You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Delegated children are told never to watch their PR, so nobody follows CI on a child's fix PR #25637
T3 injects this into every provider's system prompt (<pull_request_linking>):
Delegated children never watch, even if the brief says babysit. After PR work, a child's last line is: PR , head , checks and reviews .
So a delegated child that opens a fix PR always ends its turn without watch_pull_request, even when its task explicitly says to watch the PR, fix CI and report when it's green. Nobody follows up on CI for that PR unless the parent builds its own polling.
In the fleet (Issue Triager and PR Takeovers dispatchers on nucbox-1, leads on 40 linked VMs), leads' briefs say to watch the fix PR, fix CI and add bugfix when it's green. The dispatchers resolved the conflict in favour of this rule. Since 2026-10-24, about 1,200 lead dispatches carried "do not watch", and 184 fix PRs from issue leads have no CI follow-up record.
Expected
Julius has decided that the lead that opens a fix PR owns its CI follow-up through a PR watch. So:
A delegated child may call watch_pull_request on its own PR when its task asks for it. The injected instructions should say "watch only when your task asks for it" instead of "never".
The parent is told the child is watching, e.g. the delegated task result or task_status says the child holds a PR watch on , so the parent doesn't treat the child's interim result as final.
packages/provider-core/src/server/runtimeInstructions.ts:1-3 (PULL_REQUEST_LINKING_INSTRUCTIONS, origin/main fe507c5a1e). The rule exists only in this prompt text; watch_pull_request itself (apps/server/src/mcp/toolkits/pullRequests/tools.ts:309) doesn't restrict children.
Activity