis: {{analysis_result}} - Visualization: {{viz_config}} Include key insights, trends, and recommendations for {{_record.name}}." }, "enabled": True, "id": "summary-report", "name": "Generate Executive Summary", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "dataset": "sales_2024", "date_range": "Q1 2024", "metrics": ["revenue", "units_sold", "profit_margin"] }, "name": "Data Analysis Request", "type": "analysis" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Runtime Tools Daytona Python const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Python Data Analysis with Daytona","steps":[{"config":{"model":"gpt-4o","outputVariable":"analysis_result","text":"Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}","tools":{"maxToolCalls":3,"runtimeTools":[{"config":{"allowedApis":["console"],"code":"import json\nimport statistics\n\n# Use sample_data parameter if provided, otherwise use default sample data\nif \'sample_data\' not in dir() or not sample_data:\n sample_data = [\n {\'revenue\': 50000, \'units_sold\': 500, \'profit_margin\': 0.25},\n {\'revenue\': 75000, \'units_sold\': 750, \'profit_margin\': 0.30},\n {\'revenue\': 60000, \'units_sold\': 600, \'profit_margin\': 0.28},\n {\'revenue\': 90000, \'units_sold\': 900, \'profit_margin\': 0.32},\n {\'revenue\': 80000, \'units_sold\': 800, \'profit_margin\': 0.29}\n ]\n\n# Calculate statistics for each metric\nresults = {\n \'dataset\': dataset_name,\n \'metrics_analyzed\': metrics,\n \'statistics\': {},\n \'total_records\': len(sample_data)\n}\n\nfor metric in metrics:\n values = [item[metric] for item in sample_data if metric in item]\n if values:\n results[\'statistics\'][metric] = {\n \'mean\': round(statistics.mean(values), 2),\n \'median\': round(statistics.median(values), 2),\n \'stdev\': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\n \'min\': values[0] if len(values) == 1 else min(values),\n \'max\': values[0] if len(values) == 1 else max(values),\n \'total\': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\n }\n\n# Calculate correlations (simplified)\nif \'revenue\' in results[\'statistics\'] and \'units_sold\' in results[\'statistics\']:\n results[\'insights\'] = {\n \'avg_revenue_per_unit\': round(results[\'statistics\'][\'revenue\'][\'mean\'] / results[\'statistics\'][\'units_sold\'][\'mean\'], 2),\n \'revenue_volatility_percent\': round((results[\'statistics\'][\'revenue\'][\'stdev\'] / results[\'statistics\'][\'revenue\'][\'mean\']) * 100, 2)\n }\n\nprint(json.dumps(results, indent=2))","language":"python","sandboxProvider":"daytona","timeout":15000},"description":"Perform statistical analysis on sales data using Python with numpy and pandas","name":"analyze_sales_data","parametersSchema":{"properties":{"dataset_name":{"description":"Name of the dataset to analyze","type":"string"},"metrics":{"description":"List of metrics to calculate","items":{"type":"string"},"type":"array"},"sample_data":{"description":"Sample data points","items":{"properties":{"profit_margin":{"type":"number"},"revenue":{"type":"number"},"units_sold":{"type":"number"}},"type":"object"},"type":"array"}},"required":["dataset_name","metrics"],"type":"object"},"toolType":"custom"}],"toolCallStrategy":"auto"}},"enabled":true,"id":"python-analysis","name":"Analyze Sales Data with Python","order":1,"type":"prompt"},{"config":{"model":"gpt-4o","outputVariable":"viz_config","text":"Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.","tools":{"maxToolCalls":2,"runtimeTools":[{"config":{"allowedApis":["console"],"code":"interface ChartDataPoint {\n label: string;\n value: number;\n}\n\ninterface ChartConfig {\n type: string;\n data: {\n labels: string[];\n datasets: Array<{\n label: string;\n data: number[];\n backgroundColor?: string[];\n borderColor?: string;\n borderWidth?: number;\n }>;\n };\n options: {\n responsive: boolean;\n plugins: {\n title: {\n display: boolean;\n text: string;\n };\n legend: {\n display: boolean;\n };\n };\n };\n}\n\n// Extract labels and values from data points\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\n\n// Generate color palette\nconst colors = [\n \'rgba(255, 99, 132, 0.8)\',\n \'rgba(54, 162, 235, 0.8)\',\n \'rgba(255, 206, 86, 0.8)\',\n \'rgba(75, 192, 192, 0.8)\',\n \'rgba(153, 102, 255, 0.8)\'\n];\n\n// Build Chart.js configuration\nconst config: ChartConfig = {\n type: chart_type,\n data: {\n labels: labels,\n datasets: [{\n label: title,\n data: values,\n backgroundColor: colors.slice(0, values.length),\n borderColor: \'rgba(0, 0, 0, 0.1)\',\n borderWidth: 1\n }]\n },\n options: {\n responsive: true,\n plugins: {\n title: {\n display: true,\n text: title\n },\n legend: {\n display: chart_type === \'pie\' || chart_type === \'radar\'\n }\n }\n }\n};\n\nconsole.log(JSON.stringify(config, null, 2));","language":"typescript","sandboxProvider":"daytona","timeout":10000},"description":"Generate Chart.js configuration using TypeScript for data visualization","name":"generate_chart_config","parametersSchema":{"properties":{"chart_type":{"description":"Type of chart to generate","enum":["bar","line","pie","radar"],"type":"string"},"data_points":{"description":"Data points for the chart","items":{"properties":{"label":{"type":"string"},"value":{"type":"number"}},"type":"object"},"type":"array"},"title":{"description":"Chart title","type":"string"}},"required":["chart_type","data_points","title"],"type":"object"},"toolType":"custom"}],"toolCallStrategy":"auto"}},"enabled":true,"id":"typescript-visualization","name":"Generate Visualization Config with TypeScript","order":2,"type":"prompt"},{"config":{"model":"gpt-4o","outputVariable":"executive_summary","responseFormat":"markdown","text":"Create an executive summary report based on:\n- Analysis: {{analysis_result}}\n- Visualization: {{viz_config}}\n\nInclude key insights, trends, and recommendations for {{_record.name}}."},"enabled":true,"id":"summary-report","name":"Generate Executive Summary","order":3,"type":"prompt"}]},"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"dataset":"sales_2024","date_range":"Q1 2024","metrics":["revenue","units_sold","profit_margin"]},"name":"Data Analysis Request","type":"analysis"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Runtime Tools Daytona Python package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Python Data Analysis with Daytona\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"analysis_result\",\n \"text\": \"Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"import json\\nimport statistics\\n\\n# Use sample_data parameter if provided, otherwise use default sample data\\nif 'sample_data' not in dir() or not sample_data:\\n sample_data = [\\n {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25},\\n {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30},\\n {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28},\\n {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32},\\n {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29}\\n ]\\n\\n# Calculate statistics for each metric\\nresults = {\\n 'dataset': dataset_name,\\n 'metrics_analyzed': metrics,\\n 'statistics': {},\\n 'total_records': len(sample_data)\\n}\\n\\nfor metric in metrics:\\n values = [item[metric] for item in sample_data if metric in item]\\n if values:\\n results['statistics'][metric] = {\\n 'mean': round(statistics.mean(values), 2),\\n 'median': round(statistics.median(values), 2),\\n 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\\n 'min': values[0] if len(values) == 1 else min(values),\\n 'max': values[0] if len(values) == 1 else max(values),\\n 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\\n }\\n\\n# Calculate correlations (simplified)\\nif 'revenue' in results['statistics'] and 'units_sold' in results['statistics']:\\n results['insights'] = {\\n 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2),\\n 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2)\\n }\\n\\nprint(json.dumps(results, indent=2))\",\n \"language\": \"python\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 15000\n },\n \"description\": \"Perform statistical analysis on sales data using Python with numpy and pandas\",\n \"name\": \"analyze_sales_data\",\n \"parametersSchema\": {\n \"properties\": {\n \"dataset_name\": {\n \"description\": \"Name of the dataset to analyze\",\n \"type\": \"string\"\n },\n \"metrics\": {\n \"description\": \"List of metrics to calculate\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n },\n \"sample_data\": {\n \"description\": \"Sample data points\",\n \"items\": {\n \"properties\": {\n \"profit_margin\": {\n \"type\": \"number\"\n },\n \"revenue\": {\n \"type\": \"number\"\n },\n \"units_sold\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"dataset_name\",\n \"metrics\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"python-analysis\",\n \"name\": \"Analyze Sales Data with Python\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"viz_config\",\n \"text\": \"Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 2,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"interface ChartDataPoint {\\n label: string;\\n value: number;\\n}\\n\\ninterface ChartConfig {\\n type: string;\\n data: {\\n labels: string[];\\n datasets: Array<{\\n label: string;\\n data: number[];\\n backgroundColor?: string[];\\n borderColor?: string;\\n borderWidth?: number;\\n }>;\\n };\\n options: {\\n responsive: boolean;\\n plugins: {\\n title: {\\n display: boolean;\\n text: string;\\n };\\n legend: {\\n display: boolean;\\n };\\n };\\n };\\n}\\n\\n// Extract labels and values from data points\\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\\n\\n// Generate color palette\\nconst colors = [\\n 'rgba(255, 99, 132, 0.8)',\\n 'rgba(54, 162, 235, 0.8)',\\n 'rgba(255, 206, 86, 0.8)',\\n 'rgba(75, 192, 192, 0.8)',\\n 'rgba(153, 102, 255, 0.8)'\\n];\\n\\n// Build Chart.js configuration\\nconst config: ChartConfig = {\\n type: chart_type,\\n data: {\\n labels: labels,\\n datasets: [{\\n label: title,\\n data: values,\\n backgroundColor: colors.slice(0, values.length),\\n borderColor: 'rgba(0, 0, 0, 0.1)',\\n borderWidth: 1\\n }]\\n },\\n options: {\\n responsive: true,\\n plugins: {\\n title: {\\n display: true,\\n text: title\\n },\\n legend: {\\n display: chart_type === 'pie' || chart_type === 'radar'\\n }\\n }\\n }\\n};\\n\\nconsole.log(JSON.stringify(config, null, 2));\",\n \"language\": \"typescript\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 10000\n },\n \"description\": \"Generate Chart.js configuration using TypeScript for data visualization\",\n \"name\": \"generate_chart_config\",\n \"parametersSchema\": {\n \"properties\": {\n \"chart_type\": {\n \"description\": \"Type of chart to generate\",\n \"enum\": [\n \"bar\",\n \"line\",\n \"pie\",\n \"radar\"\n ],\n \"type\": \"string\"\n },\n \"data_points\": {\n \"description\": \"Data points for the chart\",\n \"items\": {\n \"properties\": {\n \"label\": {\n \"type\": \"string\"\n },\n \"value\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n },\n \"title\": {\n \"description\": \"Chart title\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"chart_type\",\n \"data_points\",\n \"title\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"typescript-visualization\",\n \"name\": \"Generate Visualization Config with TypeScript\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create an executive summary report based on:\\n- Analysis: {{analysis_result}}\\n- Visualization: {{viz_config}}\\n\\nInclude key insights, trends, and recommendations for {{_record.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"summary-report\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"dataset\": \"sales_2024\",\n \"date_range\": \"Q1 2024\",\n \"metrics\": [\n \"revenue\",\n \"units_sold\",\n \"profit_margin\"\n ]\n },\n \"name\": \"Data Analysis Request\",\n \"type\": \"analysis\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Runtime Tools Daytona Python require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Python Data Analysis with Daytona\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"analysis_result\",\n \"text\": \"Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"import json\\nimport statistics\\n\\n# Use sample_data parameter if provided, otherwise use default sample data\\nif 'sample_data' not in dir() or not sample_data:\\n sample_data = [\\n {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25},\\n {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30},\\n {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28},\\n {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32},\\n {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29}\\n ]\\n\\n# Calculate statistics for each metric\\nresults = {\\n 'dataset': dataset_name,\\n 'metrics_analyzed': metrics,\\n 'statistics': {},\\n 'total_records': len(sample_data)\\n}\\n\\nfor metric in metrics:\\n values = [item[metric] for item in sample_data if metric in item]\\n if values:\\n results['statistics'][metric] = {\\n 'mean': round(statistics.mean(values), 2),\\n 'median': round(statistics.median(values), 2),\\n 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\\n 'min': values[0] if len(values) == 1 else min(values),\\n 'max': values[0] if len(values) == 1 else max(values),\\n 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\\n }\\n\\n# Calculate correlations (simplified)\\nif 'revenue' in results['statistics'] and 'units_sold' in results['statistics']:\\n results['insights'] = {\\n 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2),\\n 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2)\\n }\\n\\nprint(json.dumps(results, indent=2))\",\n \"language\": \"python\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 15000\n },\n \"description\": \"Perform statistical analysis on sales data using Python with numpy and pandas\",\n \"name\": \"analyze_sales_data\",\n \"parametersSchema\": {\n \"properties\": {\n \"dataset_name\": {\n \"description\": \"Name of the dataset to analyze\",\n \"type\": \"string\"\n },\n \"metrics\": {\n \"description\": \"List of metrics to calculate\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n },\n \"sample_data\": {\n \"description\": \"Sample data points\",\n \"items\": {\n \"properties\": {\n \"profit_margin\": {\n \"type\": \"number\"\n },\n \"revenue\": {\n \"type\": \"number\"\n },\n \"units_sold\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"dataset_name\",\n \"metrics\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"python-analysis\",\n \"name\": \"Analyze Sales Data with Python\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"viz_config\",\n \"text\": \"Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 2,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"interface ChartDataPoint {\\n label: string;\\n value: number;\\n}\\n\\ninterface ChartConfig {\\n type: string;\\n data: {\\n labels: string[];\\n datasets: Array<{\\n label: string;\\n data: number[];\\n backgroundColor?: string[];\\n borderColor?: string;\\n borderWidth?: number;\\n }>;\\n };\\n options: {\\n responsive: boolean;\\n plugins: {\\n title: {\\n display: boolean;\\n text: string;\\n };\\n legend: {\\n display: boolean;\\n };\\n };\\n };\\n}\\n\\n// Extract labels and values from data points\\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\\n\\n// Generate color palette\\nconst colors = [\\n 'rgba(255, 99, 132, 0.8)',\\n 'rgba(54, 162, 235, 0.8)',\\n 'rgba(255, 206, 86, 0.8)',\\n 'rgba(75, 192, 192, 0.8)',\\n 'rgba(153, 102, 255, 0.8)'\\n];\\n\\n// Build Chart.js configuration\\nconst config: ChartConfig = {\\n type: chart_type,\\n data: {\\n labels: labels,\\n datasets: [{\\n label: title,\\n data: values,\\n backgroundColor: colors.slice(0, values.length),\\n borderColor: 'rgba(0, 0, 0, 0.1)',\\n borderWidth: 1\\n }]\\n },\\n options: {\\n responsive: true,\\n plugins: {\\n title: {\\n display: true,\\n text: title\\n },\\n legend: {\\n display: chart_type === 'pie' || chart_type === 'radar'\\n }\\n }\\n }\\n};\\n\\nconsole.log(JSON.stringify(config, null, 2));\",\n \"language\": \"typescript\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 10000\n },\n \"description\": \"Generate Chart.js configuration using TypeScript for data visualization\",\n \"name\": \"generate_chart_config\",\n \"parametersSchema\": {\n \"properties\": {\n \"chart_type\": {\n \"description\": \"Type of chart to generate\",\n \"enum\": [\n \"bar\",\n \"line\",\n \"pie\",\n \"radar\"\n ],\n \"type\": \"string\"\n },\n \"data_points\": {\n \"description\": \"Data points for the chart\",\n \"items\": {\n \"properties\": {\n \"label\": {\n \"type\": \"string\"\n },\n \"value\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n },\n \"title\": {\n \"description\": \"Chart title\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"chart_type\",\n \"data_points\",\n \"title\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"typescript-visualization\",\n \"name\": \"Generate Visualization Config with TypeScript\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create an executive summary report based on:\\n- Analysis: {{analysis_result}}\\n- Visualization: {{viz_config}}\\n\\nInclude key insights, trends, and recommendations for {{_record.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"summary-report\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"dataset\": \"sales_2024\",\n \"date_range\": \"Q1 2024\",\n \"metrics\": [\n \"revenue\",\n \"units_sold\",\n \"profit_margin\"\n ]\n },\n \"name\": \"Data Analysis Request\",\n \"type\": \"analysis\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Runtime Tools Daytona Python import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Python Data Analysis with Daytona\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"analysis_result\",\n \"text\": \"Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"import json\\nimport statistics\\n\\n# Use sample_data parameter if provided, otherwise use default sample data\\nif 'sample_data' not in dir() or not sample_data:\\n sample_data = [\\n {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25},\\n {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30},\\n {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28},\\n {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32},\\n {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29}\\n ]\\n\\n# Calculate statistics for each metric\\nresults = {\\n 'dataset': dataset_name,\\n 'metrics_analyzed': metrics,\\n 'statistics': {},\\n 'total_records': len(sample_data)\\n}\\n\\nfor metric in metrics:\\n values = [item[metric] for item in sample_data if metric in item]\\n if values:\\n results['statistics'][metric] = {\\n 'mean': round(statistics.mean(values), 2),\\n 'median': round(statistics.median(values), 2),\\n 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\\n 'min': values[0] if len(values) == 1 else min(values),\\n 'max': values[0] if len(values) == 1 else max(values),\\n 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\\n }\\n\\n# Calculate correlations (simplified)\\nif 'revenue' in results['statistics'] and 'units_sold' in results['statistics']:\\n results['insights'] = {\\n 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2),\\n 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2)\\n }\\n\\nprint(json.dumps(results, indent=2))\",\n \"language\": \"python\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 15000\n },\n \"description\": \"Perform statistical analysis on sales data using Python with numpy and pandas\",\n \"name\": \"analyze_sales_data\",\n \"parametersSchema\": {\n \"properties\": {\n \"dataset_name\": {\n \"description\": \"Name of the dataset to analyze\",\n \"type\": \"string\"\n },\n \"metrics\": {\n \"description\": \"List of metrics to calculate\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n },\n \"sample_data\": {\n \"description\": \"Sample data points\",\n \"items\": {\n \"properties\": {\n \"profit_margin\": {\n \"type\": \"number\"\n },\n \"revenue\": {\n \"type\": \"number\"\n },\n \"units_sold\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"dataset_name\",\n \"metrics\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"python-analysis\",\n \"name\": \"Analyze Sales Data with Python\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"viz_config\",\n \"text\": \"Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 2,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"interface ChartDataPoint {\\n label: string;\\n value: number;\\n}\\n\\ninterface ChartConfig {\\n type: string;\\n data: {\\n labels: string[];\\n datasets: Array<{\\n label: string;\\n data: number[];\\n backgroundColor?: string[];\\n borderColor?: string;\\n borderWidth?: number;\\n }>;\\n };\\n options: {\\n responsive: boolean;\\n plugins: {\\n title: {\\n display: boolean;\\n text: string;\\n };\\n legend: {\\n display: boolean;\\n };\\n };\\n };\\n}\\n\\n// Extract labels and values from data points\\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\\n\\n// Generate color palette\\nconst colors = [\\n 'rgba(255, 99, 132, 0.8)',\\n 'rgba(54, 162, 235, 0.8)',\\n 'rgba(255, 206, 86, 0.8)',\\n 'rgba(75, 192, 192, 0.8)',\\n 'rgba(153, 102, 255, 0.8)'\\n];\\n\\n// Build Chart.js configuration\\nconst config: ChartConfig = {\\n type: chart_type,\\n data: {\\n labels: labels,\\n datasets: [{\\n label: title,\\n data: values,\\n backgroundColor: colors.slice(0, values.length),\\n borderColor: 'rgba(0, 0, 0, 0.1)',\\n borderWidth: 1\\n }]\\n },\\n options: {\\n responsive: true,\\n plugins: {\\n title: {\\n display: true,\\n text: title\\n },\\n legend: {\\n display: chart_type === 'pie' || chart_type === 'radar'\\n }\\n }\\n }\\n};\\n\\nconsole.log(JSON.stringify(config, null, 2));\",\n \"language\": \"typescript\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 10000\n },\n \"description\": \"Generate Chart.js configuration using TypeScript for data visualization\",\n \"name\": \"generate_chart_config\",\n \"parametersSchema\": {\n \"properties\": {\n \"chart_type\": {\n \"description\": \"Type of chart to generate\",\n \"enum\": [\n \"bar\",\n \"line\",\n \"pie\",\n \"radar\"\n ],\n \"type\": \"string\"\n },\n \"data_points\": {\n \"description\": \"Data points for the chart\",\n \"items\": {\n \"properties\": {\n \"label\": {\n \"type\": \"string\"\n },\n \"value\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n },\n \"title\": {\n \"description\": \"Chart title\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"chart_type\",\n \"data_points\",\n \"title\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"typescript-visualization\",\n \"name\": \"Generate Visualization Config with TypeScript\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create an executive summary report based on:\\n- Analysis: {{analysis_result}}\\n- Visualization: {{viz_config}}\\n\\nInclude key insights, trends, and recommendations for {{_record.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"summary-report\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"dataset\": \"sales_2024\",\n \"date_range\": \"Q1 2024\",\n \"metrics\": [\n \"revenue\",\n \"units_sold\",\n \"profit_margin\"\n ]\n },\n \"name\": \"Data Analysis Request\",\n \"type\": \"analysis\"\n }\n}") .asString(); ``` ```php Dispatch - Runtime Tools Daytona Python request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Python Data Analysis with Daytona", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "analysis_result", "text": "Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}", "tools": { "maxToolCalls": 3, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "import json\\nimport statistics\\n\\n# Use sample_data parameter if provided, otherwise use default sample data\\nif \'sample_data\' not in dir() or not sample_data:\\n sample_data = [\\n {\'revenue\': 50000, \'units_sold\': 500, \'profit_margin\': 0.25},\\n {\'revenue\': 75000, \'units_sold\': 750, \'profit_margin\': 0.30},\\n {\'revenue\': 60000, \'units_sold\': 600, \'profit_margin\': 0.28},\\n {\'revenue\': 90000, \'units_sold\': 900, \'profit_margin\': 0.32},\\n {\'revenue\': 80000, \'units_sold\': 800, \'profit_margin\': 0.29}\\n ]\\n\\n# Calculate statistics for each metric\\nresults = {\\n \'dataset\': dataset_name,\\n \'metrics_analyzed\': metrics,\\n \'statistics\': {},\\n \'total_records\': len(sample_data)\\n}\\n\\nfor metric in metrics:\\n values = [item[metric] for item in sample_data if metric in item]\\n if values:\\n results[\'statistics\'][metric] = {\\n \'mean\': round(statistics.mean(values), 2),\\n \'median\': round(statistics.median(values), 2),\\n \'stdev\': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\\n \'min\': values[0] if len(values) == 1 else min(values),\\n \'max\': values[0] if len(values) == 1 else max(values),\\n \'total\': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\\n }\\n\\n# Calculate correlations (simplified)\\nif \'revenue\' in results[\'statistics\'] and \'units_sold\' in results[\'statistics\']:\\n results[\'insights\'] = {\\n \'avg_revenue_per_unit\': round(results[\'statistics\'][\'revenue\'][\'mean\'] / results[\'statistics\'][\'units_sold\'][\'mean\'], 2),\\n \'revenue_volatility_percent\': round((results[\'statistics\'][\'revenue\'][\'stdev\'] / results[\'statistics\'][\'revenue\'][\'mean\']) * 100, 2)\\n }\\n\\nprint(json.dumps(results, indent=2))", "language": "python", "sandboxProvider": "daytona", "timeout": 15000 }, "description": "Perform statistical analysis on sales data using Python with numpy and pandas", "name": "analyze_sales_data", "parametersSchema": { "properties": { "dataset_name": { "description": "Name of the dataset to analyze", "type": "string" }, "metrics": { "description": "List of metrics to calculate", "items": { "type": "string" }, "type": "array" }, "sample_data": { "description": "Sample data points", "items": { "properties": { "profit_margin": { "type": "number" }, "revenue": { "type": "number" }, "units_sold": { "type": "number" } }, "type": "object" }, "type": "array" } }, "required": [ "dataset_name", "metrics" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "python-analysis", "name": "Analyze Sales Data with Python", "order": 1, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "viz_config", "text": "Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.", "tools": { "maxToolCalls": 2, "runtimeTools": [ { "config": { "allowedApis": [ "console" ], "code": "interface ChartDataPoint {\\n label: string;\\n value: number;\\n}\\n\\ninterface ChartConfig {\\n type: string;\\n data: {\\n labels: string[];\\n datasets: Array<{\\n label: string;\\n data: number[];\\n backgroundColor?: string[];\\n borderColor?: string;\\n borderWidth?: number;\\n }>;\\n };\\n options: {\\n responsive: boolean;\\n plugins: {\\n title: {\\n display: boolean;\\n text: string;\\n };\\n legend: {\\n display: boolean;\\n };\\n };\\n };\\n}\\n\\n// Extract labels and values from data points\\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\\n\\n// Generate color palette\\nconst colors = [\\n \'rgba(255, 99, 132, 0.8)\',\\n \'rgba(54, 162, 235, 0.8)\',\\n \'rgba(255, 206, 86, 0.8)\',\\n \'rgba(75, 192, 192, 0.8)\',\\n \'rgba(153, 102, 255, 0.8)\'\\n];\\n\\n// Build Chart.js configuration\\nconst config: ChartConfig = {\\n type: chart_type,\\n data: {\\n labels: labels,\\n datasets: [{\\n label: title,\\n data: values,\\n backgroundColor: colors.slice(0, values.length),\\n borderColor: \'rgba(0, 0, 0, 0.1)\',\\n borderWidth: 1\\n }]\\n },\\n options: {\\n responsive: true,\\n plugins: {\\n title: {\\n display: true,\\n text: title\\n },\\n legend: {\\n display: chart_type === \'pie\' || chart_type === \'radar\'\\n }\\n }\\n }\\n};\\n\\nconsole.log(JSON.stringify(config, null, 2));", "language": "typescript", "sandboxProvider": "daytona", "timeout": 10000 }, "description": "Generate Chart.js configuration using TypeScript for data visualization", "name": "generate_chart_config", "parametersSchema": { "properties": { "chart_type": { "description": "Type of chart to generate", "enum": [ "bar", "line", "pie", "radar" ], "type": "string" }, "data_points": { "description": "Data points for the chart", "items": { "properties": { "label": { "type": "string" }, "value": { "type": "number" } }, "type": "object" }, "type": "array" }, "title": { "description": "Chart title", "type": "string" } }, "required": [ "chart_type", "data_points", "title" ], "type": "object" }, "toolType": "custom" } ], "toolCallStrategy": "auto" } }, "enabled": true, "id": "typescript-visualization", "name": "Generate Visualization Config with TypeScript", "order": 2, "type": "prompt" }, { "config": { "model": "gpt-4o", "outputVariable": "executive_summary", "responseFormat": "markdown", "text": "Create an executive summary report based on:\\n- Analysis: {{analysis_result}}\\n- Visualization: {{viz_config}}\\n\\nInclude key insights, trends, and recommendations for {{_record.name}}." }, "enabled": true, "id": "summary-report", "name": "Generate Executive Summary", "order": 3, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "dataset": "sales_2024", "date_range": "Q1 2024", "metrics": [ "revenue", "units_sold", "profit_margin" ] }, "name": "Data Analysis Request", "type": "analysis" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Runtime Tools Daytona Python using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Python Data Analysis with Daytona\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"analysis_result\",\n \"text\": \"Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}\",\n \"tools\": {\n \"maxToolCalls\": 3,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"import json\\nimport statistics\\n\\n# Use sample_data parameter if provided, otherwise use default sample data\\nif 'sample_data' not in dir() or not sample_data:\\n sample_data = [\\n {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25},\\n {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30},\\n {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28},\\n {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32},\\n {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29}\\n ]\\n\\n# Calculate statistics for each metric\\nresults = {\\n 'dataset': dataset_name,\\n 'metrics_analyzed': metrics,\\n 'statistics': {},\\n 'total_records': len(sample_data)\\n}\\n\\nfor metric in metrics:\\n values = [item[metric] for item in sample_data if metric in item]\\n if values:\\n results['statistics'][metric] = {\\n 'mean': round(statistics.mean(values), 2),\\n 'median': round(statistics.median(values), 2),\\n 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0,\\n 'min': values[0] if len(values) == 1 else min(values),\\n 'max': values[0] if len(values) == 1 else max(values),\\n 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values)\\n }\\n\\n# Calculate correlations (simplified)\\nif 'revenue' in results['statistics'] and 'units_sold' in results['statistics']:\\n results['insights'] = {\\n 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2),\\n 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2)\\n }\\n\\nprint(json.dumps(results, indent=2))\",\n \"language\": \"python\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 15000\n },\n \"description\": \"Perform statistical analysis on sales data using Python with numpy and pandas\",\n \"name\": \"analyze_sales_data\",\n \"parametersSchema\": {\n \"properties\": {\n \"dataset_name\": {\n \"description\": \"Name of the dataset to analyze\",\n \"type\": \"string\"\n },\n \"metrics\": {\n \"description\": \"List of metrics to calculate\",\n \"items\": {\n \"type\": \"string\"\n },\n \"type\": \"array\"\n },\n \"sample_data\": {\n \"description\": \"Sample data points\",\n \"items\": {\n \"properties\": {\n \"profit_margin\": {\n \"type\": \"number\"\n },\n \"revenue\": {\n \"type\": \"number\"\n },\n \"units_sold\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n }\n },\n \"required\": [\n \"dataset_name\",\n \"metrics\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"python-analysis\",\n \"name\": \"Analyze Sales Data with Python\",\n \"order\": 1,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"viz_config\",\n \"text\": \"Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.\",\n \"tools\": {\n \"maxToolCalls\": 2,\n \"runtimeTools\": [\n {\n \"config\": {\n \"allowedApis\": [\n \"console\"\n ],\n \"code\": \"interface ChartDataPoint {\\n label: string;\\n value: number;\\n}\\n\\ninterface ChartConfig {\\n type: string;\\n data: {\\n labels: string[];\\n datasets: Array<{\\n label: string;\\n data: number[];\\n backgroundColor?: string[];\\n borderColor?: string;\\n borderWidth?: number;\\n }>;\\n };\\n options: {\\n responsive: boolean;\\n plugins: {\\n title: {\\n display: boolean;\\n text: string;\\n };\\n legend: {\\n display: boolean;\\n };\\n };\\n };\\n}\\n\\n// Extract labels and values from data points\\nconst labels = data_points.map((dp: ChartDataPoint) => dp.label);\\nconst values = data_points.map((dp: ChartDataPoint) => dp.value);\\n\\n// Generate color palette\\nconst colors = [\\n 'rgba(255, 99, 132, 0.8)',\\n 'rgba(54, 162, 235, 0.8)',\\n 'rgba(255, 206, 86, 0.8)',\\n 'rgba(75, 192, 192, 0.8)',\\n 'rgba(153, 102, 255, 0.8)'\\n];\\n\\n// Build Chart.js configuration\\nconst config: ChartConfig = {\\n type: chart_type,\\n data: {\\n labels: labels,\\n datasets: [{\\n label: title,\\n data: values,\\n backgroundColor: colors.slice(0, values.length),\\n borderColor: 'rgba(0, 0, 0, 0.1)',\\n borderWidth: 1\\n }]\\n },\\n options: {\\n responsive: true,\\n plugins: {\\n title: {\\n display: true,\\n text: title\\n },\\n legend: {\\n display: chart_type === 'pie' || chart_type === 'radar'\\n }\\n }\\n }\\n};\\n\\nconsole.log(JSON.stringify(config, null, 2));\",\n \"language\": \"typescript\",\n \"sandboxProvider\": \"daytona\",\n \"timeout\": 10000\n },\n \"description\": \"Generate Chart.js configuration using TypeScript for data visualization\",\n \"name\": \"generate_chart_config\",\n \"parametersSchema\": {\n \"properties\": {\n \"chart_type\": {\n \"description\": \"Type of chart to generate\",\n \"enum\": [\n \"bar\",\n \"line\",\n \"pie\",\n \"radar\"\n ],\n \"type\": \"string\"\n },\n \"data_points\": {\n \"description\": \"Data points for the chart\",\n \"items\": {\n \"properties\": {\n \"label\": {\n \"type\": \"string\"\n },\n \"value\": {\n \"type\": \"number\"\n }\n },\n \"type\": \"object\"\n },\n \"type\": \"array\"\n },\n \"title\": {\n \"description\": \"Chart title\",\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"chart_type\",\n \"data_points\",\n \"title\"\n ],\n \"type\": \"object\"\n },\n \"toolType\": \"custom\"\n }\n ],\n \"toolCallStrategy\": \"auto\"\n }\n },\n \"enabled\": true,\n \"id\": \"typescript-visualization\",\n \"name\": \"Generate Visualization Config with TypeScript\",\n \"order\": 2,\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"executive_summary\",\n \"responseFormat\": \"markdown\",\n \"text\": \"Create an executive summary report based on:\\n- Analysis: {{analysis_result}}\\n- Visualization: {{viz_config}}\\n\\nInclude key insights, trends, and recommendations for {{_record.name}}.\"\n },\n \"enabled\": true,\n \"id\": \"summary-report\",\n \"name\": \"Generate Executive Summary\",\n \"order\": 3,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"dataset\": \"sales_2024\",\n \"date_range\": \"Q1 2024\",\n \"metrics\": [\n \"revenue\",\n \"units_sold\",\n \"profit_margin\"\n ]\n },\n \"name\": \"Data Analysis Request\",\n \"type\": \"analysis\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Runtime Tools Daytona Python import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Python Data Analysis with Daytona", "steps": [ [ "config": [ "model": "gpt-4o", "outputVariable": "analysis_result", "text": "Analyze the sales data for {{_record.metadata.dataset}} during {{_record.metadata.date_range}}. Use the Python analysis tool to calculate statistics for: {{_record.metadata.metrics}}", "tools": [ "maxToolCalls": 3, "runtimeTools": [ [ "config": [ "allowedApis": ["console"], "code": "import json import statistics # Use sample_data parameter if provided, otherwise use default sample data if 'sample_data' not in dir() or not sample_data: sample_data = [ {'revenue': 50000, 'units_sold': 500, 'profit_margin': 0.25}, {'revenue': 75000, 'units_sold': 750, 'profit_margin': 0.30}, {'revenue': 60000, 'units_sold': 600, 'profit_margin': 0.28}, {'revenue': 90000, 'units_sold': 900, 'profit_margin': 0.32}, {'revenue': 80000, 'units_sold': 800, 'profit_margin': 0.29} ] # Calculate statistics for each metric results = { 'dataset': dataset_name, 'metrics_analyzed': metrics, 'statistics': {}, 'total_records': len(sample_data) } for metric in metrics: values = [item[metric] for item in sample_data if metric in item] if values: results['statistics'][metric] = { 'mean': round(statistics.mean(values), 2), 'median': round(statistics.median(values), 2), 'stdev': round(statistics.stdev(values), 2) if len(values) > 1 else 0, 'min': values[0] if len(values) == 1 else min(values), 'max': values[0] if len(values) == 1 else max(values), 'total': round(sum(values), 2) if isinstance(values[0], (int, float)) else len(values) } # Calculate correlations (simplified) if 'revenue' in results['statistics'] and 'units_sold' in results['statistics']: results['insights'] = { 'avg_revenue_per_unit': round(results['statistics']['revenue']['mean'] / results['statistics']['units_sold']['mean'], 2), 'revenue_volatility_percent': round((results['statistics']['revenue']['stdev'] / results['statistics']['revenue']['mean']) * 100, 2) } print(json.dumps(results, indent=2))", "language": "python", "sandboxProvider": "daytona", "timeout": 15000 ], "description": "Perform statistical analysis on sales data using Python with numpy and pandas", "name": "analyze_sales_data", "parametersSchema": [ "properties": [ "dataset_name": [ "description": "Name of the dataset to analyze", "type": "string" ], "metrics": [ "description": "List of metrics to calculate", "items": ["type": "string"], "type": "array" ], "sample_data": [ "description": "Sample data points", "items": [ "properties": [ "profit_margin": ["type": "number"], "revenue": ["type": "number"], "units_sold": ["type": "number"] ], "type": "object" ], "type": "array" ] ], "required": ["dataset_name", "metrics"], "type": "object" ], "toolType": "custom" ] ], "toolCallStrategy": "auto" ] ], "enabled": true, "id": "python-analysis", "name": "Analyze Sales Data with Python", "order": 1, "type": "prompt" ], [ "config": [ "model": "gpt-4o", "outputVariable": "viz_config", "text": "Based on the analysis results {{analysis_result}}, create a visualization configuration. Use the TypeScript config generator tool.", "tools": [ "maxToolCalls": 2, "runtimeTools": [ [ "config": [ "allowedApis": ["console"], "code": "interface ChartDataPoint { label: string; value: number; } interface ChartConfig { type: string; data: { labels: string[]; datasets: Array<{ label: string; data: number[]; backgroundColor?: string[]; borderColor?: string; borderWidth?: number; }>; }; options: { responsive: boolean; plugins: { title: { display: boolean; text: string; }; legend: { display: boolean; }; }; }; } // Extract labels and values from data points const labels = data_points.map((dp: ChartDataPoint) => dp.label); const values = data_points.map((dp: ChartDataPoint) => dp.value); // Generate color palette const colors = [ 'rgba(255, 99, 132, 0.8)', 'rgba(54, 162, 235, 0.8)', 'rgba(255, 206, 86, 0.8)', 'rgba(75, 192, 192, 0.8)', 'rgba(153, 102, 255, 0.8)' ]; // Build Chart.js configuration const config: ChartConfig = { type: chart_type, data: { labels: labels, datasets: [{ label: title, data: values, backgroundColor: colors.slice(0, values.length), borderColor: 'rgba(0, 0, 0, 0.1)', borderWidth: 1 }] }, options: { responsive: true, plugins: { title: { display: true, text: title }, legend: { display: chart_type === 'pie' || chart_type === 'radar' } } } }; console.log(JSON.stringify(config, null, 2));", "language": "typescript", "sandboxProvider": "daytona", "timeout": 10000 ], "description": "Generate Chart.js configuration using TypeScript for data visualization", "name": "generate_chart_config", "parametersSchema": [ "properties": [ "chart_type": [ "description": "Type of chart to generate", "enum": ["bar", "line", "pie", "radar"], "type": "string" ], "data_points": [ "description": "Data points for the chart", "items": [ "properties": [ "label": ["type": "string"], "value": ["type": "number"] ], "type": "object" ], "type": "array" ], "title": [ "description": "Chart title", "type": "string" ] ], "required": ["chart_type", "data_points", "title"], "type": "object" ], "toolType": "custom" ] ], "toolCallStrategy": "auto" ] ], "enabled": true, "id": "typescript-visualization", "name": "Generate Visualization Config with TypeScript", "order": 2, "type": "prompt" ], [ "config": [ "model": "gpt-4o", "outputVariable": "executive_summary", "responseFormat": "markdown", "text": "Create an executive summary report based on: - Analysis: {{analysis_result}} - Visualization: {{viz_config}} Include key insights, trends, and recommendations for {{_record.name}}." ], "enabled": true, "id": "summary-report", "name": "Generate Executive Summary", "order": 3, "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "dataset": "sales_2024", "date_range": "Q1 2024", "metrics": ["revenue", "units_sold", "profit_margin"] ], "name": "Data Analysis Request", "type": "analysis" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Saved MCP Servers **Request** ```json { "flow": { "description": "Agent using saved MCP servers for documentation lookup", "name": "Documentation Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.", "tools": { "maxToolCalls": 5, "toolCallStrategy": "auto", "toolIds": [ "mcp:context7:resolve-library-id", "mcp:context7:get-library-docs" ] }, "userPrompt": "Look up the React documentation and summarize the key concepts about hooks." }, "enabled": true, "id": "agent-step", "name": "Documentation Lookup Agent", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "streamResponse": true } } ``` **SDK Code** ```python Dispatch - Saved MCP Servers import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "description": "Agent using saved MCP servers for documentation lookup", "name": "Documentation Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.", "tools": { "maxToolCalls": 5, "toolCallStrategy": "auto", "toolIds": ["mcp:context7:resolve-library-id", "mcp:context7:get-library-docs"] }, "userPrompt": "Look up the React documentation and summarize the key concepts about hooks." }, "enabled": True, "id": "agent-step", "name": "Documentation Lookup Agent", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "streamResponse": True } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Saved MCP Servers const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"description":"Agent using saved MCP servers for documentation lookup","name":"Documentation Agent","steps":[{"config":{"model":"gpt-4o","outputVariable":"agent_response","systemPrompt":"You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.","tools":{"maxToolCalls":5,"toolCallStrategy":"auto","toolIds":["mcp:context7:resolve-library-id","mcp:context7:get-library-docs"]},"userPrompt":"Look up the React documentation and summarize the key concepts about hooks."},"enabled":true,"id":"agent-step","name":"Documentation Lookup Agent","order":1,"type":"prompt"}]},"options":{"flowMode":"virtual","streamResponse":true}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Saved MCP Servers package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"description\": \"Agent using saved MCP servers for documentation lookup\",\n \"name\": \"Documentation Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"toolCallStrategy\": \"auto\",\n \"toolIds\": [\n \"mcp:context7:resolve-library-id\",\n \"mcp:context7:get-library-docs\"\n ]\n },\n \"userPrompt\": \"Look up the React documentation and summarize the key concepts about hooks.\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Documentation Lookup Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Saved MCP Servers require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"description\": \"Agent using saved MCP servers for documentation lookup\",\n \"name\": \"Documentation Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"toolCallStrategy\": \"auto\",\n \"toolIds\": [\n \"mcp:context7:resolve-library-id\",\n \"mcp:context7:get-library-docs\"\n ]\n },\n \"userPrompt\": \"Look up the React documentation and summarize the key concepts about hooks.\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Documentation Lookup Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Saved MCP Servers import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"description\": \"Agent using saved MCP servers for documentation lookup\",\n \"name\": \"Documentation Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"toolCallStrategy\": \"auto\",\n \"toolIds\": [\n \"mcp:context7:resolve-library-id\",\n \"mcp:context7:get-library-docs\"\n ]\n },\n \"userPrompt\": \"Look up the React documentation and summarize the key concepts about hooks.\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Documentation Lookup Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}") .asString(); ``` ```php Dispatch - Saved MCP Servers request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "description": "Agent using saved MCP servers for documentation lookup", "name": "Documentation Agent", "steps": [ { "config": { "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.", "tools": { "maxToolCalls": 5, "toolCallStrategy": "auto", "toolIds": [ "mcp:context7:resolve-library-id", "mcp:context7:get-library-docs" ] }, "userPrompt": "Look up the React documentation and summarize the key concepts about hooks." }, "enabled": true, "id": "agent-step", "name": "Documentation Lookup Agent", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "virtual", "streamResponse": true } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Saved MCP Servers using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"description\": \"Agent using saved MCP servers for documentation lookup\",\n \"name\": \"Documentation Agent\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"gpt-4o\",\n \"outputVariable\": \"agent_response\",\n \"systemPrompt\": \"You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.\",\n \"tools\": {\n \"maxToolCalls\": 5,\n \"toolCallStrategy\": \"auto\",\n \"toolIds\": [\n \"mcp:context7:resolve-library-id\",\n \"mcp:context7:get-library-docs\"\n ]\n },\n \"userPrompt\": \"Look up the React documentation and summarize the key concepts about hooks.\"\n },\n \"enabled\": true,\n \"id\": \"agent-step\",\n \"name\": \"Documentation Lookup Agent\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"streamResponse\": true\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Saved MCP Servers import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "description": "Agent using saved MCP servers for documentation lookup", "name": "Documentation Agent", "steps": [ [ "config": [ "model": "gpt-4o", "outputVariable": "agent_response", "systemPrompt": "You are a helpful documentation assistant. Use the available tools to look up library documentation and provide accurate, helpful summaries.", "tools": [ "maxToolCalls": 5, "toolCallStrategy": "auto", "toolIds": ["mcp:context7:resolve-library-id", "mcp:context7:get-library-docs"] ], "userPrompt": "Look up the React documentation and summarize the key concepts about hooks." ], "enabled": true, "id": "agent-step", "name": "Documentation Lookup Agent", "order": 1, "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "streamResponse": true ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Screenshot to Flow Generation **Request** ```json { "flow": { "name": "AI Flow Generator", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "generated_steps", "responseFormat": "json", "systemPrompt": "You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps." }, "enabled": true, "name": "Generate Flow Steps", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==", "type": "image" }, { "text": "Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\n- Data inputs visible in the UI\n- Actions/buttons and what they should do\n- API calls that might be needed\n- Any conditional logic suggested by the design\n\nReturn a JSON array of Runtype flow steps.", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "task": "generate_flow_steps", "user_request": "Create a flow that implements this UI design" }, "name": "Generate Flow from Screenshot", "type": "flow_generation" } } ``` **SDK Code** ```python Dispatch - Screenshot to Flow Generation import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "AI Flow Generator", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "generated_steps", "responseFormat": "json", "systemPrompt": "You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps." }, "enabled": True, "name": "Generate Flow Steps", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==", "type": "image" }, { "text": "Analyze this screenshot and generate flow steps to implement the functionality shown. Consider: - Data inputs visible in the UI - Actions/buttons and what they should do - API calls that might be needed - Any conditional logic suggested by the design Return a JSON array of Runtype flow steps.", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "task": "generate_flow_steps", "user_request": "Create a flow that implements this UI design" }, "name": "Generate Flow from Screenshot", "type": "flow_generation" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Screenshot to Flow Generation const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"AI Flow Generator","steps":[{"config":{"model":"claude-sonnet-4-5","outputVariable":"generated_steps","responseFormat":"json","systemPrompt":"You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps."},"enabled":true,"name":"Generate Flow Steps","order":0,"type":"prompt"}]},"messages":[{"content":[{"image":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==","type":"image"},{"text":"Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\n- Data inputs visible in the UI\n- Actions/buttons and what they should do\n- API calls that might be needed\n- Any conditional logic suggested by the design\n\nReturn a JSON array of Runtype flow steps.","type":"text"}],"role":"user"}],"options":{"flowMode":"virtual","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"task":"generate_flow_steps","user_request":"Create a flow that implements this UI design"},"name":"Generate Flow from Screenshot","type":"flow_generation"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Screenshot to Flow Generation package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"AI Flow Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"generated_steps\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Flow Steps\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\\n- Data inputs visible in the UI\\n- Actions/buttons and what they should do\\n- API calls that might be needed\\n- Any conditional logic suggested by the design\\n\\nReturn a JSON array of Runtype flow steps.\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"task\": \"generate_flow_steps\",\n \"user_request\": \"Create a flow that implements this UI design\"\n },\n \"name\": \"Generate Flow from Screenshot\",\n \"type\": \"flow_generation\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Screenshot to Flow Generation require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"AI Flow Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"generated_steps\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Flow Steps\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\\n- Data inputs visible in the UI\\n- Actions/buttons and what they should do\\n- API calls that might be needed\\n- Any conditional logic suggested by the design\\n\\nReturn a JSON array of Runtype flow steps.\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"task\": \"generate_flow_steps\",\n \"user_request\": \"Create a flow that implements this UI design\"\n },\n \"name\": \"Generate Flow from Screenshot\",\n \"type\": \"flow_generation\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Screenshot to Flow Generation import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"AI Flow Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"generated_steps\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Flow Steps\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\\n- Data inputs visible in the UI\\n- Actions/buttons and what they should do\\n- API calls that might be needed\\n- Any conditional logic suggested by the design\\n\\nReturn a JSON array of Runtype flow steps.\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"task\": \"generate_flow_steps\",\n \"user_request\": \"Create a flow that implements this UI design\"\n },\n \"name\": \"Generate Flow from Screenshot\",\n \"type\": \"flow_generation\"\n }\n}") .asString(); ``` ```php Dispatch - Screenshot to Flow Generation request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "AI Flow Generator", "steps": [ { "config": { "model": "claude-sonnet-4-5", "outputVariable": "generated_steps", "responseFormat": "json", "systemPrompt": "You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps." }, "enabled": true, "name": "Generate Flow Steps", "order": 0, "type": "prompt" } ] }, "messages": [ { "content": [ { "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==", "type": "image" }, { "text": "Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\\n- Data inputs visible in the UI\\n- Actions/buttons and what they should do\\n- API calls that might be needed\\n- Any conditional logic suggested by the design\\n\\nReturn a JSON array of Runtype flow steps.", "type": "text" } ], "role": "user" } ], "options": { "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "task": "generate_flow_steps", "user_request": "Create a flow that implements this UI design" }, "name": "Generate Flow from Screenshot", "type": "flow_generation" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Screenshot to Flow Generation using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"AI Flow Generator\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"claude-sonnet-4-5\",\n \"outputVariable\": \"generated_steps\",\n \"responseFormat\": \"json\",\n \"systemPrompt\": \"You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps.\"\n },\n \"enabled\": true,\n \"name\": \"Generate Flow Steps\",\n \"order\": 0,\n \"type\": \"prompt\"\n }\n ]\n },\n \"messages\": [\n {\n \"content\": [\n {\n \"image\": \"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==\",\n \"type\": \"image\"\n },\n {\n \"text\": \"Analyze this screenshot and generate flow steps to implement the functionality shown. Consider:\\n- Data inputs visible in the UI\\n- Actions/buttons and what they should do\\n- API calls that might be needed\\n- Any conditional logic suggested by the design\\n\\nReturn a JSON array of Runtype flow steps.\",\n \"type\": \"text\"\n }\n ],\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"task\": \"generate_flow_steps\",\n \"user_request\": \"Create a flow that implements this UI design\"\n },\n \"name\": \"Generate Flow from Screenshot\",\n \"type\": \"flow_generation\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Screenshot to Flow Generation import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "AI Flow Generator", "steps": [ [ "config": [ "model": "claude-sonnet-4-5", "outputVariable": "generated_steps", "responseFormat": "json", "systemPrompt": "You are a Runtype flow generator. Analyze the provided screenshot and generate appropriate flow steps to implement the functionality shown. Return a JSON array of flow steps." ], "enabled": true, "name": "Generate Flow Steps", "order": 0, "type": "prompt" ] ] ], "messages": [ [ "content": [ [ "image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==", "type": "image" ], [ "text": "Analyze this screenshot and generate flow steps to implement the functionality shown. Consider: - Data inputs visible in the UI - Actions/buttons and what they should do - API calls that might be needed - Any conditional logic suggested by the design Return a JSON array of Runtype flow steps.", "type": "text" ] ], "role": "user" ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "task": "generate_flow_steps", "user_request": "Create a flow that implements this UI design" ], "name": "Generate Flow from Screenshot", "type": "flow_generation" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Standalone Flow Execution **Request** ```json { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "messages": [ { "content": "tell me a joke", "role": "user" } ], "options": { "debugMode": false, "flowMode": "existing", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": {}, "name": "run", "type": "chat" } } ``` **SDK Code** ```python Dispatch - Standalone Flow Execution import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "messages": [ { "content": "tell me a joke", "role": "user" } ], "options": { "debugMode": False, "flowMode": "existing", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": {}, "name": "run", "type": "chat" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Standalone Flow Execution const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"id":"flow_01k9pfvrswf6d8rgm1kzcsxbcd"},"messages":[{"content":"tell me a joke","role":"user"}],"options":{"debugMode":false,"flowMode":"existing","recordMode":"virtual","streamResponse":true},"record":{"metadata":{},"name":"run","type":"chat"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Standalone Flow Execution package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"messages\": [\n {\n \"content\": \"tell me a joke\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"debugMode\": false,\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"run\",\n \"type\": \"chat\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Standalone Flow Execution require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"messages\": [\n {\n \"content\": \"tell me a joke\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"debugMode\": false,\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"run\",\n \"type\": \"chat\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Standalone Flow Execution import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"messages\": [\n {\n \"content\": \"tell me a joke\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"debugMode\": false,\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"run\",\n \"type\": \"chat\"\n }\n}") .asString(); ``` ```php Dispatch - Standalone Flow Execution request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "messages": [ { "content": "tell me a joke", "role": "user" } ], "options": { "debugMode": false, "flowMode": "existing", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": {}, "name": "run", "type": "chat" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Standalone Flow Execution using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"messages\": [\n {\n \"content\": \"tell me a joke\",\n \"role\": \"user\"\n }\n ],\n \"options\": {\n \"debugMode\": false,\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"run\",\n \"type\": \"chat\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Standalone Flow Execution import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": ["id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd"], "messages": [ [ "content": "tell me a joke", "role": "user" ] ], "options": [ "debugMode": false, "flowMode": "existing", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [], "name": "run", "type": "chat" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Test Step Results Storage **Request** ```json { "flow": { "name": "Step Results Test Flow", "steps": [ { "config": { "maxTokens": 500, "model": "gpt-4o-mini", "outputVariable": "analysis", "systemPrompt": "You are a business analyst.", "temperature": 0.7, "userPrompt": "Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights." }, "name": "Analyze Company", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "summary", "systemPrompt": "You are a report writer.", "temperature": 0.5, "userPrompt": "Create a brief summary of this analysis:\n\n{{analysis}}" }, "name": "Generate Summary", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "metadata": { "company": "Acme Corp", "department": "Engineering", "test_scenario": "step_results_tracking" }, "name": "Step Results Test Record", "type": "test" } } ``` **SDK Code** ```python Dispatch - Test Step Results Storage import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "Step Results Test Flow", "steps": [ { "config": { "maxTokens": 500, "model": "gpt-4o-mini", "outputVariable": "analysis", "systemPrompt": "You are a business analyst.", "temperature": 0.7, "userPrompt": "Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights." }, "name": "Analyze Company", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "summary", "systemPrompt": "You are a report writer.", "temperature": 0.5, "userPrompt": "Create a brief summary of this analysis: {{analysis}}" }, "name": "Generate Summary", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": True, "streamResponse": True }, "record": { "metadata": { "company": "Acme Corp", "department": "Engineering", "test_scenario": "step_results_tracking" }, "name": "Step Results Test Record", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Test Step Results Storage const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"Step Results Test Flow","steps":[{"config":{"maxTokens":500,"model":"gpt-4o-mini","outputVariable":"analysis","systemPrompt":"You are a business analyst.","temperature":0.7,"userPrompt":"Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights."},"name":"Analyze Company","type":"prompt"},{"config":{"model":"gpt-3.5-turbo","outputVariable":"summary","systemPrompt":"You are a report writer.","temperature":0.5,"userPrompt":"Create a brief summary of this analysis:\n\n{{analysis}}"},"name":"Generate Summary","type":"prompt"}]},"options":{"flowMode":"virtual","recordMode":"virtual","storeResults":true,"streamResponse":true},"record":{"metadata":{"company":"Acme Corp","department":"Engineering","test_scenario":"step_results_tracking"},"name":"Step Results Test Record","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Test Step Results Storage package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"Step Results Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 500,\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"analysis\",\n \"systemPrompt\": \"You are a business analyst.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights.\"\n },\n \"name\": \"Analyze Company\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"summary\",\n \"systemPrompt\": \"You are a report writer.\",\n \"temperature\": 0.5,\n \"userPrompt\": \"Create a brief summary of this analysis:\\n\\n{{analysis}}\"\n },\n \"name\": \"Generate Summary\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company\": \"Acme Corp\",\n \"department\": \"Engineering\",\n \"test_scenario\": \"step_results_tracking\"\n },\n \"name\": \"Step Results Test Record\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Test Step Results Storage require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"Step Results Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 500,\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"analysis\",\n \"systemPrompt\": \"You are a business analyst.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights.\"\n },\n \"name\": \"Analyze Company\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"summary\",\n \"systemPrompt\": \"You are a report writer.\",\n \"temperature\": 0.5,\n \"userPrompt\": \"Create a brief summary of this analysis:\\n\\n{{analysis}}\"\n },\n \"name\": \"Generate Summary\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company\": \"Acme Corp\",\n \"department\": \"Engineering\",\n \"test_scenario\": \"step_results_tracking\"\n },\n \"name\": \"Step Results Test Record\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Test Step Results Storage import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"Step Results Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 500,\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"analysis\",\n \"systemPrompt\": \"You are a business analyst.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights.\"\n },\n \"name\": \"Analyze Company\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"summary\",\n \"systemPrompt\": \"You are a report writer.\",\n \"temperature\": 0.5,\n \"userPrompt\": \"Create a brief summary of this analysis:\\n\\n{{analysis}}\"\n },\n \"name\": \"Generate Summary\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company\": \"Acme Corp\",\n \"department\": \"Engineering\",\n \"test_scenario\": \"step_results_tracking\"\n },\n \"name\": \"Step Results Test Record\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Test Step Results Storage request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "Step Results Test Flow", "steps": [ { "config": { "maxTokens": 500, "model": "gpt-4o-mini", "outputVariable": "analysis", "systemPrompt": "You are a business analyst.", "temperature": 0.7, "userPrompt": "Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights." }, "name": "Analyze Company", "type": "prompt" }, { "config": { "model": "gpt-3.5-turbo", "outputVariable": "summary", "systemPrompt": "You are a report writer.", "temperature": 0.5, "userPrompt": "Create a brief summary of this analysis:\\n\\n{{analysis}}" }, "name": "Generate Summary", "type": "prompt" } ] }, "options": { "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true }, "record": { "metadata": { "company": "Acme Corp", "department": "Engineering", "test_scenario": "step_results_tracking" }, "name": "Step Results Test Record", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Test Step Results Storage using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"Step Results Test Flow\",\n \"steps\": [\n {\n \"config\": {\n \"maxTokens\": 500,\n \"model\": \"gpt-4o-mini\",\n \"outputVariable\": \"analysis\",\n \"systemPrompt\": \"You are a business analyst.\",\n \"temperature\": 0.7,\n \"userPrompt\": \"Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights.\"\n },\n \"name\": \"Analyze Company\",\n \"type\": \"prompt\"\n },\n {\n \"config\": {\n \"model\": \"gpt-3.5-turbo\",\n \"outputVariable\": \"summary\",\n \"systemPrompt\": \"You are a report writer.\",\n \"temperature\": 0.5,\n \"userPrompt\": \"Create a brief summary of this analysis:\\n\\n{{analysis}}\"\n },\n \"name\": \"Generate Summary\",\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"virtual\",\n \"recordMode\": \"virtual\",\n \"storeResults\": true,\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company\": \"Acme Corp\",\n \"department\": \"Engineering\",\n \"test_scenario\": \"step_results_tracking\"\n },\n \"name\": \"Step Results Test Record\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Test Step Results Storage import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "Step Results Test Flow", "steps": [ [ "config": [ "maxTokens": 500, "model": "gpt-4o-mini", "outputVariable": "analysis", "systemPrompt": "You are a business analyst.", "temperature": 0.7, "userPrompt": "Analyze the company {{_record.metadata.company}} in the {{_record.metadata.department}} department. Provide insights." ], "name": "Analyze Company", "type": "prompt" ], [ "config": [ "model": "gpt-3.5-turbo", "outputVariable": "summary", "systemPrompt": "You are a report writer.", "temperature": 0.5, "userPrompt": "Create a brief summary of this analysis: {{analysis}}" ], "name": "Generate Summary", "type": "prompt" ] ] ], "options": [ "flowMode": "virtual", "recordMode": "virtual", "storeResults": true, "streamResponse": true ], "record": [ "metadata": [ "company": "Acme Corp", "department": "Engineering", "test_scenario": "step_results_tracking" ], "name": "Step Results Test Record", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Upsert Flow Mode **Request** ```json { "flow": { "name": "My SDK Flow", "steps": [ { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "text", "userPrompt": "Summarize the following: {{input}}" }, "enabled": true, "name": "Process Data", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "input": "Hello world, this is a test message." }, "name": "Test Record", "type": "test" } } ``` **SDK Code** ```python Dispatch - Upsert Flow Mode import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "My SDK Flow", "steps": [ { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "text", "userPrompt": "Summarize the following: {{input}}" }, "enabled": True, "name": "Process Data", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "input": "Hello world, this is a test message." }, "name": "Test Record", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Upsert Flow Mode const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"My SDK Flow","steps":[{"config":{"model":"google/gemma-4-26b-a4b-it","responseFormat":"text","userPrompt":"Summarize the following: {{input}}"},"enabled":true,"name":"Process Data","order":1,"type":"prompt"}]},"options":{"flowMode":"upsert","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"input":"Hello world, this is a test message."},"name":"Test Record","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Upsert Flow Mode package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"My SDK Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Summarize the following: {{input}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"input\": \"Hello world, this is a test message.\"\n },\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Upsert Flow Mode require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"My SDK Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Summarize the following: {{input}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"input\": \"Hello world, this is a test message.\"\n },\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Upsert Flow Mode import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"My SDK Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Summarize the following: {{input}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"input\": \"Hello world, this is a test message.\"\n },\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Upsert Flow Mode request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "My SDK Flow", "steps": [ { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "text", "userPrompt": "Summarize the following: {{input}}" }, "enabled": true, "name": "Process Data", "order": 1, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "input": "Hello world, this is a test message." }, "name": "Test Record", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Upsert Flow Mode using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"My SDK Flow\",\n \"steps\": [\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"text\",\n \"userPrompt\": \"Summarize the following: {{input}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 1,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"input\": \"Hello world, this is a test message.\"\n },\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Upsert Flow Mode import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "My SDK Flow", "steps": [ [ "config": [ "model": "google/gemma-4-26b-a4b-it", "responseFormat": "text", "userPrompt": "Summarize the following: {{input}}" ], "enabled": true, "name": "Process Data", "order": 1, "type": "prompt" ] ] ], "options": [ "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": ["input": "Hello world, this is a test message."], "name": "Test Record", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Upsert with Options **Request** ```json { "flow": { "name": "My SDK Flow v2", "steps": [ { "config": { "http": { "method": "GET", "url": "https://api.example.com/data" }, "outputVariable": "api_data" }, "enabled": true, "name": "Fetch Data", "order": 1, "type": "fetch-url" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "json", "userPrompt": "Analyze this data: {{api_data}}" }, "enabled": true, "name": "Process Data", "order": 2, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true, "upsertOptions": { "allowOverwriteExternalChanges": false, "createVersionOnChange": true } }, "record": { "metadata": {}, "name": "Test Record", "type": "test" } } ``` **SDK Code** ```python Dispatch - Upsert with Options import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "name": "My SDK Flow v2", "steps": [ { "config": { "http": { "method": "GET", "url": "https://api.example.com/data" }, "outputVariable": "api_data" }, "enabled": True, "name": "Fetch Data", "order": 1, "type": "fetch-url" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "json", "userPrompt": "Analyze this data: {{api_data}}" }, "enabled": True, "name": "Process Data", "order": 2, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": True, "upsertOptions": { "allowOverwriteExternalChanges": False, "createVersionOnChange": True } }, "record": { "metadata": {}, "name": "Test Record", "type": "test" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Upsert with Options const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"name":"My SDK Flow v2","steps":[{"config":{"http":{"method":"GET","url":"https://api.example.com/data"},"outputVariable":"api_data"},"enabled":true,"name":"Fetch Data","order":1,"type":"fetch-url"},{"config":{"model":"google/gemma-4-26b-a4b-it","responseFormat":"json","userPrompt":"Analyze this data: {{api_data}}"},"enabled":true,"name":"Process Data","order":2,"type":"prompt"}]},"options":{"flowMode":"upsert","recordMode":"virtual","streamResponse":true,"upsertOptions":{"allowOverwriteExternalChanges":false,"createVersionOnChange":true}},"record":{"metadata":{},"name":"Test Record","type":"test"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Upsert with Options package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"name\": \"My SDK Flow v2\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"method\": \"GET\",\n \"url\": \"https://api.example.com/data\"\n },\n \"outputVariable\": \"api_data\"\n },\n \"enabled\": true,\n \"name\": \"Fetch Data\",\n \"order\": 1,\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Analyze this data: {{api_data}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 2,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true,\n \"upsertOptions\": {\n \"allowOverwriteExternalChanges\": false,\n \"createVersionOnChange\": true\n }\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Upsert with Options require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"name\": \"My SDK Flow v2\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"method\": \"GET\",\n \"url\": \"https://api.example.com/data\"\n },\n \"outputVariable\": \"api_data\"\n },\n \"enabled\": true,\n \"name\": \"Fetch Data\",\n \"order\": 1,\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Analyze this data: {{api_data}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 2,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true,\n \"upsertOptions\": {\n \"allowOverwriteExternalChanges\": false,\n \"createVersionOnChange\": true\n }\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Upsert with Options import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"name\": \"My SDK Flow v2\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"method\": \"GET\",\n \"url\": \"https://api.example.com/data\"\n },\n \"outputVariable\": \"api_data\"\n },\n \"enabled\": true,\n \"name\": \"Fetch Data\",\n \"order\": 1,\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Analyze this data: {{api_data}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 2,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true,\n \"upsertOptions\": {\n \"allowOverwriteExternalChanges\": false,\n \"createVersionOnChange\": true\n }\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}") .asString(); ``` ```php Dispatch - Upsert with Options request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "name": "My SDK Flow v2", "steps": [ { "config": { "http": { "method": "GET", "url": "https://api.example.com/data" }, "outputVariable": "api_data" }, "enabled": true, "name": "Fetch Data", "order": 1, "type": "fetch-url" }, { "config": { "model": "google/gemma-4-26b-a4b-it", "responseFormat": "json", "userPrompt": "Analyze this data: {{api_data}}" }, "enabled": true, "name": "Process Data", "order": 2, "type": "prompt" } ] }, "options": { "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true, "upsertOptions": { "allowOverwriteExternalChanges": false, "createVersionOnChange": true } }, "record": { "metadata": {}, "name": "Test Record", "type": "test" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Upsert with Options using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"name\": \"My SDK Flow v2\",\n \"steps\": [\n {\n \"config\": {\n \"http\": {\n \"method\": \"GET\",\n \"url\": \"https://api.example.com/data\"\n },\n \"outputVariable\": \"api_data\"\n },\n \"enabled\": true,\n \"name\": \"Fetch Data\",\n \"order\": 1,\n \"type\": \"fetch-url\"\n },\n {\n \"config\": {\n \"model\": \"google/gemma-4-26b-a4b-it\",\n \"responseFormat\": \"json\",\n \"userPrompt\": \"Analyze this data: {{api_data}}\"\n },\n \"enabled\": true,\n \"name\": \"Process Data\",\n \"order\": 2,\n \"type\": \"prompt\"\n }\n ]\n },\n \"options\": {\n \"flowMode\": \"upsert\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true,\n \"upsertOptions\": {\n \"allowOverwriteExternalChanges\": false,\n \"createVersionOnChange\": true\n }\n },\n \"record\": {\n \"metadata\": {},\n \"name\": \"Test Record\",\n \"type\": \"test\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Upsert with Options import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": [ "name": "My SDK Flow v2", "steps": [ [ "config": [ "http": [ "method": "GET", "url": "https://api.example.com/data" ], "outputVariable": "api_data" ], "enabled": true, "name": "Fetch Data", "order": 1, "type": "fetch-url" ], [ "config": [ "model": "google/gemma-4-26b-a4b-it", "responseFormat": "json", "userPrompt": "Analyze this data: {{api_data}}" ], "enabled": true, "name": "Process Data", "order": 2, "type": "prompt" ] ] ], "options": [ "flowMode": "upsert", "recordMode": "virtual", "streamResponse": true, "upsertOptions": [ "allowOverwriteExternalChanges": false, "createVersionOnChange": true ] ], "record": [ "metadata": [], "name": "Test Record", "type": "test" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ``` ### Dispatch - Create Virtual Record with Flow **Request** ```json { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "company_name": "Acme Corp", "contact_email": "contact@acme.com", "employee_count": 500, "industry": "Technology", "revenue": "10M" }, "name": "Test Customer Analysis", "type": "customer" } } ``` **SDK Code** ```python Dispatch - Create Virtual Record with Flow import requests url = "https://api.runtype.com/v1/dispatch" payload = { "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "virtual", "streamResponse": True }, "record": { "metadata": { "company_name": "Acme Corp", "contact_email": "contact@acme.com", "employee_count": 500, "industry": "Technology", "revenue": "10M" }, "name": "Test Customer Analysis", "type": "customer" } } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript Dispatch - Create Virtual Record with Flow const url = 'https://api.runtype.com/v1/dispatch'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"flow":{"id":"flow_01k9pfvrswf6d8rgm1kzcsxbcd"},"options":{"flowMode":"existing","recordMode":"virtual","streamResponse":true},"record":{"metadata":{"company_name":"Acme Corp","contact_email":"contact@acme.com","employee_count":500,"industry":"Technology","revenue":"10M"},"name":"Test Customer Analysis","type":"customer"}}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go Dispatch - Create Virtual Record with Flow package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.runtype.com/v1/dispatch" payload := strings.NewReader("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company_name\": \"Acme Corp\",\n \"contact_email\": \"contact@acme.com\",\n \"employee_count\": 500,\n \"industry\": \"Technology\",\n \"revenue\": \"10M\"\n },\n \"name\": \"Test Customer Analysis\",\n \"type\": \"customer\"\n }\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby Dispatch - Create Virtual Record with Flow require 'uri' require 'net/http' url = URI("https://api.runtype.com/v1/dispatch") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Post.new(url) request["Authorization"] = 'Bearer ' request["Content-Type"] = 'application/json' request.body = "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company_name\": \"Acme Corp\",\n \"contact_email\": \"contact@acme.com\",\n \"employee_count\": 500,\n \"industry\": \"Technology\",\n \"revenue\": \"10M\"\n },\n \"name\": \"Test Customer Analysis\",\n \"type\": \"customer\"\n }\n}" response = http.request(request) puts response.read_body ``` ```java Dispatch - Create Virtual Record with Flow import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.runtype.com/v1/dispatch") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company_name\": \"Acme Corp\",\n \"contact_email\": \"contact@acme.com\",\n \"employee_count\": 500,\n \"industry\": \"Technology\",\n \"revenue\": \"10M\"\n },\n \"name\": \"Test Customer Analysis\",\n \"type\": \"customer\"\n }\n}") .asString(); ``` ```php Dispatch - Create Virtual Record with Flow request('POST', 'https://api.runtype.com/v1/dispatch', [ 'body' => '{ "flow": { "id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd" }, "options": { "flowMode": "existing", "recordMode": "virtual", "streamResponse": true }, "record": { "metadata": { "company_name": "Acme Corp", "contact_email": "contact@acme.com", "employee_count": 500, "industry": "Technology", "revenue": "10M" }, "name": "Test Customer Analysis", "type": "customer" } }', 'headers' => [ 'Authorization' => 'Bearer ', 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp Dispatch - Create Virtual Record with Flow using RestSharp; var client = new RestClient("https://api.runtype.com/v1/dispatch"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"flow\": {\n \"id\": \"flow_01k9pfvrswf6d8rgm1kzcsxbcd\"\n },\n \"options\": {\n \"flowMode\": \"existing\",\n \"recordMode\": \"virtual\",\n \"streamResponse\": true\n },\n \"record\": {\n \"metadata\": {\n \"company_name\": \"Acme Corp\",\n \"contact_email\": \"contact@acme.com\",\n \"employee_count\": 500,\n \"industry\": \"Technology\",\n \"revenue\": \"10M\"\n },\n \"name\": \"Test Customer Analysis\",\n \"type\": \"customer\"\n }\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift Dispatch - Create Virtual Record with Flow import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "flow": ["id": "flow_01k9pfvrswf6d8rgm1kzcsxbcd"], "options": [ "flowMode": "existing", "recordMode": "virtual", "streamResponse": true ], "record": [ "metadata": [ "company_name": "Acme Corp", "contact_email": "contact@acme.com", "employee_count": 500, "industry": "Technology", "revenue": "10M" ], "name": "Test Customer Analysis", "type": "customer" ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/dispatch")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ```