diff --git a/docs/WEB-UI.md b/docs/WEB-UI.md index dc324fc..6f75014 100644 --- a/docs/WEB-UI.md +++ b/docs/WEB-UI.md @@ -386,18 +386,16 @@ run. Every pill in the column — outcome pills and the VM-only `orphan`/ sized to fit `cancelled`, the longest word) with left-aligned content, so the column reads as a clean list instead of ragged pill widths. -Rows are ordered **newest first by run number, then attempt** — the `#N` the -Run column actually shows, not `started` timestamp and not `run_id` either. -Both were tried and both break once more than one repo/workflow is in the -mix (the admin endpoint pulls from every repo on the instance): sorting by -time lets a manually re-run old workflow (its `started_at` bumped to now, -its number unchanged) jump above a genuinely newer run; sorting by `run_id` -looks right for a single workflow but `run_id` is an *instance-wide* -sequence shared by every repo/workflow, not a per-workflow counter, so a -rarely-triggered workflow's #53 can land a `run_id` between two ids from a -busier workflow's #141/#142 — putting #53's row between them even though 53 -is nowhere near 141. `run.number` is the only one of the three that means -what the column header says. +Rows are ordered **newest first by actual start time, globally** — +`run.started` (a run still queued reads as "now", since it was only just +created), with `run_id` then `attempt` as tiebreakers for runs sharing the +exact same timestamp. `run.number` is deliberately *not* the sort key: it is +a per-repo/workflow counter, and the admin endpoint mixes every repo/workflow +on the instance into one feed, so a rarely-triggered workflow's #53 that just +fired legitimately outranks a #142 from a busier workflow that ran hours +earlier — sorting by `number` would bury it. A manual re-run bumping +`started_at` and jumping its row back to the top is not a bug either: it +really is the most recent activity on that run. The row-count dropdown at the right end of the card's header bar picks how many to list — 10 / 25 / 50 / 100, default from `[web].executions_limit` (10). The choice rides on the card's own polling URL diff --git a/src/ci_orchestrator/operations/executions.py b/src/ci_orchestrator/operations/executions.py index 3fdf7b9..7a76d3b 100644 --- a/src/ci_orchestrator/operations/executions.py +++ b/src/ci_orchestrator/operations/executions.py @@ -350,27 +350,21 @@ def _cached_runs( return runs, source, error, auth_failed, refused -def _recency_key(run: Execution) -> tuple[int, int, int]: +def _recency_key(run: Execution, now: datetime) -> tuple[datetime, int, int]: """Sort key for "newest first" (used with ``sorted(..., reverse=True)``). - Ordered by ``number`` -- the ``#N`` the Run column actually shows -- then - ``attempt``, then ``run_id`` only to keep ties stable. ``run_id`` is - Gitea's *instance-wide* id (shared across every repo/workflow the admin - endpoint pulls from), not a per-workflow counter, so it does not track - ``number`` at all once more than one workflow is in the mix: a run #53 - from a rarely-triggered workflow can easily land a run id between two - #141/#142 runs from a busier one, putting #53's row between them even - though the column reads 142, 141, ..., 53. ``number`` is what "newest - first" has to mean here. - - Two things this key deliberately does NOT sort by, both tried before: - ``started`` timestamp lets a manually re-run old workflow's ``started_at`` - (bumped to now) jump it above a genuinely newer run even though its - number/id never changed; ``run_id`` alone is the instance-wide id - described above. ``attempt`` still breaks a same-number re-run correctly - (attempt 2 outranks attempt 1) without either flaw. + Global recency: the admin endpoint mixes every repo/workflow on the + instance, and each one keeps its own ``number`` counter, so there is no + way to read "most recent across the whole instance" off a per-repo + number -- a #53 from a rarely-triggered workflow that just ran outranks a + #142 from a busier one that ran hours ago. ``started`` is what actually + answers "when did this happen"; a run still queued (no ``started`` yet) + reads as ``now`` since it was only just created. A manual re-run bumping + ``started_at`` and jumping the row back to the top is not a bug here -- + it really is the most recent activity on that run. ``run_id``/``attempt`` + only break a tie between runs sharing the exact same timestamp. """ - return (run.number, run.attempt, run.run_id) + return (run.started or now, run.run_id, run.attempt) def _attach_vms( @@ -462,7 +456,7 @@ def list_executions( runs, unmatched = _attach_vms( sorted( (_to_execution(item, moment) for item in raw_runs), - key=_recency_key, + key=lambda run: _recency_key(run, moment), reverse=True, ), vms, diff --git a/tests/python/test_operations_executions.py b/tests/python/test_operations_executions.py index 1a460d6..5005801 100644 --- a/tests/python/test_operations_executions.py +++ b/tests/python/test_operations_executions.py @@ -432,50 +432,43 @@ def test_queued_run_sorts_above_started_runs( assert [r.status for r in view.runs] == ["queued", "success"] -def test_a_rerun_does_not_jump_above_a_newer_run( +def test_a_rerun_sorts_above_a_run_that_started_earlier( tmp_path: Path, monkeypatch: pytest.MonkeyPatch ) -> None: - """Re-running an old workflow bumps its ``started_at`` to now, but its - run id/number never change -- sorting by wall-clock time would put that - stale run above a genuinely newer one it should still trail. The Run - column must read strictly by run, descending, not by whichever attempt - was most recently kicked off.""" + """Re-running an old workflow really is fresh activity -- it belongs at + the top of a "most recent globally" feed, same as any other run that just + started.""" payload = [ _run(run_id=12, number=12, attempt=1, started="2026-07-25T10:00:00Z"), _run(run_id=13, number=13, attempt=1, started="2026-07-25T10:05:00Z"), - # #12 gets manually re-run after #13 already started -- its - # started_at is now the latest timestamp of the three. + # #12 gets manually re-run after #13 already started. _run(run_id=12, number=12, attempt=2, started="2026-07-25T10:10:00Z"), ] _install_urlopen(monkeypatch, _admin_ok(payload)) view = list_executions(_make_config(tmp_path), [], token="tok", now=_NOW) - assert [(r.number, r.attempt) for r in view.runs] == [(13, 1), (12, 2), (12, 1)] + assert [(r.number, r.attempt) for r in view.runs] == [(12, 2), (13, 1), (12, 1)] -def test_a_lower_numbered_run_from_a_busier_workflow_does_not_land_in_between( +def test_a_more_recent_run_from_a_quiet_workflow_sorts_above_an_older_higher_numbered_run( tmp_path: Path, monkeypatch: pytest.MonkeyPatch ) -> None: - """``run_id`` is instance-wide (every repo/workflow the admin endpoint - pulls from shares one sequence), not a per-workflow counter -- a rarely - triggered workflow's #53 can easily get a run id that falls between two - ids from a busier workflow's #141/#142, even though 53 is nowhere near - 141 or 142. The Run column has to read by the number it shows, not by - that shared id.""" + """``number`` is a per-repo/workflow counter -- it cannot answer "most + recent across the whole instance" at all once more than one repo is in + the mix. A rarely-triggered workflow's #53 that just ran outranks a + #141/#142 from a busier workflow that ran hours earlier.""" payload = [ - _run(run_id=9001, number=142, started="2026-07-25T12:00:00Z"), - # A different, rarely-run workflow's id landed between the two above - # purely because of when it happened to fire -- not because #53 is - # newer than #141. - _run(run_id=9000, number=53, path=".gitea/workflows/rare.yml", started="2026-07-25T09:00:00Z"), - _run(run_id=8000, number=141, started="2026-07-25T11:00:00Z"), + _run(run_id=8000, number=141, started="2026-07-25T09:00:00Z"), + _run(run_id=9001, number=142, started="2026-07-25T10:00:00Z"), + # A different, rarely-run workflow -- but it just fired, after both. + _run(run_id=1, number=53, path=".gitea/workflows/rare.yml", started="2026-07-25T11:00:00Z"), ] _install_urlopen(monkeypatch, _admin_ok(payload)) view = list_executions(_make_config(tmp_path), [], token="tok", now=_NOW) - assert [r.number for r in view.runs] == [142, 141, 53] + assert [r.number for r in view.runs] == [53, 142, 141] def test_same_number_and_attempt_falls_back_to_run_id(