Vertesia Agent Runs API
Agent runs are long-running conversational workflow executions with stable IDs, message streams, artifacts, child workflow inspection, lifecycle controls, and searchable metadata.
Vertesia Agent Runs API is one of 48 APIs that Vertesia publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 6 JSON Schema definitions.
Tagged areas include Agent Runs. The published artifact set on APIs.io includes an OpenAPI specification and 6 JSON Schemas.
This API exposes 28 operations across 23 paths, and defines 205 schemas. It is described by OpenAPI 3.2.0, at version 1.6.0-dev.20261019.172735Z.
Requests are made against a single base URL, https://api.{region}.vertesia.io/api/v1.
28 operations
23 paths
205 schemas
1 DELETE15 GET10 POST2 PUT
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 2
Vertesia Agent Runs API declares
2 security schemes
for authenticating requests.
It accepts HTTP bearer tokens (bearerAuth).
It supports OAuth 2.0 (OAuth2) using the authorizationCode flow, exposing 33 scopes.
Paths & Operations 28
Across 23 paths, the API surfaces 28 operations — 1 DELETE, 15 GET, 10 POST, 2 PUT. Each is listed below with its method, path, parameters, and response codes.
Agent Runs 28
Agent runs are long-running conversational workflow executions with stable IDs, message streams, artifacts, child workflow inspection, lifecycle controls, and searchable metadata.
POST
/agents
Create an agent run
GET
/agents
List agent runs
GET
/agents/search
Search agent runs
GET
/agents/{agentRunId}
Retrieve an agent run
DELETE
/agents/{agentRunId}
Terminate an agent run
POST
/agents/{agentRunId}/restart
Restart an agent run
POST
/agents/{agentRunId}/fork
Fork an agent run
POST
/agents/{agentRunId}/signal/{signalName}
Signal an agent run
POST
/agents/{agentRunId}/budget
Add token budget to a paused run
GET
/agents/{agentRunId}/query/{queryName}
Query an agent run
GET
/agents/{agentRunId}/updates
List agent run updates
POST
/agents/{agentRunId}/updates
Post an agent run update
GET
/agents/{agentRunId}/stream
Stream an agent run
GET
/agents/{agentRunId}/artifacts
List agent run artifacts
GET
/agents/{agentRunId}/artifact-content/{path}
Read editable agent artifact content
PUT
/agents/{agentRunId}/artifact-content/{path}
Update editable agent artifact content
GET
/agents/{agentRunId}/artifacts/{path}
Get an agent run artifact
PUT
/agents/{agentRunId}/artifacts/{path}
Create an artifact upload URL
GET
/agents/{agentRunId}/details
Get agent run details
GET
/agents/{agentRunId}/children
List child agent runs
GET
/agents/{agentRunId}/context
Get process run context
GET
/agents/{agentRunId}/history
Get process run history
POST
/agents/{agentRunId}/advance
Advance a process run
POST
/agents/{agentRunId}/retry-node
Retry a process node
POST
/agents/{agentRunId}/answer-task
Answer a process task
GET
/agents/{agentRunId}/children/{childWorkflowId}/details
Get child agent run details
GET
/agents/{agentRunId}/details/stream
Stream agent run details
POST
/agents/{agentRunId}/feedback
Rate an agent run
Schemas 205
The contract defines 205 schemas that model the data the API accepts and returns. The most detailed are AgentRun (55 properties), AutonomousRunResponse (55 properties), NodeDefinition (38 properties), CreateAgentRunPayload (36 properties). Each schema is shown below with its type and property counts.
SignalEventProperties
object
Signal event properties for workflow events
6 properties
1 required
PromptStatus
string
PromptSegmentDefType
string
WorkflowQueryResult
SignalAgentResponse
object
Response from signaling an agent workflow.
2 properties
2 required
TaskType_CHILD_WORKFLOW
string
ProcessScriptSource
ActivityTask
object
12 properties
9 required
BedrockMistralOptions
object
8 properties
RetryProcessNodePayload
object
2 properties
InteractionExecutionConfiguration
object
14 properties
ProcessBudgetSummary
object
8 properties
3 required
EventCategory
string
PostAgentRunUpdatePayload
object
Payload for posting an update into an agent's workflow stream.
6 properties
AgentRunResponse
object
1 required
ProcessRunConfig
object
7 properties
TimerTask
object
14 properties
9 required
OpenAiGptImageOptions
object
12 properties
AdvanceProcessPayload
object
2 properties
ListWorkflowRunsResponse
object
3 properties
1 required
AgentRunArtifactPathArray
array
ModelOptions
object
ProcessNodeRunType
string
UserChannel
object
1 required
TwelvelabsPegasusOptions
object
4 properties
SupervisedRunResponse
object
30 properties
12 required
ProcessContextResponse
object
3 properties
3 required
OpenAiTranscriptionOptions
object
2 properties
JSONValue
RunDataStorageLevel
string
ProcessAgentPhaseReset
object
3 properties
2 required
CreateProcessRunWithDefinitionPayload
object
Payload to start a process from an inline definition.
10 properties
1 required
TaskType_TIMER
string
AgentRunLlmEvaluationResult
object
Latest LLM evaluation result for a run.
11 properties
7 required
PromptRole
string
BedrockMantleClaudeOptions
object
12 properties
VertexAIGeminiOptions
object
27 properties
ProcessAgentToolInputContains
object
4 properties
2 required
EmailChannel
object
Email channel configuration with threading support. Used for email-based agent communication.
6 properties
2 required
AnswerProcessTaskPayload
object
2 properties
2 required
AgentRunFeedbackRating
string
Thumbs up or thumbs down on an agent run.
OpenAiImageGenerationOptions
object
12 properties
1 required
VertexAIClaudeOptions
object
12 properties
AgentRunFeedbackCounts
object
Ratings over the retained feedback entries, one vote per rater: a user who rated the run and one of its answers counts once, by their latest rating.
4 properties
2 required
XAIGrokImageOptions
object
6 properties
TaskType_SIGNAL
string
ConversationVisibility
string
RestartAgentRunPayload
object
Optional restart options. POST /agents/:id/restart accepts no body at all.
1 property
BranchDefinition
object
4 properties
1 required
ProcessAgentToolPhase
object
8 properties
3 required
AgentMessageType
number
PromptSegmentRef_PromptTemplateRef
object
4 properties
2 required
VertexAIGeminiOmniVideoOptions
object
5 properties
WorkflowRunEvent
object
11 properties
4 required
StoredTypeRef
object
4 properties
3 required
BedrockGptOssOptions
object
9 properties
AgentResourceAction
string
OpenAiAudioOptions
object
3 properties
BedrockPalmyraOptions
object
10 properties
ProcessNodeType
string
ProcessNodeReturnsDefinition
object
2 properties
AgentResourceReference
object
A navigable reference to a resource an agent tool mutated. Tools return these as tool-result metadata (see {@link ToolResultMeta.resources } ); the conversatio…
5 properties
4 required
ChildWorkflowTask
object
13 properties
9 required
NodeHistoryEntry
object
14 properties
3 required
JSONSchemaProperties
object
AgentMessageDetails
object
32 properties
StringValueMap
object
BedrockConverseOptions
object
10 properties
VertexAIGrokOptions
object
5 properties
CompactMessage
object
Compact message format for efficient wire transfer. Primary type used throughout the system. ~85% smaller than legacy AgentMessage format.
7 properties
1 required
TaskType_ACTIVITY
string
AgentResourceType
string
The kinds of Vertesia resource an agent tool can report having created, updated, or deleted. Restricted to resources that have a real detail route to navigate…
ProcessHistoryRef
object
3 properties
3 required
InteractionRef
object
13 properties
7 required
NodeDefinition
object
38 properties
1 required
TurnEvaluationFlag
string
Reason behind an evaluation severity.
UpdateAgentArtifactContentResponse
object
Result of a conditional agent artifact update.
2 properties
2 required
BranchNodeBranchDefinition
object
5 properties
2 required
InteractiveChannel
object
Interactive (UI chat) channel configuration. Used for real-time chat interface communication.
1 property
1 required
JSONSchema
object
9 properties
AgentRunEvaluation
object
Evaluation summary of an agent run.
10 properties
5 required
BedrockAI21Options
object
9 properties
ProcessDefinitionBody
object
9 properties
5 required
FileProcessingStatus
string
Status of a file being processed for conversation use.
PostAgentRunUpdateResponse
object
Response from posting an agent update.
1 property
1 required
SignalAgentPayload
object
Generic signal payload sent to a running agent workflow.
GroqOptions
object
8 properties
1 required
EventError
object
Error information from failed workflow events
4 properties
InteractionStatus
string
TurnTerminalType
string
How an agent turn ended.
BedrockCohereCommandOptions
object
10 properties
CreateRunPayload
Payload to create and start an agent run or a process run.
SignalTask
object
16 properties
9 required
EvaluationOutcome
string
Outcome of an LLM evaluation run.
ProcessResourcesDefinition
object
1 property
TransitionDefinition
object
5 properties
1 required
WorkflowRun
object
21 properties
2 required
AgentTask
object
Agent task information for workflow history UI representation. This is separate from the analytics AgentEvent types. Consistent with WorkflowTask naming conven…
22 properties
6 required
OpenAiImageGenerationMask
object
2 properties
ParallelCollectMode
string
ParallelCollectDefinition
object
3 properties
1 required
ParallelCollectField
string
ProcessState
object
7 properties
4 required
ResourceRef
object
9 properties
3 required
AzureFoundryChatOptions
object
10 properties
TaskField
object
6 properties
2 required
ProcessScriptResourceMap
object
BedrockMantleResponsesOptions
object
9 properties
ProcessScriptInlineSource
object
Script files stored directly in the process definition. The source is a discriminated object so artifact- and Git-backed sources can be added without changing…
2 properties
2 required
JSONObject
object
BedrockMantleChatCompletionsOptions
object
8 properties
AgentRunStatus
string
Status of an agent run through its lifecycle.
ThinkingLevel
string
AgentCheckpointConfiguration
object
2 properties
OpenRouterTextOptions
object
23 properties
HumanTaskDefinition
object
4 properties
2 required
InteractionVisibility
string
ReasoningEffort
string
TaskStatus
string
AgentBudgetConfiguration
object
Weighted token budget for an agent run and its subagent workstreams. A call is charged output × outputtokenweight + uncached input × inputtokenweight + cached…
8 properties
TerminateAgentRunResponse
object
Response from terminating an agent run.
2 properties
1 required
OpenAiDalleOptions
object
6 properties
InCodeTypeRef
object
4 properties
3 required
HttpTimeoutOptions
object
HTTP timeouts applied to a driver's upstream LLM-provider calls. All values are in milliseconds. Drivers should map these onto whatever HTTP client their SDK u…
4 properties
EvaluationGateReason
string
Why a run was selected for LLM evaluation.
BedrockClaudeOptions
object
13 properties
EvaluationVerdict
string
LLM evaluation verdict for a turn.
MistralTextOptions
object
14 properties
PendingActivity
object
7 properties
3 required
ConfigModes
string
OpenAiThinkingOptions
object
12 properties
UpdateAgentArtifactContentPayload
object
Conditional text update for an agent artifact.
2 properties
2 required
AgentRunFeedbackReasonCode
string
Why the run was rated the way it was.
AgentSearchScope
string
Defines the scope for agent search operations.
ProcessDefinitionFormatVersion
number
ServerSentEventsResponse
string
AgentArtifactUrlResponse
object
Signed artifact URL response for agent artifacts.
2 properties
2 required
AgentRunFeedbackStatus
string
Whether the rating was recorded.
OpenAiSpeechOptions
object
5 properties
ProcessAgentExecutionPolicy
object
11 properties
1 required
CreateAgentRunPayload
object
Payload to create and start a new agent run.
36 properties
1 required
CreateProcessRunByIdPayload
object
Payload to start a stored process by id.
10 properties
1 required
ListAgentRunsResponse
object
3 properties
3 required
ProcessDefinitionMetadata
object
AgentRun
object
AgentRun — the client-facing stable identity for a running or completed agent. All operations use id as the sole identifier. Temporal workflow internals are ne…
55 properties
12 required
RunKind
string
Internal discriminator key for documents stored in the agentruns collection.
AgentRunEvaluationRollup
object
Fold of the turn evaluations of a run.
11 properties
7 required
SearchAgentRunsResponse
object
Response from the agent runs search endpoint.
2 properties
2 required
AgentRunContradictionReason
string
AgentArtifactContentResponse
object
Text content and concurrency token for an agent artifact.
3 properties
3 required
WorkflowHistory
object
1 required
EventRef
object
11 properties
10 required
AgentRunArchiveState
string
Archive lifecycle state for an agent run. - none: No archive exists (default) - pending: Terminal status recorded; archive workflow triggered - archiving: Arch…
WorkflowTask
object
1 required
AnthropicClaudeOptions
object
13 properties
EvaluationSeverity
string
Worst deterministic detector level. none means no detector fired, not success.
WorkflowExecutionStatus
number
ImagenTaskType
string
BedrockNovaOptions
object
9 properties
NodeDefinitionMap
object
ImagenMaskMode
string
TaskFieldType
string
ProcessHistoryResponse
object
4 properties
3 required
NovaCanvasOptions
object
13 properties
1 required
ProcessScriptLanguage
string
TextFallbackOptions
object
10 properties
AgentToolApprovalMode
string
ProcessScriptResource
object
4 properties
3 required
RunType
string
Public-facing runtime mode.
RunSource
object
5 properties
5 required
AgentRunFeedbackPayload
object
A user rating on an agent run.
6 properties
2 required
BinaryFileResponse
string
ImagenOptions
object
19 properties
BranchJoinPolicy
string
InferenceProfileId
string
MongoDB ObjectId of the inference profile.
JsonLogicRule
object
AllocateAgentRunBudgetPayload
Add exactly one allowance: weighted tokens or USD.
ProgrammaticRunResponse
object
30 properties
12 required
ProcessTerminalReason
string
Why a process run ended other than by reaching a final node. tokenbudgetexhausted: the run spent its token budget; it ends with status failed.
TransitionTrigger
string
PlanTask
object
5 properties
2 required
AutonomousRunResponse
object
AgentRun — the client-facing stable identity for a running or completed agent. All operations use id as the sole identifier. Temporal workflow internals are ne…
55 properties
12 required
ExecutionTokenUsage
object
9 properties
AgentRunUpdatesResponse
object
Response payload for retrieving compact agent updates.
1 property
1 required
SkillContextTriggers
object
Context triggers for auto-injection of skills. When these conditions match, the skill is automatically injected into the agent context.
3 properties
AgentRunFeedbackEntry
object
One recorded rating on an agent run.
10 properties
5 required
AgentRunType
string
How the agent run was created.
ProcessContextDefinition
object
2 properties
2 required
ErrorResponse
object
Standard JSON error response returned by the server error handler.
5 properties
2 required
AgentRunnerOptions
object
Configuration options for Agent Runner functionality. These options control how interactions are exposed and executed in the Agent Runner.
11 properties
AgentRunSearchHit
object
A single search hit from Elasticsearch.
27 properties
8 required
ContentObjectTypeRef
object
1 required
PromptTemplateRef
object
10 properties
7 required
ParallelFailurePolicy
string
ConversationActivityState
string
OpenAiTextOptions
object
16 properties
InitialToolCall
object
A tool invocation executed before the first model turn of a conversation. Results are injected into the initial context so the agent starts with them in hand.
4 properties
2 required
ProcessRunType
string
ConversationFile
object
Represents a file being processed in a conversation workflow.
13 properties
6 required
AgentRunFeedbackResponse
object
Result of rating an agent run.
2 properties
1 required
RunSourceTypes
string
PromptCacheMode
string
TemplateType
string
WorkflowRunWithDetails
object
24 properties
2 required
ProcessBudgetState
object
11 properties
3 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Vertesia 12
Other APIs Vertesia publishes across the network.
Vertesia Access Control Entries API
Vertesia Account API
Vertesia Accounts API
Vertesia API Keys API
Vertesia Apps API
Vertesia Audit Trail API
Vertesia Bulk Operations API
Vertesia Collections API
Vertesia Commands API
Vertesia Content Object Types API
Vertesia Content Query API
Vertesia Costs API
#Agent Runs
Where this information came from
This is an independent, third-party profile of Vertesia Agent Runs API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.