-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
[Bug]: Session status blind spot | Sessions in done state excluded from context saturation monitoring — agents run dead for hours undetected #91832
Copy link
Copy link
Closed as not planned
Closed as not planned
Copy link
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.bugSomething isn't workingSomething isn't workingclawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:message-lossChannel message delivery can be lost, duplicated, or misrouted.Channel message delivery can be lost, duplicated, or misrouted.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.staleMarked as stale due to inactivityMarked as stale due to inactivity
Description
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.bugSomething isn't workingSomething isn't workingclawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:message-lossChannel message delivery can be lost, duplicated, or misrouted.Channel message delivery can be lost, duplicated, or misrouted.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.staleMarked as stale due to inactivityMarked as stale due to inactivity
Type
Fields
Priority
None yet
Bug type
Behavior bug (incorrect output/state without crash)
Beta release blocker
No
Summary
Sessions in
donestate excluded from context saturation monitoring — agents run dead for hours undetectedSteps to reproduce
runningtodonestatusdonestate are not flagged by Sentinel or Shadow monitoringExpected behavior
Sessions in
donestate should still trigger context saturation alerts if they exceed the configured threshold. Adonesession at 100% context is a zombie session that needs cleanup — it should be treated the same as arunningsession for monitoring purposes.Actual behavior
Sessions in
donestate are invisible to monitoring. Observed agents running dead for 627 minutes (Cato), 638 minutes (Sentry), and 2,914 minutes (Mando Telegram) with zero alerts fired. Only discovered manually.OpenClaw version
2026.6.1
Operating system
macOS 15.4
Install method
npm global
Model
anthropic/claude-sonnet-4-6
Provider / routing chain
openclaw -> anthropic
Additional provider/model setup details
No response
Logs, screenshots, and evidence
Impact and severity
Critical. Compliance-critical agents (Cato — compliance orchestrator for SEC-registered RIA) ran unresponsive for 10+ hours with no detection. Any message sent to those agents during the window failed silently.
Additional information
Fleet context: 32+ agent fleet on macOS 15.4, OpenClaw 2026.6.1. Observed Cato (compliance orchestrator) dead for 627 minutes, Sentry dead for 638 minutes, Mando Telegram session dead for 2,914 minutes — all in
donestate at 100% context. Zero alerts fired. Root cause identified: Shadow v1 only monitoredrunningsessions. Workaround deployed: custom Shadow v2 script checking all session states. This should be native OpenClaw behavior, not requiring a custom workaround.