{ "openapi": "3.0.1", "info": { "title": "Semantic Synthesis Engine", "description": "RAG Pipeline, Agentic Infrastructure, Idempotent Ingestion — deterministic-first LLM synthesis over Delta-Sync Sentinel manifests, gated by a separated Critic/canary assertion step.", "version": "0.1", "x-build-id": "4do9Q9piSYmUNJ62F" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automationnation~semantic-synthesis-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automationnation-semantic-synthesis-engine", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automationnation~semantic-synthesis-engine/runs": { "post": { "operationId": "runs-sync-automationnation-semantic-synthesis-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automationnation~semantic-synthesis-engine/run-sync": { "post": { "operationId": "run-sync-automationnation-semantic-synthesis-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "sentinelDatasetId", "manifestId", "maxCostUsd", "anthropicApiKey" ], "properties": { "sentinelActorId": { "title": "Sentinel Actor ID", "type": "string", "description": "The Apify actor id or 'username/name' slug of the Delta-Sync Sentinel deployment to read committed manifests from. An agent should treat this as the upstream source-of-truth pointer, not a config detail to guess — always read it from the Sentinel's own actor metadata rather than hardcoding it." }, "sentinelDatasetId": { "title": "Sentinel Dataset ID", "type": "string", "description": "The defaultDatasetId of the specific Sentinel run whose committed chunks should be read. Required because manifestId alone is only unique within one dataset — an agent must carry this value forward from the Sentinel run it is reacting to, not assume a single global dataset." }, "manifestId": { "title": "Manifest ID", "type": "string", "description": "The exact manifest_id emitted by the Sentinel's commit step (see Sentinel README: 'Lifecycle example'). This is the trigger key: synthesis is always scoped to exactly one committed manifest, never to a raw cursor range or an unbounded dataset scan, so that a synthesis run is reproducible and cheap to verify." }, "synthesisMode": { "title": "Synthesis Mode", "enum": [ "structured_extract", "narrative_summary" ], "type": "string", "description": "Which synthesis strategy to run. 'structured_extract' is rule-based and fully deterministic (same chunks -> byte-identical output; prefer this by default). 'narrative_summary' invokes model reasoning and is non-deterministic across model versions — use only when a human-readable narrative is explicitly required, and treat its output as advisory rather than as a fact source.", "default": "structured_extract" }, "maxOutputTokens": { "title": "Max Output Tokens", "minimum": 100, "type": "integer", "description": "Upper bound on synthesis output size. Exists so an agent can budget downstream context-window usage before calling this actor, not just after receiving a response.", "default": 2000 }, "canaryMinCoverageRatio": { "title": "Canary Min Coverage Ratio", "minimum": 0, "maximum": 100, "type": "integer", "description": "The Critic's deterministic acceptance threshold, expressed as a percentage (0-100): the minimum percentage of the manifest's chunk_ids that the synthesis output must traceably reference for the run to pass. Below this, status is 'critic_rejected' rather than 'ok' — this is a hallucination/omission guard, not a quality-of-writing check.", "default": 80 }, "maxCostUsd": { "title": "Max Cost (USD)", "type": "string", "description": "Hard spending ceiling, same contract as the Sentinel's identically-named field: checked before model-assisted synthesis is invoked, and the run self-terminates rather than exceed it. String type because the Apify input form has no float field." }, "anthropicApiKey": { "title": "Anthropic API Key (BYOK)", "type": "string", "description": "Your own Anthropic API key. This actor makes no LLM calls under any shared/platform key — every synthesize() call is billed directly to the key you provide here. Required; the run fails with a structured MISSING_API_KEY error if absent, before any Sentinel data is even fetched." } } }, "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 } } } } } } } } } }