Files
executus/schedule/runner_test.go
T
steve eea84e6e2c
executus CI / test (pull_request) Successful in 1m39s
fix: address verified gadfly P4c findings (3-cloud fleet)
critic (all 3 models — HIGH):
- ExtendOnce was a single global one-shot shared across every run a System
  monitors, so only the FIRST run to stall got its extension and all others
  were killed by the backstop. Key the fired-state per run (RunInfo.RunID).
- Kill is now sticky: a `killed` flag short-circuits later ticks so a wavering
  Escalator returning ExtendBy after a Kill can't un-collapse the deadline; a
  Kill paired with Nudge/ExtendBy ignores the latter.
- watch() recovers panics from a misbehaving Escalator (logs; the run falls
  back to its existing deadline) instead of silently killing the watch goroutine.

checkpoint (deepseek — HIGH): handle.Save advanced the throttle clock BEFORE
the store write, so a failed save was silently throttled away (caller believes
it persisted). Advance lastSave only after a successful persist.

schedule (all 3): compute Next BEFORE Run — a permanently-unparseable cron now
skips the job entirely instead of re-running it every tick forever; nil required
callbacks return a validate() error instead of a first-tick nil panic; Loop
recovers tick panics; the Mark-failure => possible-re-run trade-off is documented
(Run must be idempotent). + tests for each.

Triaged-but-kept: critic backstopMul<=1 floor (it's a total-runtime multiple, so
a floor >1 is intentional, not the reported footgun); checkpoint Load (nil,nil)
on miss (documented convention).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 23:32:27 -04:00

112 lines
3.7 KiB
Go

package schedule
import (
"context"
"errors"
"testing"
"time"
)
func TestTickRunsDueAndStampsNext(t *testing.T) {
ctx := context.Background()
now := time.Date(2026, 1, 1, 12, 0, 0, 0, time.UTC)
var ran []string
marked := map[string]time.Time{}
r := &Runner{
Now: func() time.Time { return now },
Due: func(_ context.Context, _ time.Time) ([]Due, error) {
return []Due{{ID: "a", Cron: "hourly"}, {ID: "b", Cron: "bad"}}, nil
},
Run: func(_ context.Context, id string) error { ran = append(ran, id); return nil },
Mark: func(_ context.Context, id string, _, next time.Time) error { marked[id] = next; return nil },
Next: func(cron string, after time.Time) (time.Time, error) {
if cron == "bad" {
return time.Time{}, errors.New("unparseable")
}
return after.Add(time.Hour), nil
},
}
if err := r.Tick(ctx); err != nil {
t.Fatal(err)
}
// Next is checked first, so the bad-cron job is skipped BEFORE Run — only
// the parseable job runs and gets stamped (no hot-loop of a bad-cron Run).
if len(ran) != 1 || ran[0] != "a" {
t.Errorf("ran = %v, want only [a] (bad-cron b skipped before Run)", ran)
}
if marked["a"] != now.Add(time.Hour) {
t.Errorf("a next = %v, want +1h", marked["a"])
}
if _, ok := marked["b"]; ok {
t.Errorf("b should not be stamped (bad cron), got %v", marked["b"])
}
}
func TestTickRunFailureDoesNotStampOrStall(t *testing.T) {
ctx := context.Background()
var ran []string
marked := map[string]bool{}
r := &Runner{
Due: func(_ context.Context, _ time.Time) ([]Due, error) {
return []Due{{ID: "x", Cron: "h"}, {ID: "y", Cron: "h"}}, nil
},
Run: func(_ context.Context, id string) error {
ran = append(ran, id)
if id == "x" {
return errors.New("boom")
}
return nil
},
Mark: func(_ context.Context, id string, _, _ time.Time) error { marked[id] = true; return nil },
Next: func(string, time.Time) (time.Time, error) { return time.Now(), nil },
}
if err := r.Tick(ctx); err != nil {
t.Fatal(err)
}
if len(ran) != 2 { // y still runs despite x failing
t.Errorf("ran = %v, want both attempted", ran)
}
if marked["x"] { // failed job NOT stamped -> stays due, retries
t.Error("failed job x should not be stamped")
}
if !marked["y"] {
t.Error("y should be stamped")
}
}
func TestTickDueErrorIsFatalToPass(t *testing.T) {
r := &Runner{
Due: func(context.Context, time.Time) ([]Due, error) { return nil, errors.New("store down") },
Run: func(context.Context, string) error { return nil },
Mark: func(context.Context, string, time.Time, time.Time) error { return nil },
Next: func(string, time.Time) (time.Time, error) { return time.Now(), nil },
}
if err := r.Tick(context.Background()); err == nil {
t.Error("Tick should surface the Due lister error")
}
}
func TestUnparseableCronSkipsRunEntirely(t *testing.T) {
var ran []string
r := &Runner{
Due: func(context.Context, time.Time) ([]Due, error) { return []Due{{ID: "z", Cron: "bad"}}, nil },
Run: func(_ context.Context, id string) error { ran = append(ran, id); return nil },
Mark: func(context.Context, string, time.Time, time.Time) error { return nil },
Next: func(string, time.Time) (time.Time, error) { return time.Time{}, errors.New("bad cron") },
}
if err := r.Tick(context.Background()); err != nil {
t.Fatal(err)
}
if len(ran) != 0 {
t.Errorf("a job with an unparseable cron must NOT be run (avoids hot-loop), ran=%v", ran)
}
}
func TestValidateRejectsNilCallbacks(t *testing.T) {
r := &Runner{Due: func(context.Context, time.Time) ([]Due, error) { return nil, nil }} // missing Run/Mark/Next
if err := r.Tick(context.Background()); err == nil {
t.Error("Tick should return a validation error for a partially-wired Runner, not panic")
}
}