Progress bar: fresh-this-run counter; fix KeyError 'success'

- Completed X/Y now carries (+N new): samples generated by THIS run,
  excluding the checkpoint-restored head start (previously 98/164 told
  you nothing about how much work this invocation actually did)
- rate/eta computed over fresh samples only (restored ones counted
  toward 141/6s = 23/s when 1 sample had been generated)
- fix KeyError 'success': advance() still read the success/failed task
  fields after they were dropped from the column set -- first advance
  on a resumed bench killed the whole benchmark
- set_overall: give the overall task the fields the shared columns
  actually read (cur/retries/elapsed/eta); the old field set was from
  a previous column layout

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
sora 2026-09-14 03:05:18 +00:00
parent 20d2d5537a
commit f5c2e4c5af

View File

@ -43,7 +43,7 @@ class RichTerminalProgress:
TextColumn("[progress.description]{task.description}"), TextColumn("[progress.description]{task.description}"),
BarColumn(complete_style="green", finished_style="bold green"), BarColumn(complete_style="green", finished_style="bold green"),
TaskProgressColumn(), TaskProgressColumn(),
TextColumn("• Completed {task.completed}/{task.total}"), TextColumn("• Completed {task.completed}/{task.total} [dim]{task.fields[new]}[/dim]"),
TextColumn("• in-flight [yellow]{task.fields[inflight]}[/yellow] ([yellow]{task.fields[cur]}[/yellow])"), TextColumn("• in-flight [yellow]{task.fields[inflight]}[/yellow] ([yellow]{task.fields[cur]}[/yellow])"),
TextColumn("• [red]retries {task.fields[retries]}[/red]"), TextColumn("• [red]retries {task.fields[retries]}[/red]"),
TextColumn("• [dim]{task.fields[rate]}/s[/dim]"), TextColumn("• [dim]{task.fields[rate]}/s[/dim]"),
@ -59,6 +59,7 @@ class RichTerminalProgress:
self.started = 0.0 self.started = 0.0
self.current_started = 0.0 self.current_started = 0.0
self.inflight = 0 self.inflight = 0
self.restored = 0 # checkpoint head start (drives the '+N new' marker)
self.heartbeat_task = None self.heartbeat_task = None
def set_overall(self, total: int, done: int, label: str = 'benches'): def set_overall(self, total: int, done: int, label: str = 'benches'):
@ -73,8 +74,8 @@ class RichTerminalProgress:
# overall task the same fields or rendering raises KeyError # overall task the same fields or rendering raises KeyError
self.overall_id = self.progress.add_task( self.overall_id = self.progress.add_task(
f'[cyan]{label}[/cyan]', total=total, completed=min(done, total), f'[cyan]{label}[/cyan]', total=total, completed=min(done, total),
inflight=0, rate='0.00', success=done, failed=0, new='', inflight=0, cur='0s', retries=0, rate='0.00',
waiting='00:00', last_result='') elapsed='0s', eta='-')
else: else:
self.progress.update(self.overall_id, completed=min(done, total)) self.progress.update(self.overall_id, completed=min(done, total))
@ -88,6 +89,7 @@ class RichTerminalProgress:
if self.disabled: if self.disabled:
return return
self.started = time.monotonic() self.started = time.monotonic()
self.restored = max(completed, 0)
if self.task_id is not None: if self.task_id is not None:
return # one live reporter at a time; reuse across benchmarks return # one live reporter at a time; reuse across benchmarks
self.progress.start() self.progress.start()
@ -95,18 +97,24 @@ class RichTerminalProgress:
f"[green]{description}", f"[green]{description}",
total=total, total=total,
completed=min(completed, total), completed=min(completed, total),
success=completed, new=self._new_txt(completed),
failed=0,
rate="0.00", rate="0.00",
inflight=0, inflight=0,
cur="0s", cur="0s",
retries=0,
elapsed="0s", elapsed="0s",
eta="-", eta="-",
waiting="00:00",
last_result="restored",
) )
self.heartbeat_task = asyncio.create_task(self._heartbeat()) self.heartbeat_task = asyncio.create_task(self._heartbeat())
def _new_txt(self, absolute_done: int) -> str:
"""'(+N new)' marker: samples completed by THIS run, i.e. absolute
progress minus the checkpoint-restored head start. Empty when the
run started fresh (nothing was restored, nothing to distinguish)."""
if not getattr(self, 'restored', 0):
return ''
return f'(+{max(absolute_done - self.restored, 0)} new)'
def reset_samples(self, total: int, description: str, completed: int = 0): def reset_samples(self, total: int, description: str, completed: int = 0):
if self.disabled: if self.disabled:
return return
@ -114,20 +122,20 @@ class RichTerminalProgress:
self.started = time.monotonic() self.started = time.monotonic()
self.inflight = 0 self.inflight = 0
self.bench_name = description self.bench_name = description
self.restored = max(completed, 0) # checkpoint head start this bench
desc = f'[green]{self.bench_tag}{description} · generating[/green]' desc = f'[green]{self.bench_tag}{description} · generating[/green]'
if self.task_id is None: if self.task_id is None:
self.progress.start() self.progress.start()
self.task_id = self.progress.add_task( self.task_id = self.progress.add_task(
desc, total=total, completed=min(completed, total), desc, total=total, completed=min(completed, total),
success=completed, failed=0, rate='0.00', inflight=0, new=self._new_txt(completed), rate='0.00', inflight=0,
cur='0s', elapsed='0s', eta='-', retries=0, cur='0s', elapsed='0s', eta='-', retries=0)
waiting='00:00', last_result='restored')
else: else:
self.progress.update(self.task_id, description=desc, self.progress.update(self.task_id, description=desc,
total=total, completed=min(completed, total), total=total, completed=min(completed, total),
success=completed, failed=0, rate='0.00', new=self._new_txt(completed), rate='0.00',
inflight=0, cur='0s', elapsed='0s', eta='-', retries=0, inflight=0, cur='0s', elapsed='0s', eta='-',
last_result='redone') retries=0)
# ALWAYS recreate the heartbeat: the previous one may have died during # ALWAYS recreate the heartbeat: the previous one may have died during
# pause/resume cycles between benchmarks (stale reference -> silent # pause/resume cycles between benchmarks (stale reference -> silent
# death -> frozen clock while the spinner still animates) # death -> frozen clock while the spinner still animates)
@ -161,8 +169,7 @@ class RichTerminalProgress:
return return
self.inflight += 1 self.inflight += 1
self.current_started = time.monotonic() self.current_started = time.monotonic()
self.progress.update(self.task_id, inflight=self.inflight, cur='0s', self.progress.update(self.task_id, inflight=self.inflight, cur='0s')
waiting="00:00", last_result=f"waiting {label}")
def set_retries(self, n: int): def set_retries(self, n: int):
"""Show the retry count on the bar (from the adapter's attempt).""" """Show the retry count on the bar (from the adapter's attempt)."""
@ -185,22 +192,20 @@ class RichTerminalProgress:
return return
task = self.progress.tasks[self.task_id] task = self.progress.tasks[self.task_id]
completed = task.completed + 1 completed = task.completed + 1
ok = task.fields["success"] + (1 if success else 0)
failed = task.fields["failed"] + (0 if success else 1)
self.inflight = max(0, self.inflight - 1) self.inflight = max(0, self.inflight - 1)
elapsed = max(time.monotonic() - self.started, 1e-6) elapsed = max(time.monotonic() - self.started, 1e-6)
# rate/eta over THIS RUN's fresh samples only: counting the restored
# head start would print 141/6s = 23/s when 1 sample was generated
fresh = max(completed - getattr(self, 'restored', 0), 0)
self.progress.update( self.progress.update(
self.task_id, self.task_id,
advance=1, advance=1,
success=ok, new=self._new_txt(completed),
failed=failed, rate=f"{fresh / elapsed:.2f}",
rate=f"{completed / elapsed:.2f}",
inflight=self.inflight, cur='0s', inflight=self.inflight, cur='0s',
elapsed=_fmt(elapsed), elapsed=_fmt(elapsed),
eta=_fmt((task.total - completed) * elapsed / completed) eta=_fmt((task.total - completed) * elapsed / fresh)
if completed and task.total and task.total > completed else '-', if fresh and task.total and task.total > completed else '-',
waiting="00:00",
last_result="success" if success else "failed",
) )
async def _heartbeat(self): async def _heartbeat(self):