Keys are stored hashed, so a migration that drops them cannot recreate them: every person and every script needs a new one issued, and the old ones cannot even be looked up to say which they were. `llmgw keys move-store` copies instead. Found by running it against the real cluster, twice, after the gateway had already been stopped. The first order came from the order the migrations create tables in, and users is created in a later migration than api_keys even though api_keys references it — so the copy died three tables in. The order is now checked by a test that derives the foreign keys from the migrations rather than restating them, so a new reference fails there instead of during somebody's migration. Checked by putting the wrong order back and watching it fail. Then key_claims. Its sealed column is emptied the moment a claim is used, so every claimed row holds an empty blob in a NOT NULL column. An empty blob scans as a typed nil slice and a genuine NULL as an untyped one — a distinction this side can see and pgx cannot, since it encodes any nil slice as NULL. Restored before the insert, which is the difference between a copy that completes and one that stops four tables in. One transaction per table rather than one for the whole copy: a single transaction holding every row of a large usage table is how a migration runs out of memory on the machine least able to spare it. A failure therefore leaves a partial copy, which is why the destination must have been empty — starting again is dropping and recreating it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
254 lines
7.6 KiB
Go
254 lines
7.6 KiB
Go
package store
|
|
|
|
import (
|
|
"context"
|
|
"os"
|
|
"path/filepath"
|
|
"regexp"
|
|
"slices"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func TestEveryTableIsInTheCopyOrder(t *testing.T) {
|
|
// A table added by a migration and not added here is copied by nothing,
|
|
// and the destination comes up quietly missing it — discovered when
|
|
// somebody looks for a setting that was there before the move. Read out of
|
|
// the migrations rather than listed twice, so the two cannot disagree.
|
|
var declared []string
|
|
entries, err := migrationFS.ReadDir("migrations/sqlite")
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
for _, e := range entries {
|
|
body, err := migrationFS.ReadFile("migrations/sqlite/" + e.Name())
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
for _, line := range strings.Split(string(body), "\n") {
|
|
line = strings.TrimSpace(line)
|
|
rest, ok := strings.CutPrefix(line, "CREATE TABLE ")
|
|
if !ok {
|
|
continue
|
|
}
|
|
name, _, _ := strings.Cut(rest, " ")
|
|
name = strings.TrimSuffix(strings.TrimSpace(name), "(")
|
|
declared = append(declared, name)
|
|
}
|
|
}
|
|
if len(declared) == 0 {
|
|
t.Fatal("found no tables in the migrations, so this test proves nothing")
|
|
}
|
|
for _, name := range declared {
|
|
if !slices.Contains(copyOrder, name) {
|
|
t.Errorf("%q is created by a migration but nothing copies it", name)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestCopyRefusesADestinationThatAlreadyHasRows(t *testing.T) {
|
|
// Merging two stores means deciding what happens when both hold a project
|
|
// with the same id and different contents, and every answer is a guess
|
|
// about which one somebody meant.
|
|
ctx := context.Background()
|
|
src, dst := openDB(t), openDB(t)
|
|
tree(t, src)
|
|
tree(t, dst)
|
|
|
|
_, err := src.CopyTo(ctx, dst)
|
|
if err == nil || !strings.Contains(err.Error(), "empty store") {
|
|
t.Errorf("copying into a populated store gave %v", err)
|
|
}
|
|
}
|
|
|
|
func TestACopiedStoreStillAuthenticatesTheSameKey(t *testing.T) {
|
|
// The reason this exists. Keys are stored hashed, so a migration that
|
|
// loses them cannot recreate them: every person and every script would
|
|
// need a new one issued.
|
|
ctx := context.Background()
|
|
src := openDB(t)
|
|
proj := tree(t, src)
|
|
secret, k := mustKey(t, src, "k1", proj)
|
|
|
|
if err := src.WriteUsage(ctx, []Usage{{
|
|
At: time.Now(), KeyID: k.ID, ProjectID: proj, Model: "m", ServedModel: "m",
|
|
PromptTokens: 3, CompletionTokens: 4, CostMicros: 99, Status: 200,
|
|
}}); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
dst, err := Open(ctx, filepath.Join(t.TempDir(), "copy.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer dst.Close()
|
|
|
|
res, err := src.CopyTo(ctx, dst)
|
|
if err != nil {
|
|
t.Fatalf("copying: %v", err)
|
|
}
|
|
if len(res) != len(copyOrder) {
|
|
t.Errorf("copied %d tables of %d", len(res), len(copyOrder))
|
|
}
|
|
|
|
// The same secret the caller already holds still resolves, in the copy.
|
|
got, err := dst.KeyByHash(ctx, HashKey(secret))
|
|
if err != nil {
|
|
t.Fatalf("the copied store does not know the key: %v", err)
|
|
}
|
|
if got.ID != k.ID || got.ProjectID != proj {
|
|
t.Errorf("key came back as %+v", got)
|
|
}
|
|
|
|
// And the spend it had, so a budget is not quietly reset by moving.
|
|
spend, err := dst.SpendSince(ctx, time.Now().Add(-time.Hour))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if spend[k.ID] != 99 {
|
|
t.Errorf("spend after the copy = %d, want 99", spend[k.ID])
|
|
}
|
|
}
|
|
|
|
func TestCopyCarriesConversationsAndNotes(t *testing.T) {
|
|
ctx := context.Background()
|
|
src := openDB(t)
|
|
proj := tree(t, src)
|
|
if err := src.SetThreadRetention(ctx, proj, 24); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if err := src.AppendThread(ctx, proj, "th1", []Message{
|
|
{Role: "user", Content: "remembered"},
|
|
}); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
dst, err := Open(ctx, filepath.Join(t.TempDir(), "copy.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer dst.Close()
|
|
if _, err := src.CopyTo(ctx, dst); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
msgs, err := dst.Thread(ctx, proj, "th1")
|
|
if err != nil {
|
|
t.Fatalf("the conversation did not survive: %v", err)
|
|
}
|
|
if len(msgs) != 1 || msgs[0].Content != "remembered" {
|
|
t.Errorf("thread came back as %+v", msgs)
|
|
}
|
|
// The retention setting is a column on projects, so it rides along — a
|
|
// destination that kept the conversations and forgot the promise about
|
|
// how long would be worse than one that kept neither.
|
|
if d, err := dst.ThreadRetention(ctx, proj); err != nil || d == 0 {
|
|
t.Errorf("retention after the copy = %v (err %v)", d, err)
|
|
}
|
|
}
|
|
|
|
func TestCopyingAnEmptyStoreIsFine(t *testing.T) {
|
|
ctx := context.Background()
|
|
src := openDB(t)
|
|
dst, err := Open(ctx, filepath.Join(t.TempDir(), "copy.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer dst.Close()
|
|
if _, err := src.CopyTo(ctx, dst); err != nil {
|
|
t.Errorf("copying an empty store failed: %v", err)
|
|
}
|
|
_ = os.Remove("")
|
|
}
|
|
|
|
func TestTheCopyOrderSatisfiesTheForeignKeys(t *testing.T) {
|
|
// Completeness is not enough: a table copied before the one it references
|
|
// fails on a constraint partway through, leaving some tables copied and
|
|
// some not. The first version of copyOrder followed the order the
|
|
// migrations create tables in, and users is created after api_keys even
|
|
// though api_keys points at it — so the copy died three tables in, on a
|
|
// real database, after the gateway had already been stopped.
|
|
//
|
|
// Derived from the migrations rather than restated, so a new reference
|
|
// fails here rather than during somebody's migration.
|
|
deps := map[string]map[string]bool{}
|
|
note := func(table, ref string) {
|
|
if table == ref {
|
|
return
|
|
}
|
|
if deps[table] == nil {
|
|
deps[table] = map[string]bool{}
|
|
}
|
|
deps[table][ref] = true
|
|
}
|
|
|
|
entries, err := migrationFS.ReadDir("migrations/sqlite")
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
body := ""
|
|
for _, e := range entries {
|
|
b, err := migrationFS.ReadFile("migrations/sqlite/" + e.Name())
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
body += string(b)
|
|
}
|
|
|
|
// Table bodies, so a REFERENCES is attributed to the table holding it.
|
|
for _, m := range regexpCreateTable.FindAllStringSubmatch(body, -1) {
|
|
for _, r := range regexpReferences.FindAllStringSubmatch(m[2], -1) {
|
|
note(m[1], r[1])
|
|
}
|
|
}
|
|
// And columns added later, which is exactly how api_keys got its user_id.
|
|
for _, m := range regexpAlterRef.FindAllStringSubmatch(body, -1) {
|
|
note(m[1], m[2])
|
|
}
|
|
if len(deps) == 0 {
|
|
t.Fatal("found no foreign keys, so this test proves nothing")
|
|
}
|
|
|
|
position := map[string]int{}
|
|
for i, t := range copyOrder {
|
|
position[t] = i
|
|
}
|
|
for table, refs := range deps {
|
|
for ref := range refs {
|
|
if position[ref] > position[table] {
|
|
t.Errorf("%s is copied before %s, which it references", table, ref)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
var (
|
|
regexpCreateTable = regexp.MustCompile(`(?s)CREATE TABLE (\w+)\s*\((.*?)\n\);`)
|
|
regexpReferences = regexp.MustCompile(`REFERENCES\s+(\w+)`)
|
|
regexpAlterRef = regexp.MustCompile(`ALTER TABLE (\w+) ADD COLUMN[^;]*REFERENCES\s+(\w+)`)
|
|
)
|
|
|
|
func TestAnEmptyBlobDoesNotBecomeNullInTheCopy(t *testing.T) {
|
|
// key_claims.sealed is emptied the moment a claim is used, so a claimed
|
|
// row holds an empty blob in a NOT NULL column. An empty blob scans as a
|
|
// typed nil slice and a real NULL as an untyped one; pgx cannot tell them
|
|
// apart, so the distinction is restored before the insert.
|
|
if got := keepEmptyBytes([]byte(nil)); got == nil {
|
|
t.Error("an empty byte column would be inserted as NULL")
|
|
} else if b, ok := got.([]byte); !ok || len(b) != 0 {
|
|
t.Errorf("empty bytes came out as %#v", got)
|
|
}
|
|
// A genuine NULL arrives as an untyped nil and must stay one.
|
|
if got := keepEmptyBytes(nil); got != nil {
|
|
t.Errorf("a NULL became %#v", got)
|
|
}
|
|
// Everything else passes through.
|
|
if got := keepEmptyBytes(int64(7)); got != int64(7) {
|
|
t.Errorf("a number was rewritten to %#v", got)
|
|
}
|
|
if got := keepEmptyBytes([]byte("x")); string(got.([]byte)) != "x" {
|
|
t.Errorf("a non-empty blob was rewritten to %#v", got)
|
|
}
|
|
}
|