Bohdan Triapitsyn
bb45164ae8
Arm the target button in the composer and the next prompt becomes a goal: the server keeps the session working toward it (idle tick -> small-model audit -> continuation) until the objective is verifiably complete, blocked, or out of budget — even with the UI closed. Server (packages/web/server/lib/session-goal): - event-driven loop on the global SSE hub; goal state lives in session.metadata.openchamber.goal (merge-safe patches, stale-write guard by goal id), so it survives restarts and syncs to every client for free - the small-model audit (objective + last assistant turn only, language pinned to the objective) is the sole termination authority; blocked needs 3 consecutive verdicts, audit outages tolerate one unaudited continuation then stop the goal as resumable-blocked - hard stops: optional token budget, auto-continuation cap (Resume grants a fresh allowance), turn errors; user abort pauses the goal instead of blocking it, and resuming over an aborted tail nudges immediately - token accounting as a snapshot of the latest turn (input + cache.read + output), goal-relative via a creation baseline and segmented across compactions; a compaction summary skips the audit and continues - continuations reuse the session's own provider/model/agent/variant UI: - three-mode target button (arm / disarm / manage dialog), informational goal strip with inline pause/resume and an Evaluating indicator, sidebar state glyph, objective length counter (2000-char server clamp), read-only completed goals - goal entry points: composer (sessions and drafts), start-new-session- from-answer dialog, plan implement dialog (plan content becomes the objective), scheduled tasks (Run as goal + budget) - Settings -> Chat -> Goal: feature toggle + default token budget with three-layer parity (web server, client persistence, VS Code bridge); VS Code renders goal state but hides the entry points (the loop runs in the web server only) Notifications: per-turn "ready" notifications are suppressed while a goal is active; settling sends one final notification (desktop, web-push, APNs generic titles with the session name as body) honoring the completion toggle. Error/question/permission notifications are untouched. Docs: user guide (session-goals) in all 9 locales + sidebar entry, scheduled-tasks cross-reference, server module DOCUMENTATION.md.
36 lines
1.5 KiB
Plaintext
36 lines
1.5 KiB
Plaintext
---
|
|
title: Scheduled Tasks
|
|
description: Run a prompt automatically on a schedule.
|
|
---
|
|
|
|
# Scheduled Tasks
|
|
|
|
A scheduled task runs a prompt for you on a schedule — for example, a daily "summarize yesterday's changes" or a weekly cleanup. When it runs, OpenChamber starts a new session and sends the prompt on its own. Open the scheduler from the button at the top of the session sidebar.
|
|
|
|
## Create a task
|
|
|
|
1. Open the scheduled tasks dialog from the session sidebar.
|
|
2. Add a task and give it a name.
|
|
3. Choose when it runs:
|
|
- **daily** — at one or more times each day
|
|
- **weekly** — on chosen weekdays and times
|
|
- **once** — a single date and time
|
|
4. Set what it does: the prompt to send, and the provider, model, and agent to use. The prompt can be a slash command, like `/review`.
|
|
5. Save, and make sure the task is enabled.
|
|
|
|
You can run any task immediately with **run now** to check it does what you expect.
|
|
|
|
Check **Run as goal** to make the run pursue its prompt to completion instead of stopping after one reply — see [Session Goals](/session-goals/).
|
|
|
|
## What success looks like
|
|
|
|
After a run, the task shows when it last ran, whether it succeeded, and a link to the session it created. If a run fails, the error is shown there too.
|
|
|
|
## Keep in mind
|
|
|
|
Tasks only fire while the OpenChamber server is running. If you close it, scheduled runs are paused until it's back up.
|
|
|
|
## Related
|
|
|
|
- [Commands & Snippets](/commands-snippets/) — reuse a slash command as the prompt
|