{ "openapi": "3.0.1", "info": { "title": "Dataset Drift Monitor", "description": "Scheduled scraper ran successfully, but did the output quietly change? Compare the current dataset shape with the latest baseline for count, field, missing-rate, and type-distribution drift.", "version": "0.1", "x-build-id": "VlPIaK6n8jL0xatNV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/checksmithcats~dataset-drift-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-checksmithcats-dataset-drift-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/checksmithcats~dataset-drift-monitor/runs": { "post": { "operationId": "runs-sync-checksmithcats-dataset-drift-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/checksmithcats~dataset-drift-monitor/run-sync": { "post": { "operationId": "run-sync-checksmithcats-dataset-drift-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "datasetId": { "title": "Dataset ID", "type": "string", "description": "Dataset ID to read through the platform API." }, "runId": { "title": "Actor run ID", "type": "string", "description": "Actor run ID. The monitor resolves its default dataset ID." }, "apiToken": { "title": "API token", "type": "string", "description": "Optional token for private datasets or runs. Sent in the Authorization header only and not stored in reports or state." }, "items": { "title": "Submitted JSON items", "type": "array", "description": "Optional inline array of item objects. Use this when not reading from Apify API.", "items": { "type": "object" } }, "dataJson": { "title": "Submitted JSON text", "type": "string", "description": "Optional JSON array, or an object with an items array." }, "csvText": { "title": "Submitted CSV text", "type": "string", "description": "Optional CSV with a header row. Values are analyzed only as aggregate shape signals." }, "baselineKey": { "title": "Stable baseline key", "type": "string", "description": "Stable identity used for repeated comparisons. Required for submitted data and recommended for runId-based checks." }, "sampleLimit": { "title": "Sample limit", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of rows to sample from the current dataset. Keep the default small for scheduled runs.", "default": 200 }, "countDropRatio": { "title": "Record-count drop threshold", "minimum": 0.01, "maximum": 0.95, "type": "number", "description": "Warn when record count drops by at least this ratio compared with the latest baseline.", "default": 0.25 }, "missingRateDelta": { "title": "Field missing-rate increase threshold", "minimum": 0.01, "maximum": 1, "type": "number", "description": "Warn when a field's missing rate increases by at least this absolute amount.", "default": 0.2 }, "typeShiftDelta": { "title": "Type-distribution shift threshold", "minimum": 0.01, "maximum": 1, "type": "number", "description": "Warn when a field's observed type distribution moves by at least this amount.", "default": 0.5 }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Key-value store name for the latest compact baseline snapshot.", "default": "dataset-drift-monitor-state" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }