After Stop, the step's Thinking indicator keeps animating: a thought the abort cut off is never cleared #174
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?
After Stop run on run 66,
agent.summarizeread interrupted: a grey ■, "Summarise the change — interrupted", and the reason "stopped with the run". Below that card, though, the orange Thinking indicator went on animating. It was still animating after trogdor was powered off and the status light read Backend down. A step that has ended, on a backend that is off, cannot be thinking.Cause
The animated row is not drawn from the step's state. It is the console's live buffer of the part the model is writing: stream B's deltas, held in
deltaStore(ui/src/state/store.ts) and drawn byLiveText→ThinkingIndicator(ui/src/components/Transcript.tsx,Reasoning.tsx).A live part leaves that buffer in only two ways (
ingest,store.ts):oc.part.reasoningoroc.part.textwithtime.end(partEnds);oc.child.ended.A Stop aborts the step's own session in the middle of a thought, so the part is never settled. Run 66's
agent.summarizeon production shows it:oc.part.reasoningforprt_145c29767001qiIybEr3gnAOjA, withtime.startonly;osf.step.interrupted, and 274632osf.attempt.closed;time.endfor that part ever arrives. It is the only one of the step's six reasoning parts never settled.Nothing for the step clears the buffer either. Neither
osf.step.interrupted,osf.attempt.closed, nor stream B's ownendframe (sent once none of its steps is writing,ui/src/lib/sse.tsonly stops reading) drops the step's entry. So the indicator stays until the page is reloaded: stream B is not replayed, and the settled transcript draws no live row.The same holds for every way a step's session ends mid-part: a Stop on the step or the run, a time-out, a context-budget abort, or osfd restarting. A text part cut off the same way would leave its half-written answer on screen as live text.
Fix
osf.attempt.closed), or the step leavesrunningfor any reason, drop every live entry for that step fromdeltaStore:byStepand everybySessionentry with itsstepId. Its subagents' sessions end with it.endframe the same way, for the steps it names. That covers a client that missed the closing event.Done when
osf.attempt.closed(and, separately, anendframe), and the step has no live entry left.[data-thinking-indicator]disappears without a reload. The fixture'srun_stopped(ui/dev/fakeosfd.py, from #152) can carry the unsettled part.Related: #152 (an operator's Stop reads interrupted) and #173 (the message box under an interrupted step).
step.skipped: <label>and never says the step was put back #175Shipped in
74e261c(changestop-and-resume-read-calmly, commit684779a), live since 21:30Z on 2026-10-16.osf.attempt.closed), the console drops that step's live parts, its subagents' included, and ignores late deltas for them. The same happens when the live stream ends for the step. So a Stop, a time-out, a budget abort or an osfd restart no longer leaves a Thinking row animating.openspec.apply.soloat 22:04:05Z while text streamed. The row read interrupted within 2 s ("stopped by the operator; 4/6 tasks done"). No live text was left at 2, 10 or 30 s, without a reload.The change is archived in the next push. Closing.