-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
[Bug]: Long-running tasks complete but agent doesn't reply to user #96263
Copy link
Copy link
Closed
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.regressionBehavior that previously worked and now failsBehavior that previously worked and now failsstaleMarked 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.regressionBehavior that previously worked and now failsBehavior that previously worked and now failsstaleMarked as stale due to inactivityMarked as stale due to inactivity
Type
Fields
Priority
None yet
Bug type
Regression (worked before, now fails)
Beta release blocker
No
Summary
When executing long-running tasks (15-30 minutes) via custom tools, the task completes successfully but the agent never sends the result back to the user. The user must explicitly ask "why didn't you reply?" to get the result.
Steps to reproduce
exec(..., background: true)→process(poll, timeout=1800000)process✓Expected behavior
After
process(poll)returns with the completed task result, the agent should automatically:Actual behavior
OpenClaw version
2026.6.9
Operating system
macOS (Darwin 25.3.0, arm64)
Install method
package manager
Model
Claude Opus 4.6
Provider / routing chain
dingding -> openclaw -> extentions
Additional provider/model setup details
Configuration (sanitized)
{ "channels": { "dingtalk-connector": { "accounts": { "my_account": { "asyncMode": false, "separateSessionByConversation": true } } } }, "agents": { "list": [{ "tools": { "profile": "coding", "alsoAllow": ["custom_tool"] } }] } }Workaround
Manually call
message(action: 'send', ...)after tool completes, but agent doesn't do this automatically.Questions
Logs, screenshots, and evidence
Impact and severity
Additional information
Suspected Root Cause
Possibly related to v2026.6.9 changes:
Hypothesis:
process(poll)waits