Extend the model picker to schedules

schedules.model_id (migration 0013) pins every fired run of a recurring spawn
to a registered model backend, exactly like a hand-spawned agent: the worker
copies it into each firing's spawn payload, the launched agent records the pin,
and resumes stay on the same backend. The Schedules form gets the same Model
dropdown as the spawn form (Claude subscription by default), with a badge in
the schedules table. Create/update routes fail fast on a missing or disabled
backend so a stale selection bounces immediately instead of every firing
failing asynchronously in Activity; a backend deleted later still fails each
firing visibly rather than silently falling back to the subscription.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DzDofD7gP63WpeLG8vEdZu
This commit is contained in:
Claude
2026-07-29 18:54:31 +00:00
parent 2d5c0e34d7
commit 44632ea771
40 changed files with 208 additions and 51 deletions
+3 -1
View File
@@ -236,7 +236,9 @@ What the dashboard can now do (all state-changing actions require `ADMIN_TOKEN`)
enqueues a `sync` command so the worker clones it. Manual mode (existing `root_dir`)
still works; every project with a remote gets a **Pull now** button, and spawn always
pulls first.
- **Schedules** — recurring agent spawns: a name prefix, a prompt, and an interval. The
- **Schedules** — recurring agent spawns: a name prefix, a prompt, an interval, and
optionally a **model backend** (the same dropdown the spawn form has — every fired run
spawns on it). The
worker fires each due schedule as a normal queued `spawn` with a timestamped agent name
(`nightly-20260710-090000`), so runs are fresh, stateless agents and show up in
Activity. The canonical prompt keeps its state in the repo: *"Read @notes.md, continue