> **Looking for scheduling?** See [Automation & Tasks](/automation) for choosing the right mechanism. This page covers **tracking** background work, not scheduling it.
Tasks do **not** replace sessions, cron jobs, or heartbeats — they are the **activity ledger** that records what detached work happened, when, and whether it succeeded.
Not every agent run creates a task. Heartbeat turns and normal interactive chat do not. All cron executions, ACP spawns, subagent spawns, and CLI agent commands do.
- Isolated cron runs and subagent completions best-effort clean up tracked browser tabs/processes for their child session before final cleanup bookkeeping.
Main-session cron tasks use `silent` notify policy by default — they create records for tracking but do not generate notifications. Isolated cron tasks also default to `silent` but are more visible because they run in their own session.
Session-backed `video_generate` runs also use `silent` notify policy. They still create task records, but completion is handed back to the original agent session as an internal wake so the agent can write the follow-up message and attach the finished video itself. If you opt into `tools.media.asyncCompletion.directSend`, async `music_generate` and `video_generate` completions try direct channel delivery first before falling back to the requester-session wake path.
While a session-backed `video_generate` task is still active, the tool also acts as a guardrail: repeated `video_generate` calls in that same session return the active task status instead of starting a second concurrent generation. Use `action: "status"` when you want an explicit progress/status lookup from the agent side.
- Subagent tasks: backing child session disappeared from the target agent store.
- Cron tasks: the cron runtime no longer tracks the job as active.
- CLI tasks: isolated child-session tasks use the child session; chat-backed CLI tasks use the live run context instead, so lingering channel/group/direct session rows do not keep them alive.
**Direct delivery** — if the task has a channel target (the `requesterOrigin`), the completion message goes straight to that channel (Telegram, Discord, Slack, etc.). For subagent completions, OpenClaw also preserves bound thread/topic routing when available and can fill a missing `to` / account from the requester session's stored route (`lastChannel` / `lastTo` / `lastAccountId`) before giving up on direct delivery.
**Session-queued delivery** — if direct delivery fails or no origin is set, the update is queued as a system event in the requester's session and surfaces on the next heartbeat.
- Subagent completion delivery prefers the latest visible assistant text; if that is empty it falls back to sanitized latest tool/toolResult text, and timeout-only tool-call runs can collapse to a short partial-progress summary.
1.**Reconciliation** — checks whether active tasks still have authoritative runtime backing. ACP/subagent tasks use child-session state, cron tasks use active-job ownership, and chat-backed CLI tasks use the owning run context. If that backing state is gone for more than 5 minutes, the task is marked `lost`.
[Task Flow](/automation/taskflow) is the flow orchestration layer above background tasks. A single flow may coordinate multiple tasks over its lifetime using managed or mirrored sync modes. Use `openclaw tasks` to inspect individual task records and `openclaw tasks flow` to inspect the orchestrating flow.
A cron job **definition** lives in `~/.openclaw/cron/jobs.json`. **Every** cron execution creates a task record — both main-session and isolated. Main-session cron tasks default to `silent` notify policy so they track without generating notifications.
Heartbeat runs are main-session turns — they do not create task records. When a task completes, it can trigger a heartbeat wake so you see the result promptly.
A task may reference a `childSessionKey` (where work runs) and a `requesterSessionKey` (who started it). Sessions are conversation context; tasks are activity tracking on top of that.
A task's `runId` links to the agent run doing the work. Agent lifecycle events (start, end, error) automatically update the task status — you do not need to manage the lifecycle manually.