Remove no-tool goal continuation suppression (#20523)

## Why

`/goal` is supposed to keep Codex working until the goal is actually
done. The previous continuation logic had two ways to stop early: the
continuation prompt told the model to wait for new input when it felt
blocked, and the runtime suppressed another continuation turn after a
continuation finished without any tool calls.

That made goals stop short even when the agent could still keep making
progress (I received a few reports of this from users). It also relied
on a brittle heuristic that treated "no registry tool calls" as
equivalent to "should stop."

## What changed

- removed the continuation prompt sentence that told the model to stop
and wait for new input when it could not continue productively
- removed the goal runtime suppression heuristic that stopped
auto-continuation after a no-tool continuation turn
- deleted the continuation-activity bookkeeping and left `tool_calls` as
telemetry only
- added focused regressions for the two intended behaviors: completed
no-tool continuation turns still continue, while `request_user_input`
keeps the existing turn open instead of spawning a new continuation
This commit is contained in:
Eric Traut authored and GitHub committed 2026-05-01 09:09:55 -07:00
1 parent 227bee0445
commit 3d1d164aee
5 files changed
+142 -65

No files matched your search

@@ -25,4 +25,4 @@ Before deciding that the goal is achieved, perform a completion audit against th
Do not rely on intent, partial progress, elapsed effort, memory of earlier work, or a plausible final answer as proof of completion. Only mark the goal achieved when the audit shows that the objective has actually been achieved and no required work remains. If any requirement is missing, incomplete, or unverified, keep working instead of marking the goal complete. If the objective is achieved, call update_goal with status "complete" so usage accounting is preserved. Report the final elapsed time, and if the achieved goal has a token budget, report the final consumed token budget to the user after update_goal succeeds.
If the goal has not been achieved and cannot continue productively, explain the blocker or next required input to the user and wait for new input. Do not call update_goal unless the goal is complete. Do not mark a goal complete merely because the budget is nearly exhausted or because you are stopping work.
Do not call update_goal unless the goal is complete. Do not mark a goal complete merely because the budget is nearly exhausted or because you are stopping work.