Create task (stream/json)
Create a new task or continue an existing one. Returns SSE by default, or JSON acknowledgement when requested.
Response Modes:
- default (
response_formatomitted): streaming SSE response (text/event-stream) response_format=json: synchronous acknowledgement (202+ task id/status JSON)- if
response_formatis omitted andAccept: application/jsonis sent, JSON acknowledgement is returned.
Mode Options:
agent(default): Full agent mode with all tools, execution capabilities, and memorychat: Conversational mode with limited tools (web search, knowledge search)
Direct Agent Execution:
- Use
agent_idto bypass AgentSwarm and route to a specific agent
Secrets (Opt-In):
- Use
secretsto pass only selected secret names into task runtime - If omitted, no user/project secrets are exposed by default
Authorizations
JWT authentication token
Body
Bypass AgentSwarm and route to specific agent
Array of agent IDs for multi-agent orchestration
Enable the ask_question tool for the planner with durable DB-backed suspension. When false (default), the tool and its prompt sections are removed entirely so the planner must proceed without asking the user clarifying questions.
When mode=plan, auto-execute the plan without waiting for user approval. Omit for goal mode, which is always automatic.
Optional standalone browser session references (brs_) to continue from. With one ref the agent reuses that warm, logged-in browser daemon instead of launching fresh; with multiple, the orchestrator runs one browser subagent per referenced session so each drives its own session. Every ref must exist on the user's sandbox (ownership is validated per ref). Cannot be used with an isolated task.
Optional. When set, controls how task results are handed off on completion. webhook — POST the completion artifact to the team webhook URL when configured. artifact — persist the completion artifact for GET /api/v1/tasks/{id}/artifacts. When omitted, no completion handoff runs.
webhook, artifact Maximum Neo credits this execution may consume.
1 <= x <= 500Optional file references
Optional task ID. If omitted or invalid, server generates one.
Run task in an ephemeral sandbox with no prior user context
Maximum cumulative active runtime; approval suspension time is excluded.
300 <= x <= 86400Max execution-verification loop iterations for agent/plan modes. Goal mode has a fixed 10-run ceiling and rejects this field. When omitted, defaults to 0 for agent mode (no verification) and 1 for plan mode (single execute + verify cycle). 0 = explicitly skip verification. 1+ = run that many execute+verify cycles.
0 <= x <= 5Max LLM steps for execution mode only. Goal mode uses the fixed swarm ceiling of 60 and rejects this field. Does not affect plan or verification phases. Defaults to 45 (direct) or 60 (swarm).
4 <= x <= 200Disable use of memory from previous tasks for this run. Current-task working memory remains available, while personal, team, and learned project memory are not read or updated. Explicit recall of another task is also blocked.
agent = full tools, chat = limited tools, plan = info-gathering + strategic planning, goal = plan once then autonomously execute and verify until complete
agent, chat, plan, goal Optional model. If omitted/empty, server resolves default via user/team/tag policy.
1Project ID to scope task to. If omitted, task is user-scoped.
Optional reasoning effort override for any model that advertises the value.
Read capabilities from /api/v1/models for Neo, byok_models for
BYOK, or ai_connection_models for AI connections, according to the
user's active model source.
none, minimal, low, medium, high, xhigh, max Optional response mode.
- sse: stream response events
- json: immediate acknowledgement with task id/status When omitted, server falls back to Accept header and defaults to sse.
sse, json Optional sandbox to run this task on. Use the id returned by GET /api/v1/sandboxes. When omitted, the Neo-managed cloud sandbox is used. Self-hosted sandboxes require an explicit selection.
Optional secret names to expose at runtime (opt-in). Only listed names are resolved and made available to tools. If omitted or empty, no user/project secrets are exposed.
Optional speed tier for any model that advertises speed support.
Read capabilities from /api/v1/models for Neo, byok_models for
BYOK, or ai_connection_models for AI connections, according to the
user's active model source.
standard, fast Optional shorthand user input. Used only when message.parts is absent.
Optional task title. When set, the title is persisted on create and auto title generation is skipped. When omitted, the agent generates a title from the first user message.
1 - 500Optional per-task pre-execution tool safety review policy. Each tool call is scored against a data-egress policy before it runs. With a reviewer credential configured the default is mode=enforce with fail_closed=false; without one, review is off.
Optional link to an inbox report (HackerOne, GitHub, or Security Inbox). When set, Neo associates this task with that report so triage status appears in the inbox. Starting triage again for the same report replaces the previous link.
Task visibility. Defaults to private when omitted/empty.
private, unlisted, team Response
Streaming SSE response
The response is of type string.

