Andy Dixon
072422d916
- snapshots: checksummed JSON archive of every mind-scoped state table plus identity/personality/config and the event position; stored, downloadable - fork: restore into a new mind with all ids remapped; event references are kept so history before the fork is shared by reference - export/import: same archive; import is hostile-input validated (size, allow-listed tables, row caps, column names, checksum, forced mind_id) - compare: deterministic counts, belief diffs by proposition, personality and config diffs, event mix - replay: Runtime.Step for synchronous drivers; sandbox fork driven one stimulus at a time under a forbidden capability context; recorded model responses via a replaying router; steps labelled exact / approximate / diverged with recorded-vs-replayed digests - experiments: definition (overrides, stimuli, expectations, seed, duration), background run in a disabled subject mind, stored and exportable results - migration 0015, API, UI (Snapshots and Replay tabs, Experiments section, compare page), noemactl snapshots/compare/replay/experiments, docs
65 lines
2.4 KiB
Go
65 lines
2.4 KiB
Go
package replay
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"testing"
|
|
|
|
evstore "github.com/andydixon/noema/internal/events"
|
|
"github.com/andydixon/noema/internal/minds"
|
|
"github.com/andydixon/noema/internal/replay/replaytest"
|
|
"github.com/andydixon/noema/pkg/events"
|
|
)
|
|
|
|
func TestReplayIsExactWithoutModel(t *testing.T) {
|
|
h := replaytest.NewHarness(t)
|
|
ctx := context.Background()
|
|
src, err := h.Minds.Create(ctx, minds.CreateParams{Slug: "src", DisplayName: "Source"})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
// Live run on the source, driven synchronously: one stimulus, settle.
|
|
live, err := NewDriver(ctx, h.Brain, src, "test")
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
sn, err := h.Snaps.Create(ctx, src, "t0", "", "test")
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if _, err := live.Observe(ctx, "operator", "Andy said the payments service failed after the migration", 0.8, nil); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
produced, cycles, err := live.Settle(ctx)
|
|
if err != nil || cycles == 0 || len(Digest(produced)) == 0 {
|
|
t.Fatalf("live run produced nothing: %v cycles=%d", err, cycles)
|
|
}
|
|
last, _ := h.Events.Query(ctx, evstore.Filter{MindID: src.ID, Limit: 1})
|
|
svc := &Service{DB: h.Pool, Events: h.Events, Minds: h.Minds, Snapshots: h.Snaps, Brain: h.Brain, Log: slog.New(slog.DiscardHandler)}
|
|
r, err := svc.Run(ctx, src, sn.ID, sn.EventSeq, last[0].Seq, "test")
|
|
if err != nil {
|
|
t.Fatalf("replay: %v %+v", err, r)
|
|
}
|
|
if r.Status != "done" || r.Summary.Steps != 1 || r.Summary.Exact != 1 || r.Summary.LLMLive != 0 {
|
|
t.Fatalf("expected one exact step: %+v steps=%s", r.Summary, string(r.Steps))
|
|
}
|
|
steps := StepsOf(r)
|
|
if len(steps) != 1 || !Same(steps[0].Original, steps[0].Replayed) || len(steps[0].Replayed) == 0 {
|
|
t.Fatalf("step mismatch: %+v", steps)
|
|
}
|
|
sandbox, err := h.Minds.Get(ctx, *r.ReplayMindID)
|
|
if err != nil || sandbox.Status != minds.StatusDisabled || sandbox.ForkedFromSnapshot == nil {
|
|
t.Fatalf("sandbox mind wrong: %+v %v", sandbox, err)
|
|
}
|
|
// The source's history is untouched by the replay.
|
|
after, _ := h.Events.Query(ctx, evstore.Filter{MindID: src.ID, Limit: 1})
|
|
if after[0].Seq != last[0].Seq {
|
|
t.Fatal("replay wrote into the source mind")
|
|
}
|
|
// Digest normalisation ignores ids and numbers.
|
|
if Normalise("selected 3 thoughts for 01a0a148-9034-7685-9794-cf5ec0c25fb7") != "selected <n> thoughts for <id>" {
|
|
t.Fatal(Normalise("selected 3 thoughts for 01a0a148-9034-7685-9794-cf5ec0c25fb7"))
|
|
}
|
|
_ = events.Observation
|
|
}
|