--- title: "Get Assistant Task" method: GET path: "/api_partner/assistant/tasks/{task_id}" tags: ["Assistant"] --- # Get Assistant Task `GET /api_partner/assistant/tasks/{task_id}` Poll the status and results of an assistant task. Call this endpoint repeatedly until the status is `SUCCESS`. ## Task States | Status | Description | |--------|-------------| | `PENDING` | Task is queued, not yet started | | `STARTED` | Task is actively processing — `info` contains progress details | | `SUCCESS` | Task completed — `result` contains the full response | | `FAILURE` | Task failed — `error` contains the error message | | `CANCELLED` | Task was cancelled via the cancel endpoint | | `REVOKED` | Task was revoked | ## Progress Info (during `STARTED`) While the task is running, the `info` field provides real-time progress: ```json { "id": "abc123", "status": "STARTED", "info": { "step": "EXECUTING_SEARCHES", "stepNumber": 3, "response": "partial response text...", "searches": ["query 1", "query 2"], "publicationsUsed": ["10.1234/example"], "publicationsConsulting": ["Author et al., Title, Journal, 2024"], "currentSearch": "current query being executed" } } ``` **Processing steps in order:** 1. `SCHEDULING_ASSISTANT` — task queued 2. `GENERATING_SEARCH_STRATEGY` — AI generating search queries 3. `EXECUTING_SEARCHES` — running queries against Elasticsearch 4. `RETRIEVING_UPLOADED_DOCUMENTS` — loading reference check documents (if applicable) 5. `RETRIEVING_PRIMARY_SOURCES` — enriching with primary source data 6. `COMPOSING_RESPONSE` — preparing context for LLM 7. `GENERATING_RESPONSE` — LLM generating the answer ## Success Result ```json { "id": "abc123", "status": "SUCCESS", "result": { "title": "How does protein structure affect function?", "sessionId": 42, "slug": "how-does-protein-structure-affect-function-xK9mP", "turns": [...], "lastUpdated": "2025-01-15", "createdAt": "2025-01-15", "tooManySessions": false } } ``` ## Turn Structure Each assistant turn in the `turns` array contains: | Field | Type | Description | |-------|------|-------------| | `role` | str | `"user"` or `"assistant"` | | `content` | str | Response text with numbered citation markers like `[1]`, `[2]` | | `structuredResponse` | list or null | Structured response data (when `useStructuredResponse` was true) | | `references` | list | Cited references (see below) | | `searchStrategy` | list[str] or null | Search queries that were used | | `warning` | str or null | Warning message if applicable | | `model` | str or null | The model that generated this response | | `settings` | dict or null | Settings applied (e.g., AI-suggested `rankBy`, `yearFrom`, `yearTo`) | | `publicationsConsulted` | list[dict] or null | All publications considered (including unused ones) | ## Reference Structure Each reference in the `references` array: | Field | Type | Description | |-------|------|-------------| | `answer` | str | The relevant text passage (citation statement or abstract excerpt) | | `texts` | list[str] | Text passages used | | `context` | str | Surrounding context of the passage | | `title` | str | Paper title | | `doi` | str | Paper DOI | | `link` | str | Link to the scite report page | | `type` | str | `"abstract"` or `"citation_statement"` | | `paper` | object | Full paper metadata (title, authors, journal, year, date, abstract, tally, DOI, etc.) | | `patent` | object or null | Patent data if from patent search | | `refCheckId` | str or null | Reference check task ID if from uploaded document | ## Path parameters - `task_id` string, required ## Headers - `authorization` string — Set to `Bearer ` to pass token for authorization. ## Response `200` Successful Response - AssistantPollingResponseSchema - `id` string, nullable - `info` AssitantPollingInfo - `step` string, nullable - `stepNumber` integer, nullable - `response` string, nullable - `structuredResponse` unknown[], nullable - unknown - `searches` string[], nullable - `publicationsUsed` string[], nullable - `publicationsConsulting` string[], nullable - `currentSearch` string, nullable - `dois` string[], nullable - `factChecks` FactCheck - `used` unknown[], nullable - unknown - `rejected` unknown[], nullable - unknown - `status` string, nullable - `result` AssistantResponseSchema - `title` string, nullable - `sessionId` integer, nullable - `turns` TurnSchemaOutput[] - `role` string, nullable - `content` string, nullable - `sections` string[], nullable - `structuredResponse` unknown[], nullable - unknown - `references` SciteapiModelsAssistantReferenceSchemaOutput[] - `answer` string, required - `texts` string[], required - `textSources` string[], nullable - `context` string, required - `title` string, required - `doi` string, required - `link` string, required - `type` string - `paper` SearchResultSchemaWithDateStrOutput, required - `id` string, nullable - `doi` string, nullable - `title` string, nullable - `slug` string, nullable - `authors` AuthorResults[], nullable - `authorName` string, nullable - `authorSlug` string, nullable - `authorSequenceNumber` union - … - `affiliation` string, nullable - `affiliationSlug` string, nullable - `journal` string, nullable - `shortJournal` string, nullable - `publisher` string, nullable - `memberId` integer, nullable - `abstract` string, nullable - `year` integer, nullable - `date` string, nullable - `lastUpdate` integer, nullable - `volume` string, nullable - `issue` string, nullable - `page` string, nullable - `tally` TallyResponse - `total` integer, required - `supporting` integer, required - `contradicting` integer, required - `mentioning` integer, required - `unclassified` integer, required - `doi` string, nullable - `citingPublications` integer, nullable - `issns` string[], nullable - `editorialNotices` EditorialNoticeSchema[] - `status` string, nullable - `date` string, nullable - `noticeDoi` string, nullable - `doi` string, required - `urls` string[], nullable - `normalizedTypes` string[] - `isOa` boolean - `oaStatus` string - `meshTypes` PubmedMeshTypeResponse[] - `descriptorId` string, required - `descriptorName` string, required - `qualifierId` string, nullable - `qualifierName` string, nullable - `relevancyScore` number, nullable - `citations` CitationSearch[] - `id` integer, nullable - `source` string, required - `target` string, required - `negative` number, nullable - `positive` number, nullable - `neutral` number, nullable - `section` string, nullable - `expertClassification` string, nullable - `type` string, nullable - `typeConfidence` number, nullable - `snippet` string, required - `lang` string, nullable - `langConfidence` number, nullable - `refLocation` string, nullable - `memberId` integer, nullable - `selfCites` SelfCiteSchema[] - … - `snippetHidden` boolean - `fulltextExcerpts` string[] - `highlightedFields` string[] - `patent` object, nullable - `refCheckId` string, nullable - `included` boolean, nullable - `reason` string, nullable - `feedback` FeedbackSchema - `feedbackType` 'positive' | 'negative' - `reason` string, nullable - `searchStrategy` string[], nullable - `warning` string, nullable - `model` string, nullable - `settings` object, nullable - `publicationsConsulted` object[], nullable - `columns` StructuredColumn[], nullable - `name` string, required - `slug` string, required - `instructions` string, nullable - `type` 'response' | 'dynamic' - `order` integer - `json_response_type` 'concise' | 'boolean', nullable - `turnsTotal` integer, nullable - `turnsOffset` integer, nullable - `lastUpdated` string, date, nullable - `shareToken` string, nullable - `createdAt` string, date, nullable - `hasUploadedReferences` boolean - `slug` string, required - `error` string, nullable - `usage` AssistantUsageSchema - `used` integer, required - `max` integer, required ## Other responses - `422` — Validation Error --- [API](https://skmtc.net/scite/apis/scite-api.md) · [All operations](https://skmtc.net/scite/apis/scite-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/scite/scite-api/revisions/9f4cba020e89/schema)