Merge the wipe (#190)

V-494 part 1. Store.Wipe drops every table and rebuilds from the migrations; mavend -wipe is a dry run and -confirm-wipe deletes. QA isolation and onboarding are the remaining two thirds. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01SoL7EBdYC5Mhz3DJd49GJy
2026-08-05 20:51:55 +04:00
parent 03d48ab789 82d9a3324e
commit 1bacbb7952
4 changed files with 275 additions and 0 deletions
@@ -128,6 +128,8 @@ func run(args []string) error {
 	wrappedKeyPath := flag.String("wrapped-key-file", "", "path to wrapped encryption key blob (enables cold-start unlock)")
 	reembed := flag.Bool("reembed", false, "re-embed every stored note and fact with the configured embedder, then serve normally (run once after an embedder swap; the daemon does not answer until it finishes)")
 	allowSeed := flag.Bool("allow-seed", false, "enable the backdated seed_event write path (QA only: it lets a caller place a fact in the past and mint a routine the tick loop will then act on; off means the method has nothing to write with)")
+	wipe := flag.Bool("wipe", false, "print every table and its row count, then exit without serving; add -confirm-wipe to delete all of it")
+	confirmWipe := flag.Bool("confirm-wipe", false, "with -wipe, actually remove every piece of personal data (facts, notes, vectors, events, tasks, sessions, traces, voiceprints). config, models, passkeys and the encryption key are files and survive")
 	flag.CommandLine.Parse(args)
 	reembedOnStart = *reembed
 	allowSeedOnStart = *allowSeed
@@ -210,6 +212,14 @@ func run(args []string) error {
 		}()
 	}

+	// ----- wipe: never serves, exits when it is done (Vikunja #494) -----
+	if *wipe {
+		if locked {
+			return fmt.Errorf("wipe: the store is locked and there is no key to open it with")
+		}
+		return runWipe(ctx, st, os.Stdout, *confirmWipe)
+	}
+
 	// ----- daemon components (only wired when unlocked) -----
 	// Pre-declare so the unlock path can wire them later.
 	var (
@@ -0,0 +1,45 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"io"
+
+	"github.com/kami/maven/internal/store"
+)
+
+// runWipe implements the -wipe flag: it prints what the database holds, and
+// removes it only when the operator also passed -confirm-wipe (Vikunja #494).
+//
+// Two flags rather than one, because the destructive reading of a single flag
+// is the reading a mistyped command gets. Without the confirmation this is a
+// dry run that costs nothing and answers the question a QA session actually
+// has — what is on this box right now.
+//
+// It runs before any daemon component is wired, so nothing is writing while
+// the tables go. The daemon exits afterwards rather than serving a store it
+// just emptied, because every component that read the old rows at boot would
+// still be holding them.
+func runWipe(ctx context.Context, st *store.Store, out io.Writer, confirmed bool) error {
+	counts, err := st.WipeCounts(ctx)
+	if err != nil {
+		return fmt.Errorf("wipe: read counts: %w", err)
+	}
+	total := 0
+	for _, c := range counts {
+		total += c.Rows
+		fmt.Fprintf(out, "  %-24s %d\n", c.Table, c.Rows)
+	}
+	fmt.Fprintf(out, "  %-24s %d rows in %d tables\n", "TOTAL", total, len(counts))
+
+	if !confirmed {
+		fmt.Fprintln(out, "\nnothing was deleted. pass -confirm-wipe to delete all of it.")
+		fmt.Fprintln(out, "config, models, passkeys and the encryption key are files and are never touched.")
+		return nil
+	}
+	if err := st.Wipe(ctx); err != nil {
+		return err
+	}
+	fmt.Fprintf(out, "\nwiped. %d rows gone, the schema is intact, mavend knows nobody.\n", total)
+	return nil
+}
@@ -0,0 +1,121 @@
+package store
+
+import (
+	"context"
+	"database/sql"
+	"fmt"
+	"sort"
+	"strings"
+)
+
+// WipeCount is one table and the number of rows a wipe would remove from it.
+type WipeCount struct {
+	Table string
+	Rows  int
+}
+
+// WipeCounts reports every table in the database and its row count, so a caller
+// can show what a wipe is about to destroy before it destroys it. Tables with
+// no rows are included: a QA reader needs to see that the table was considered,
+// not guess whether it was missed.
+func (s *Store) WipeCounts(ctx context.Context) ([]WipeCount, error) {
+	names, err := userTables(ctx, s.db)
+	if err != nil {
+		return nil, err
+	}
+	out := make([]WipeCount, 0, len(names))
+	for _, name := range names {
+		var n int
+		// name comes from sqlite_master, not from a caller, and is quoted.
+		q := fmt.Sprintf(`SELECT count(*) FROM %s`, quoteIdent(name))
+		if err := s.db.QueryRowContext(ctx, q).Scan(&n); err != nil {
+			return nil, fmt.Errorf("count %s: %w", name, err)
+		}
+		out = append(out, WipeCount{Table: name, Rows: n})
+	}
+	return out, nil
+}
+
+// Wipe removes every piece of personal data and leaves the install standing.
+//
+// It drops every object in the database and rebuilds the schema from
+// schema.sql plus the migration list, rather than deleting from a hand-written
+// list of tables. That is the whole point: a list has to be edited every time a
+// table is added, and the one time it is not, a wipe leaves personal data
+// behind while reporting success. Dropping what the database says exists cannot
+// miss a table (Vikunja #494).
+//
+// Nothing outside the database is touched. Config, models, the WebAuthn
+// credentials in passkeys.json and the encryption key all live in files, so
+// this leaves a working install with no memory of anyone.
+//
+// The caller is responsible for the daemon being the only thing holding the
+// store, and for asking whoever ran it whether they meant it.
+func (s *Store) Wipe(ctx context.Context) error {
+	names, err := userTables(ctx, s.db)
+	if err != nil {
+		return err
+	}
+	// Foreign keys are on per connection. Dropping tables in an arbitrary order
+	// trips them, and the drop order does not matter once everything goes.
+	if _, err := s.db.ExecContext(ctx, `PRAGMA foreign_keys = OFF`); err != nil {
+		return fmt.Errorf("wipe: disable foreign keys: %w", err)
+	}
+	defer func() {
+		if _, err := s.db.ExecContext(ctx, `PRAGMA foreign_keys = ON`); err != nil {
+			// The handle is about to be closed by the caller either way.
+			_ = err
+		}
+	}()
+
+	var drops strings.Builder
+	for _, name := range names {
+		fmt.Fprintf(&drops, "DROP TABLE IF EXISTS %s;\n", quoteIdent(name))
+	}
+	// user_version back to zero, or migrate() applies nothing to the fresh
+	// schema and every ALTER that a later migration assumes is missing.
+	drops.WriteString("PRAGMA user_version = 0;\n")
+	if _, err := s.db.ExecContext(ctx, drops.String()); err != nil {
+		return fmt.Errorf("wipe: drop tables: %w", err)
+	}
+	if _, err := s.db.ExecContext(ctx, schemaSQL); err != nil {
+		return fmt.Errorf("wipe: reapply schema: %w", err)
+	}
+	if err := migrate(ctx, s.db); err != nil {
+		return fmt.Errorf("wipe: re-migrate: %w", err)
+	}
+	// The file keeps the pages the dropped rows used until it is vacuumed, and
+	// a wipe that leaves readable text in free pages is not a wipe.
+	if _, err := s.db.ExecContext(ctx, `VACUUM`); err != nil {
+		return fmt.Errorf("wipe: vacuum: %w", err)
+	}
+	return nil
+}
+
+// userTables lists every table the schema owns, sorted, excluding sqlite's own
+// internal tables (sqlite_sequence and friends, which cannot be dropped).
+func userTables(ctx context.Context, db *sql.DB) ([]string, error) {
+	rows, err := db.QueryContext(ctx,
+		`SELECT name FROM sqlite_master WHERE type = 'table' AND name NOT LIKE 'sqlite_%'`)
+	if err != nil {
+		return nil, fmt.Errorf("list tables: %w", err)
+	}
+	defer rows.Close()
+	var names []string
+	for rows.Next() {
+		var name string
+		if err := rows.Scan(&name); err != nil {
+			return nil, fmt.Errorf("list tables: %w", err)
+		}
+		names = append(names, name)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("list tables: %w", err)
+	}
+	sort.Strings(names)
+	return names, nil
+}
+
+func quoteIdent(name string) string {
+	return `"` + strings.ReplaceAll(name, `"`, `""`) + `"`
+}
@@ -0,0 +1,99 @@
+package store
+
+import (
+	"context"
+	"database/sql"
+	"path/filepath"
+	"testing"
+	"time"
+)
+
+// A wipe has to leave a working, empty install: every table still there, every
+// migration still applied, and not one row of his anywhere (Vikunja #494).
+func TestWipeEmptiesEveryTableAndLeavesTheSchemaUsable(t *testing.T) {
+	ctx := context.Background()
+	path := filepath.Join(t.TempDir(), "wipe.db")
+	s, err := Open(ctx, path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer s.Close()
+
+	now := time.Now()
+	if _, err := s.WriteFact(ctx, now, KindSelf, "monitor", "новый", "tap:test", 1, sql.NullInt64{}); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := s.WriteNote(ctx, now, "купил монитор", []float32{0.1, 0.2}, "tap:test"); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := s.CaptureTask(ctx, Task{Text: "вернуть монитор", Source: "tap:test", Status: TaskOpen, CreatedTs: now}); err != nil {
+		t.Fatal(err)
+	}
+
+	before, err := s.WipeCounts(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	populated := 0
+	for _, c := range before {
+		if c.Rows > 0 {
+			populated++
+		}
+	}
+	if populated == 0 {
+		t.Fatal("nothing was written, so the wipe proves nothing")
+	}
+
+	if err := s.Wipe(ctx); err != nil {
+		t.Fatal(err)
+	}
+
+	after, err := s.WipeCounts(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(after) != len(before) {
+		t.Errorf("table count changed across the wipe: %d before, %d after", len(before), len(after))
+	}
+	for _, c := range after {
+		if c.Rows != 0 {
+			t.Errorf("table %s still holds %d rows after the wipe", c.Table, c.Rows)
+		}
+	}
+
+	// The migrations are what make the schema usable, so the check that matters
+	// is a write through the newest columns, not a version number.
+	if _, err := s.CaptureTask(ctx, Task{Text: "новая задача", Source: "tap:test", Status: TaskOpen, CreatedTs: now}); err != nil {
+		t.Errorf("the store is not usable after a wipe: %v", err)
+	}
+	if _, err := s.WriteFact(ctx, now, KindSelf, "monitor", "другой", "tap:test", 1, sql.NullInt64{}); err != nil {
+		t.Errorf("the store is not usable after a wipe: %v", err)
+	}
+}
+
+// A wipe that reports success while leaving a table behind is the failure the
+// drop-everything approach exists to prevent, so the count has to see the
+// tables migrations added, not only the ones schema.sql declares.
+func TestWipeCountsSeeMigratedTables(t *testing.T) {
+	ctx := context.Background()
+	s, err := Open(ctx, filepath.Join(t.TempDir(), "counts.db"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer s.Close()
+
+	counts, err := s.WipeCounts(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+	seen := map[string]bool{}
+	for _, c := range counts {
+		seen[c.Table] = true
+	}
+	// One from schema.sql, three from migrations, one from a table rebuild.
+	for _, want := range []string{"facts", "memory_vectors", "tasks", "ecosystem_traces", "nudges"} {
+		if !seen[want] {
+			t.Errorf("wipe does not see table %s", want)
+		}
+	}
+}