Keep parent agents alive while child work runs (#2458)

* fix(server): keep active agent trees resident

Idle collection treated an inactive parent turn as process quiescence even when descendant work was still running. Protect managed and provider-owned subagent trees, carry descendant activity into the idle window, and use a conservative 30-minute fallback.

* fix(server): close idle collection races

Retain managed ancestry across closed intermediates, refresh descendant state after each awaited close, and invalidate running provider subagents when their runtime is terminated.

* fix(server): serialize agent tree collection

Keep ancestors resident until managed descendants are collected, serialize descendant registration with idle collection, and preserve provider subagent state across hot reloads.

* fix(server): retain closed descendant activity

Carry persisted descendant activity through runtime closure, avoid error children pinning parents, and cancel stale provider children when reload replacement aborts.

* test(server): make descendant expiry deterministic

* fix(server): scope idle child protection

* fix(server): tighten idle tree coordination

* fix(server): reduce aggressive idle cleanup

Keep the mitigation conservative: extend the idle timeout without inferring tree liveness from incomplete lifecycle signals.

* fix(server): keep parents alive during child work

Idle cleanup now respects running managed and provider-native children while retaining a conservative 30-minute fallback.

* fix(server): clear running child state on close

* fix(server): drain child events before close
This commit is contained in:
Mohamed Boudra
2026-07-27 12:12:22 +02:00
committed by GitHub
parent 1d1132de9c
commit 80c8a08393
4 changed files with 203 additions and 15 deletions

View File

@@ -21,11 +21,12 @@ the agent runs through `ensureAgentLoaded()`, which resumes the durable provider
same Paseo agent ID. Provider history is not appended again when the canonical timeline is already
primed.
The daemon collects an eligible idle runtime after two minutes and sweeps every 15 seconds. Only
The daemon collects an eligible idle runtime after 30 minutes and sweeps every minute. Only
unarchived, non-internal agents that are exactly `idle`, have no active or pending run, replacement,
or permission, and have not been activated during the idle window are eligible. `running`,
`initializing`, and `error` agents stay resident. Subagents are considered independently; collection
does not cascade or change parentage.
`initializing`, and `error` agents stay resident. An idle parent also stays resident while current
in-memory state shows a running managed child or provider subagent. Otherwise agents are evaluated
independently; collection does not cascade or change parentage.
Active schedules targeting an existing agent protect that agent from collection. Paused, completed,
and new-agent schedules do not. A pane may remain open after collection; its next prompt resumes the