Compare commits

...

11 Commits

Author SHA1 Message Date
claude 2a2f706b74 Merge pull request 'Recall fixture: filler note ids can collide with case ids and split the two backends' (#126) from task/386-recall-fixture-filler-note-ids into master 2026-08-04 18:22:52 +02:00
claude e082e06868 Merge pull request 'Bug: morning.Item has no required/optional flag, so behaviour 1 of task 280 cannot hold' (#125) from task/473-bug-morning-item-has-no-required-flag into master 2026-08-04 18:22:45 +02:00
claude 88dc4e1383 Merge pull request 'Bug: make simulate routes with an empty seed set, so a green run proves less than it looks' (#124) from task/465-bug-make-simulate-routes-with-an-empty into master 2026-08-04 18:22:37 +02:00
claude 60759a991e Merge pull request 'Bug: spoken task capture is dead — the router calls the marker an act, and capture only rides the note intent' (#123) from task/467-bug-spoken-task-capture-is-dead into master 2026-08-04 18:22:28 +02:00
claude 9537346441 Merge pull request 'Bug: a pending clarify is global, so one unanswerable question swallows the next three utterances from anybody' (#122) from task/466-bug-a-pending-clarify-is-global-so-one-u into master 2026-08-04 18:21:49 +02:00
claude c6be818f13 Merge pull request 'Bug: pattern.Detect has no minimum-interval floor, so four fast taps mint a permanent false routine' (#121) from task/468-bug-pattern-detect-has-no-minimum-interv into master 2026-08-04 18:21:38 +02:00
claude b5575a9402 Merge pull request 'Bug: CheckFeminine flags second-person masculine verbs as self-reference' (#120) from task/462-bug-checkfeminine-flags-second-person-ma into master 2026-08-04 18:21:27 +02:00
claude fcda5e3d2c Merge pull request 'safeKey drops Cyrillic, so Russian calendar events on one day collide' (#119) from task/443-safekey-drops-cyrillic-so-russian-calend into master 2026-08-04 18:21:15 +02:00
claude bdafc82e35 Merge pull request 'llama-server core-dumps on every SIGTERM, so each mavgpud yield writes a core file' (#116) from task/491-llama-server-core-dumps-on-every-sigterm into master 2026-08-04 14:09:25 +02:00
claude c69023c310 Merge PR #117 into task/491 (V-383) 2026-08-04 14:08:59 +02:00
claude 9aabb01e2a recalleval: a filler id a case reuses is refused at load (V-386)
Every case is scored over its own notes plus the whole filler set, and the
two stores disagree about a repeated id: sqlite upserts on it, the in-memory
store appends. So one collision makes a case score differently on the two
backends, and it reads as an embedder or gate difference — the one thing this
harness exists to measure. It was dodged by hand during #373 by renaming two
ids.

The check sits in Load rather than in TestLoadFixture, so it covers every
caller of the fixture and not only the one that remembers to look.
2026-08-04 03:18:42 +04:00
2 changed files with 60 additions and 0 deletions
+35
View File
@@ -90,9 +90,44 @@ func Load() (Fixture, error) {
if len(f.Cases) == 0 {
return Fixture{}, fmt.Errorf("fixture has no cases")
}
if err := checkIDs(f); err != nil {
return Fixture{}, err
}
return f, nil
}
// checkIDs refuses a fixture where a case note and a filler note share an id.
//
// Every case is scored over its own notes plus the whole filler set, and the
// two stores disagree about what a repeated id means: the sqlite store upserts
// on it, the in-memory store appends. So one collision makes a case score
// differently on the two backends, and it reads as an embedder or gate
// difference, which is the one thing this harness exists to measure (Vikunja
// #386). It was dodged once by hand during #373 by renaming two ids.
//
// Checked in Load rather than in the test, so every caller of the fixture is
// covered and not only the one that remembers to look.
func checkIDs(f Fixture) error {
filler := make(map[string]bool, len(f.Filler))
for _, n := range f.Filler {
if n.ID == "" {
return fmt.Errorf("filler note with an empty id")
}
if filler[n.ID] {
return fmt.Errorf("duplicate filler note id %q", n.ID)
}
filler[n.ID] = true
}
for _, c := range f.Cases {
for _, n := range c.Notes {
if filler[n.ID] {
return fmt.Errorf("case %s: note id %q collides with a filler note", c.ID, n.ID)
}
}
}
return nil
}
// NewStore builds an empty store for one case, plus a function to release it.
// A factory rather than a store because every case needs a clean index — notes
// from case A must not be visible to case B's query.
@@ -337,3 +337,28 @@ func marginSweep(t *testing.T, emb router.Embedder, f Fixture) string {
}
return b.String()
}
// TestFillerIDCollisionIsRefused — the guard that keeps a fixture edit from
// looking like a backend difference (Vikunja #386).
func TestFillerIDCollisionIsRefused(t *testing.T) {
f := Fixture{
SchemaVersion: SchemaVersion,
Cases: []Case{{ID: "ru-001", Notes: []StoredNote{{ID: "f1", Text: "..."}}}},
Filler: []StoredNote{{ID: "f1", Text: "..."}},
}
if err := checkIDs(f); err == nil {
t.Fatal("a case note reusing a filler id must be refused")
}
f.Filler = append(f.Filler, StoredNote{ID: "f1", Text: "..."})
if err := checkIDs(Fixture{SchemaVersion: SchemaVersion, Filler: f.Filler}); err == nil {
t.Fatal("a duplicate filler id must be refused")
}
ok := Fixture{
SchemaVersion: SchemaVersion,
Cases: []Case{{ID: "ru-001", Notes: []StoredNote{{ID: "n1", Text: "..."}}}},
Filler: []StoredNote{{ID: "f1", Text: "..."}},
}
if err := checkIDs(ok); err != nil {
t.Fatalf("a clean fixture must pass: %v", err)
}
}