Coroutine-native client covering the full Hanzo /v1 cloud surface, for JVM and Android. Generated with openapi-generator kotlin (library=jvm-okhttp4, useCoroutines=true). Coordinate: ai.hanzo:sdk. Base URL: https://api.hanzo.ai. Co-authored-by: Hanzo Dev <[email protected]>
8.4 KiB
RunsApi
All URIs are relative to https://api.hanzo.ai
| Method | HTTP request | Description |
|---|---|---|
| automationsGetRun | GET /v1/automations/runs/{id} | Get a run (non-terminal status is refreshed from the engine) |
| automationsListRuns | GET /v1/automations/runs | List runs |
| automationsResumeRun | POST /v1/automations/runs/{id}/resume | Resume a paused run |
| automationsRunFlow | POST /v1/automations/flows/{id}/run | Start a durable run of a flow's runnable version |
| evalsGetV1EvalsHealth | GET /v1/evals/health | Health check |
| evalsPostV1EvalsRuns | POST /v1/evals/runs | Run a dataset against a model with an LLM-as-a-Judge |
automationsGetRun
AutomationsFlowRun automationsGetRun(id)
Get a run (non-terminal status is refreshed from the engine)
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
val id : kotlin.String = id_example // kotlin.String |
try {
val result : AutomationsFlowRun = apiInstance.automationsGetRun(id)
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#automationsGetRun")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#automationsGetRun")
e.printStackTrace()
}
Parameters
| Name | Type | Description | Notes |
|---|---|---|---|
| id | kotlin.String |
Return type
Authorization
Configure bearerAuth statically:
ApiClient.accessToken = ""
Configure bearerAuth dynamically:
apiInstance.accessTokenProvider = { "" }
HTTP request headers
- Content-Type: Not defined
- Accept: application/json
automationsListRuns
AutomationsListRuns200Response automationsListRuns(flowId, limit)
List runs
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
val flowId : kotlin.String = flowId_example // kotlin.String |
val limit : kotlin.Int = 56 // kotlin.Int |
try {
val result : AutomationsListRuns200Response = apiInstance.automationsListRuns(flowId, limit)
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#automationsListRuns")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#automationsListRuns")
e.printStackTrace()
}
Parameters
| flowId | kotlin.String| | [optional] |
| Name | Type | Description | Notes |
|---|---|---|---|
| limit | kotlin.Int | [optional] [default to 200] |
Return type
AutomationsListRuns200Response
Authorization
Configure bearerAuth statically:
ApiClient.accessToken = ""
Configure bearerAuth dynamically:
apiInstance.accessTokenProvider = { "" }
HTTP request headers
- Content-Type: Not defined
- Accept: application/json
automationsResumeRun
AutomationsResumeRun200Response automationsResumeRun(id, body)
Resume a paused run
The JSON body (max 64 KiB) is delivered verbatim as the waitpoint's output.
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
val id : kotlin.String = id_example // kotlin.String |
val body : kotlin.Any = // kotlin.Any |
try {
val result : AutomationsResumeRun200Response = apiInstance.automationsResumeRun(id, body)
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#automationsResumeRun")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#automationsResumeRun")
e.printStackTrace()
}
Parameters
| id | kotlin.String| | |
| Name | Type | Description | Notes |
|---|---|---|---|
| body | kotlin.Any | [optional] |
Return type
AutomationsResumeRun200Response
Authorization
Configure bearerAuth statically:
ApiClient.accessToken = ""
Configure bearerAuth dynamically:
apiInstance.accessTokenProvider = { "" }
HTTP request headers
- Content-Type: application/json
- Accept: application/json
automationsRunFlow
AutomationsFlowRun automationsRunFlow(id)
Start a durable run of a flow's runnable version
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
val id : kotlin.String = id_example // kotlin.String |
try {
val result : AutomationsFlowRun = apiInstance.automationsRunFlow(id)
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#automationsRunFlow")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#automationsRunFlow")
e.printStackTrace()
}
Parameters
| Name | Type | Description | Notes |
|---|---|---|---|
| id | kotlin.String |
Return type
Authorization
Configure bearerAuth statically:
ApiClient.accessToken = ""
Configure bearerAuth dynamically:
apiInstance.accessTokenProvider = { "" }
HTTP request headers
- Content-Type: Not defined
- Accept: application/json
evalsGetV1EvalsHealth
EvalsGetV1EvalsHealth200Response evalsGetV1EvalsHealth()
Health check
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
try {
val result : EvalsGetV1EvalsHealth200Response = apiInstance.evalsGetV1EvalsHealth()
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#evalsGetV1EvalsHealth")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#evalsGetV1EvalsHealth")
e.printStackTrace()
}
Parameters
This endpoint does not need any parameter.
Return type
EvalsGetV1EvalsHealth200Response
Authorization
No authorization required
HTTP request headers
- Content-Type: Not defined
- Accept: application/json
evalsPostV1EvalsRuns
EvalsRunSummary evalsPostV1EvalsRuns(evalsRunRequest)
Run a dataset against a model with an LLM-as-a-Judge
For each dataset item: calls the model-under-test through the Hanzo gateway, records a trace, then scores the output with the judge model against the criteria/metrics. Returns a per-item + aggregate summary with score, rationale, latency, tokens, and cost.
Example
// Import classes:
//import ai.hanzo.sdk.infrastructure.*
//import ai.hanzo.sdk.models.*
val apiInstance = RunsApi()
val evalsRunRequest : EvalsRunRequest = // EvalsRunRequest |
try {
val result : EvalsRunSummary = apiInstance.evalsPostV1EvalsRuns(evalsRunRequest)
println(result)
} catch (e: ClientException) {
println("4xx response calling RunsApi#evalsPostV1EvalsRuns")
e.printStackTrace()
} catch (e: ServerException) {
println("5xx response calling RunsApi#evalsPostV1EvalsRuns")
e.printStackTrace()
}
Parameters
| Name | Type | Description | Notes |
|---|---|---|---|
| evalsRunRequest | EvalsRunRequest |
Return type
Authorization
Configure bearerAuth statically:
ApiClient.accessToken = ""
Configure bearerAuth dynamically:
apiInstance.accessTokenProvider = { "" }
HTTP request headers
- Content-Type: application/json
- Accept: application/json