> ## Documentation Index > Fetch the complete documentation index at: https://docs.neo.projectdiscovery.io/llms.txt > Use this file to discover all available pages before exploring further. # Abort a single subagent run or tool call > Cancel one in-flight unit of work inside an active task — either a subagent run or a tool call — without stopping the parent task or its siblings. Provide exactly one of `subagent_run_id` or `tool_call_id`: - `subagent_run_id`: aborts that subagent run. The parent agent's LLM sees a structured tool result for the `trigger_*_agent` call indicating the subagent was aborted, and reasons over it. The id is surfaced in the stream via `data-subagent-stream` chunks (`subagent_run_id` field). - `tool_call_id`: aborts that tool execution. The enclosing agent sees a structured `🛑 ABORTED` tool result and reasons over it like any other tool error. The id is the Mastra-generated id surfaced in `tool-input-available` / `tool-call` stream chunks. Exactly one of the two ids must be present (not both, not neither). Idempotent: unknown ids return 200 with `success: true` and `found: false`. ## OpenAPI ````yaml https://neo.api.projectdiscovery.io/api/openapi.json post /api/v1/tasks/{id}/abort-tools openapi: 3.1.0 info: contact: name: ProjectDiscovery url: https://neo.projectdiscovery.io description: Neo API Server - Security agent orchestration platform license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 title: Neo API version: 1.0.0 servers: - description: Production url: https://neo.api.projectdiscovery.io - description: Development url: https://neo.api.dev.projectdiscovery.io - description: Local development url: http://localhost:8080 security: [] tags: - description: Task execution and management name: Tasks - description: Agent listing and management name: Agents - description: Public agent directory name: Agent Directory - description: User file storage management name: Files - description: User working memory management name: Memory - description: Scheduled and recurring task management name: Schedules - description: Knowledge base and semantic search name: Knowledge - description: Encrypted user credentials and API keys name: Secrets - description: Neo API key management for programmatic access name: API Keys - description: User profile and account information name: User - description: Task and LLM usage tracking name: Usage - description: Bring Your Own Key provider management name: BYOK - description: Model discovery and capabilities name: Models - description: Third-party integrations name: Integrations - description: Skill knowledge documents for agent prompts name: Skills - description: Team management and member invitations name: Teams - description: Prompt library management and discovery name: Prompts - description: Slack bot integration for workspace installation and OAuth name: Slack - description: GitHub integration for PR reviews and repository management name: GitHub - description: Vulnerability issue tracking and management name: Issues - description: Subscription billing and plans name: Billing - description: Project management and member assignments name: Projects - description: SSH key pair generation and management for remote server access name: SSH Keys - description: Codebase structural analysis and mapping name: Codemaps - description: AI-generated codebase documentation and security analysis name: CodeWiki - description: Captured HTTP traffic query and replay name: Network Events - description: Vulnerability triage for HackerOne, GitHub, and Security Inbox name: Triage - description: >- Application-internal endpoints used by the Neo UI. Not part of the public customer API surface. name: Internal paths: /api/v1/tasks/{id}/abort-tools: post: tags: - Tasks summary: Abort a single subagent run or tool call description: | Cancel one in-flight unit of work inside an active task — either a subagent run or a tool call — without stopping the parent task or its siblings. Provide exactly one of `subagent_run_id` or `tool_call_id`: - `subagent_run_id`: aborts that subagent run. The parent agent's LLM sees a structured tool result for the `trigger_*_agent` call indicating the subagent was aborted, and reasons over it. The id is surfaced in the stream via `data-subagent-stream` chunks (`subagent_run_id` field). - `tool_call_id`: aborts that tool execution. The enclosing agent sees a structured `🛑 ABORTED` tool result and reasons over it like any other tool error. The id is the Mastra-generated id surfaced in `tool-input-available` / `tool-call` stream chunks. Exactly one of the two ids must be present (not both, not neither). Idempotent: unknown ids return 200 with `success: true` and `found: false`. operationId: post-v1-tasks-id-abort-tools parameters: - description: Task ID in: path name: id required: true schema: format: uuid type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/AbortToolsRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/AbortToolsResponse' description: Target aborted successfully (or already gone) '400': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Invalid request (not exactly one of subagent_run_id / tool_call_id) '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Unauthorized '404': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Task or active stream not found security: - BearerAuth: [] - ApiKeyAuth: [] components: schemas: AbortToolsRequest: description: | Provide exactly one of `subagent_run_id` or `tool_call_id`. Both present or both absent is rejected with 400. Which field is set selects what gets aborted (a subagent run vs. a tool call). properties: subagent_run_id: description: | Subagent run id surfaced in the stream's `data-subagent-stream` chunks. Unique per concurrent subagent invocation within a task. Set this to abort a subagent run. type: string tool_call_id: description: | Mastra-generated tool call id surfaced in `tool-input-available` and `tool-call` stream chunks. Set this to abort a tool call. type: string type: object AbortToolsResponse: properties: found: description: | True iff the target id was actually present and aborted. False means the id was wrong or the target had already finished. Idempotent: success stays true regardless. type: boolean message: type: string stream_id: type: string subagent_run_id: description: Echoed back when a subagent run was the target. type: string success: type: boolean target: description: Which kind of target the request acted on. enum: - subagent - tool type: string tool_call_id: description: Echoed back when a tool call was the target. type: string required: - success - message - stream_id type: object ErrorResponse: properties: code: description: > Stable machine-readable error code — branch on this rather than matching the human `error`/`message` strings. Domain codes include `user_spending_cap_reached`, `project_spending_cap_reached`, and `insufficient_neo_credits`; otherwise it mirrors the error kind (e.g. `forbidden`, `invalid_request`, `not_exists`, `already_exists`). example: user_spending_cap_reached type: string error: example: Bad request type: string error_id: description: Correlation id for a specific error instance, when present. type: string kind: description: Coarse error category (e.g. "forbidden request", "invalid request"). example: forbidden request type: string message: description: | Human-readable detail (the kind prefixed to the error). For display, not for branching. type: string required: - error type: object securitySchemes: BearerAuth: bearerFormat: JWT description: JWT authentication token scheme: bearer type: http ApiKeyAuth: description: Neo API key (neo_sk_* prefix) in: header name: X-Api-Key type: apiKey ````