> ## Documentation Index > Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Continue Agent Run > Advance a persisted agent run from its current state. Dispatches on the body shape and the persisted run state. **Variants:** - PAUSED + tools provided → apply HITL tool results, resume - PAUSED + resolved admin approval (empty tools) → apply resolution, resume - RUNNING / ERROR (no unresolved HITL requirements) → resume from last persisted state - COMPLETED + new tools → continue with appended messages **Tools Parameter:** JSON string containing array of tool execution objects with results. Optional — only required when the persisted run has unresolved HITL requirements. ## OpenAPI ````yaml post /agents/{agent_id}/runs/{run_id}/continue openapi: 3.1.0 info: title: Agno API Reference description: The all-in-one, private, secure agent platform that runs in your cloud. version: 3.0.4 servers: [] security: [] paths: /agents/{agent_id}/runs/{run_id}/continue: post: tags: - Agents summary: Continue Agent Run description: >- Advance a persisted agent run from its current state. Dispatches on the body shape and the persisted run state. **Variants:** - PAUSED + tools provided → apply HITL tool results, resume - PAUSED + resolved admin approval (empty tools) → apply resolution, resume - RUNNING / ERROR (no unresolved HITL requirements) → resume from last persisted state - COMPLETED + new tools → continue with appended messages **Tools Parameter:** JSON string containing array of tool execution objects with results. Optional — only required when the persisted run has unresolved HITL requirements. operationId: continue_agent_run parameters: - name: agent_id in: path required: true schema: type: string title: Agent Id - name: run_id in: path required: true schema: type: string title: Run Id requestBody: content: application/x-www-form-urlencoded: schema: $ref: '#/components/schemas/Body_continue_agent_run' responses: '200': description: Agent run continued successfully content: application/json: schema: {} text/event-stream: example: |+ event: RunContent data: {"created_at": 1757348314, "run_id": "123..."} '400': description: Invalid JSON in tools field or invalid tool structure content: application/json: schema: $ref: '#/components/schemas/BadRequestResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/UnauthenticatedResponse' '403': description: >- Run has a pending admin approval and cannot be continued by the user yet. '404': description: Agent not found content: application/json: schema: $ref: '#/components/schemas/NotFoundResponse' '409': description: >- Continuation conflict: a durable queue ticket owns this run's continuation (continue it with background=true), or a continuation is already queued or executing. Runs in any state can be continued - a COMPLETED run forks into a follow-up; RUNNING/ERROR runs resume. '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/ValidationErrorResponse' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/InternalServerErrorResponse' security: - {} - HTTPBearer: [] components: schemas: Body_continue_agent_run: properties: tools: type: string title: Tools description: JSON string of tool call results to continue the paused run default: '' input: anyOf: - type: string - type: 'null' title: Input description: >- Optional new user-message text to append to the run before resuming. Use for continuing a COMPLETED run with a follow-up, or adding context to a RUNNING/ERROR resume. continue_from: type: string title: Continue From description: >- Continuation boundary. Use 'end', 'last_user', or a numeric message index. default: end fork: type: boolean title: Fork description: >- When true, clone the run with a new ``run_id`` before resuming. The original is untouched; the clone becomes a sibling within the same session, with ``forked_from_run_id`` set. default: false regenerate: type: boolean title: Regenerate description: >- Sugar: regenerate the last response of this run. Auto-computes ``continue_from='last_user'`` to land just after the last user message. Pair with ``additional_instructions`` to steer the new output. By default the original response is hidden from history (replaced); pass ``replace_original=false`` to keep both the original and the regenerated response visible side by side. default: false replace_original: anyOf: - type: boolean - type: 'null' title: Replace Original description: >- Only valid with ``regenerate=true``. Controls history visibility of the original response; the original run is always retained in storage. Defaults to true: the original is marked REGENERATED and hidden from history so the new response replaces it. Pass false to keep both the original and regenerated responses visible. additional_instructions: anyOf: - type: string - type: 'null' title: Additional Instructions description: >- Only valid with ``regenerate=true``: extra guidance appended as a user message before re-generation. Friendly alias for ``input``. session_id: anyOf: - type: string - type: 'null' title: Session Id description: Session ID for the paused run user_id: anyOf: - type: string - type: 'null' title: User Id description: User identifier for tracking and personalization stream: type: boolean title: Stream description: Enable streaming responses via Server-Sent Events (SSE) default: true background: type: boolean title: Background description: >- Run continue in background (survives client disconnect). Requires database. Use /resume to reconnect. default: false type: object title: Body_continue_agent_run BadRequestResponse: properties: detail: type: string title: Detail description: Human-readable error message error_id: anyOf: - type: string - type: 'null' title: Error Id description: >- Stable identifier for the specific error, present only when the error carries one error_type: anyOf: - type: string - type: 'null' title: Error Type description: Category of the error, present only when the error carries one type: object required: - detail title: BadRequestResponse example: detail: Bad request UnauthenticatedResponse: properties: detail: type: string title: Detail description: Human-readable error message error_id: anyOf: - type: string - type: 'null' title: Error Id description: >- Stable identifier for the specific error, present only when the error carries one error_type: anyOf: - type: string - type: 'null' title: Error Type description: Category of the error, present only when the error carries one type: object required: - detail title: UnauthenticatedResponse example: detail: Unauthenticated access NotFoundResponse: properties: detail: type: string title: Detail description: Human-readable error message error_id: anyOf: - type: string - type: 'null' title: Error Id description: >- Stable identifier for the specific error, present only when the error carries one error_type: anyOf: - type: string - type: 'null' title: Error Type description: Category of the error, present only when the error carries one type: object required: - detail title: NotFoundResponse example: detail: Not found ValidationErrorResponse: properties: detail: anyOf: - type: string - items: $ref: '#/components/schemas/ValidationErrorDetail' type: array title: Detail description: >- A single message for an explicitly raised 422, or a list of field-level errors for a request-validation failure type: object required: - detail title: ValidationErrorResponse description: >- 422 body. Two runtime shapes share this status code, and the same endpoint can return either, so ``detail`` is typed as their union: - FastAPI's request-validation handler emits a **list** of field-level errors (built-in coercion errors and custom-validator ``ValueError``s alike). - A route that raises ``HTTPException(status_code=422, detail="...")`` for a semantic check (e.g. an invalid cron expression) emits a **string** through the HTTPException handler. example: detail: - loc: - body - endpoint msg: Value error, Endpoint must be a path, not a full URL type: value_error InternalServerErrorResponse: properties: detail: type: string title: Detail description: Human-readable error message error_id: anyOf: - type: string - type: 'null' title: Error Id description: >- Stable identifier for the specific error, present only when the error carries one error_type: anyOf: - type: string - type: 'null' title: Error Type description: Category of the error, present only when the error carries one type: object required: - detail title: InternalServerErrorResponse example: detail: Internal server error ValidationErrorDetail: properties: loc: items: anyOf: - type: string - type: integer type: array title: Loc description: Path to the offending field, e.g. ['body', 'endpoint'] msg: type: string title: Msg description: Human-readable error message type: type: string title: Type description: Error type identifier, e.g. 'value_error' or 'missing' type: object required: - loc - msg - type title: ValidationErrorDetail description: >- One field-level error inside a 422 body, matching FastAPI's default shape. securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.