Read-only investigator agents cannot settle themselves via subagent-stop #548
Labels
No labels
P0
P1
P2
P3
bug
create
delete
enhancement
filed-by/agent
filed-by/user
frozen
lint-rule
needs-info
needs-triage
next
plugin/cc-architect
plugin/os
plugin/os-adr
plugin/os-aidd-lint
plugin/os-backlog
plugin/os-context
plugin/os-doc-hygiene
plugin/os-sdlc
plugin/os-vault
project/cc-os
ready-for-agent
ready-for-human
recurring
review
update
waiting
wayfinder:grilling
wayfinder:map
wayfinder:map
wayfinder:research
wayfinder:task
wayfinder:task
wontfix
worklist/deviations
worklist/lint-rule
worklist/new-implement-build
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set
Reference
jared/cc-os#548
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Read-only investigator agents cannot settle themselves via subagent-stop [capture]
Context
ADR-0144 makes settlement agent-initiated: an agent settles by calling the subagent-stop CLI itself and relaying
next_step. In implement rund233a2f7, ticket #542 implementation 6, two read-only investigator agents could not do this because their sandbox refuses the stop command.Observed
code-probe dispatch, 14:37:44 EDT, and message-tracer dispatch, 14:39:06 EDT, both reported the same failure.
The orchestrator had to submit the subagent-stop payload by hand for each of the two dispatches, from the scratchpad.
Reproduce
Expected
A read-only investigator agent must be able to settle itself without hand intervention. Either:
Origin