> ## Documentation Index > Fetch the complete documentation index at: https://firecrawl-capy-docs-factual-copy-fixes.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Get Agent Status > Are you an AI agent that needs a Firecrawl API key? See [firecrawl.dev/agent-onboarding/SKILL.md](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for automated onboarding instructions. ## OpenAPI ````yaml api-reference/v2-openapi.json GET /agent/{jobId} openapi: 3.0.0 info: title: Firecrawl API version: v2 description: >- API for interacting with Firecrawl services to perform web scraping and crawling tasks. contact: name: Firecrawl Support url: https://firecrawl.dev/support email: support@firecrawl.dev servers: - url: https://api.firecrawl.dev/v2 security: - bearerAuth: [] paths: /agent/{jobId}: parameters: - name: jobId in: path description: The ID of the agent job required: true schema: type: string format: uuid get: tags: - Agent summary: Get the status of an agent job operationId: getAgentStatus responses: '200': description: Successful response content: application/json: schema: type: object properties: success: type: boolean status: type: string enum: - processing - completed - failed data: type: object description: >- The extracted data (only present when status is completed). Never set on a failed run, including one that stopped at its credit limit. partial: description: >- Best-effort JSON recovered from an incomplete run. Only present on some failed runs, such as one that reached `maxCredits`; never present while the run is processing. It may be missing rows or fields, so do not treat it as a completed result. partialSchemaValid: type: boolean description: >- Whether `partial` validates against the request's JSON schema. Only present when `partial` is present and the request included a `schema`. stopReason: type: string enum: - credit_limit_reached description: >- Why a failed run stopped early. `credit_limit_reached` means the run hit its `maxCredits` limit. Only present when status is failed. message: type: string description: >- A note from the agent about the result. In `chat` mode, a follow-up that asks for no new data is answered here instead of in `data`. On a failed credit-limit stop, it may explain what is incomplete. model: type: string enum: - spark-2 - spark-1-pro - spark-1-mini default: spark-2 description: >- Model preset used for the agent run. Every new run executes on spark-2; Spark 1 names only appear on legacy runs. effort: type: string enum: - low - medium - high description: >- Reasoning budget used for the agent run (only present for runs that set effort) error: type: string description: Error message (only present when status is failed) expiresAt: type: string format: date-time creditsUsed: type: number threadId: type: string format: uuid description: The thread this run belongs to. threadTurn: type: integer description: This run's turn in the thread, starting at 1. mode: type: string enum: - extract - chat suggestions: type: array description: >- Follow-ups the agent offers for the next turn of the thread. items: type: object properties: label: type: string prompt: type: string pendingApproval: $ref: '#/components/schemas/AgentPendingApproval' exchange: $ref: '#/components/schemas/AgentExchangeSummary' '400': description: Bad request — the job ID is not a valid UUID. content: application/json: schema: type: object properties: error: type: string example: Invalid job ID format. Job ID must be a valid UUID. '404': description: Agent job not found content: application/json: schema: type: object properties: error: type: string example: Agent job not found security: - bearerAuth: [] components: schemas: AgentPendingApproval: type: object description: >- What the turn stopped to ask. Answer it on the next turn of the thread with `exchange.approve` or `exchange.decline`. properties: id: type: string description: Send this as `approvalId`. kind: type: string enum: - calls - terms description: >- `calls`: paid provider calls held back by `requireApproval`. `terms`: providers whose data terms need accepting (`onTermsRequired: "ask"`). Absent on items written before terms offers existed, which are `calls`. reason: type: string description: Why the agent wants to make these calls. calls: type: array description: The paid calls waiting for approval. Empty on a `terms` approval. items: type: object properties: id: type: string description: Pass in `exchange.approve.callIds` to approve only some calls. provider: type: string capability: type: string input: type: object description: The options the call would run with. more: type: array items: type: object description: Further inputs the same call would run with. creditsEstimate: type: number nullable: true description: Estimated credits, or null when unknown. terms: type: array description: On a `terms` approval, the providers whose terms need accepting. items: type: object properties: provider: type: string name: type: string capability: type: string adds: type: string description: What the provider would add. version: type: string description: The terms version. digest: type: string nullable: true description: >- Null when the catalog published no digest; `terms/show` returns it. url: type: string description: Where a person accepts the terms in the dashboard. resolution: type: object nullable: true description: Null until a later turn answers the approval. properties: approved: type: boolean callIds: type: array items: type: string always: type: boolean byRunId: type: string AgentExchangeSummary: type: object description: >- What the run did with Alexandria. `toolkits` and `requireApproval` are what the run resolved to after thread inheritance. properties: enabled: type: boolean toolkits: type: array items: type: string description: >- Pinned providers. Empty or absent means every provider the team can use. requireApproval: type: boolean onTermsRequired: type: string enum: - skip - ask paidCalls: type: integer description: Paid provider calls the run made. creditsUsed: type: number nullable: true description: Credits the provider calls used, or null when unknown. skippedProviders: type: array description: >- Providers that would have helped but need data terms your team has not accepted. Any `onTermsRequired` mode. items: type: object properties: provider: type: string name: type: string capability: type: string adds: type: string description: What the provider would have added. reason: type: string enum: - terms_required version: type: string description: The terms version. termsUrl: type: string description: Where a person accepts the terms in the dashboard. requiresAction: type: object description: >- `onTermsRequired: "ask"` only, when a terms offer ended the turn: the calls to view and accept each provider's terms. Nothing here runs for you, and `terms/accept` must only be called after your user explicitly agrees. properties: type: type: string enum: - accept_terms approvalId: type: string description: >- The `terms` `pendingApproval` to answer once the terms are accepted. providers: type: array items: type: object properties: provider: type: string name: type: string capability: type: string adds: type: string version: type: string digest: type: string nullable: true description: >- Null when the catalog published no digest; `terms/show` returns it. url: type: string show: type: object description: >- The `terms/show` call, as `{ provider, capability, options }` for `/v2/scrape` `alexandria`. accept: type: object description: >- The `terms/accept` call, as `{ provider, capability, options }` for `/v2/scrape` `alexandria`. securitySchemes: bearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.