a moved file relocates its ladder instead of rebuilding it, and orphans go

Moving a file into a folder made the sync look at a new path, find nothing, and
convert it again — minutes of work to produce bytes that already existed a
directory away — while the old folder stayed behind forever, because nothing ever
deleted one.

A move preserves size and mtime, and both are already in the manifest and in the
stat. So the sync indexes what is already derived on that pair, and a file that
has moved has its ladder RENAMED across.

An ambiguous match is refused rather than guessed. Two originals can share a size
and an mtime — a camera dump can write a whole card in one second — and
rebuilding is merely slow where attaching the wrong photographs to a name is
wrong.

Orphans are removed afterwards, and only on a WHOLE-TREE sync. A scoped run knows
about one folder, so everything outside it looks abandoned; deleting on that
basis would take out the library the first time somebody re-synced a subfolder.
Safe otherwise because derived/ is reproducible by definition, which is what its
name has meant since these two folders stopped being called `user` and `treated`.

Both are counted, recorded in the ledger and shown only when they happened, so an
ordinary run stays one short line.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

api/derive.ts

@@ -1,5 +1,5 @@
 import { mkdir, readdir, readFile, rename, rm, stat, writeFile } from 'node:fs/promises';
-import { join, relative } from 'node:path';
+import { dirname, join, relative } from 'node:path';
 import { sidecarPort } from '@@/sidecar-registry';
 import { mediaPath } from './media';
 
@@ -486,3 +486,123 @@ export async function reconcile(email: string, scope = ''): Promise<Reconciliati
 
   return { originals: files.length, current, missing, stale };
 }
+
+/**
+ * Every derived folder that already exists, indexed by what it was built FROM.
+ *
+ * ── What this is for ──
+ *
+ * The mapping from original to derived is by PATH, so moving a file into a folder makes the sync look
+ * somewhere new, find nothing, and convert it again — minutes of work to produce bytes that already
+ * exist a directory away, while the old folder stays behind forever because nothing deletes it.
+ *
+ * A move preserves size and mtime, so the pair identifies the same file at a new path. That is what
+ * this index is: build it once before a sync, and a file that has moved can have its ladder RENAMED
+ * into place instead of rebuilt.
+ *
+ * ── Why the pair, and not a hash ──
+ *
+ * A hash would be exact and would also mean reading every byte of every original on every sync, which
+ * is the cost this is trying to avoid. Size and mtime are already in the manifest and already in the
+ * stat, so the index is free.
+ *
+ * It is not unique in principle — two files can share both — so an ambiguous match is REFUSED below
+ * rather than guessed at. Rebuilding is slow; attaching the wrong pictures to a name is wrong.
+ */
+export type DerivedIndex = Map<string, string[]>;
+
+const indexKey = (bytes: number, mtimeMs: number) => `${bytes}:${mtimeMs}`;
+
+/** Walk `derived/`, reading each manifest. Directories are the unit — a manifest is one built original. */
+export async function indexDerived(root: string, prefix = '', into: DerivedIndex = new Map()): Promise<DerivedIndex> {
+  const entries = await readdir(join(root, prefix), { withFileTypes: true }).catch(() => []);
+
+  for (const entry of entries) {
+    if (!entry.isDirectory() || entry.name.startsWith('.')) continue;
+    const rel = prefix ? `${prefix}/${entry.name}` : entry.name;
+
+    const raw = await readFile(join(root, rel, MANIFEST), 'utf8').catch(() => null);
+    if (raw) {
+      try {
+        const manifest = JSON.parse(raw) as Manifest;
+        const key = indexKey(manifest.source.bytes, manifest.source.mtimeMs);
+        into.set(key, [...(into.get(key) ?? []), rel]);
+      } catch {
+        // Unreadable manifest: not indexed, so the file it belongs to rebuilds. One corrupt folder
+        // costs one conversion rather than making the whole index untrustworthy.
+      }
+      // A built original is a leaf — its contents are renditions, not more originals.
+      continue;
+    }
+
+    await indexDerived(root, rel, into);
+  }
+
+  return into;
+}
+
+/**
+ * Has this original simply MOVED? If so, put its ladder where the file now is.
+ *
+ * Returns true when the folder was relocated and is now correct for this path.
+ *
+ * Refuses an ambiguous match. Two originals sharing a size and an mtime is unlikely and not
+ * impossible — a camera dump can write a whole card in one second — and attaching the wrong
+ * photographs to a name is a worse outcome than converting again.
+ */
+export async function relocateDerived(
+  index: DerivedIndex,
+  derivedRoot: string,
+  relativePath: string,
+  source: { bytes: number; mtimeMs: number },
+): Promise<boolean> {
+  const candidates = index.get(indexKey(source.bytes, source.mtimeMs)) ?? [];
+  if (candidates.length !== 1) return false;
+
+  const from = candidates[0]!;
+  if (from === relativePath) return false;
+
+  const fromDir = join(derivedRoot, from);
+  const toDir = join(derivedRoot, relativePath);
+
+  // Only if the destination is genuinely empty. A folder already there is either current — in which
+  // case nothing needed doing — or half-built, and overwriting it with a rename is not a repair.
+  if (await stat(toDir).catch(() => null)) return false;
+
+  try {
+    await mkdir(dirname(toDir), { recursive: true });
+    await rename(fromDir, toDir);
+    // Claimed, so a second original with the same size and mtime cannot take it too.
+    index.delete(indexKey(source.bytes, source.mtimeMs));
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Remove derived folders whose original is gone.
+ *
+ * ── Only for a whole-tree sync ──
+ *
+ * A scoped sync knows about one folder, so everything outside it would look abandoned. Deleting on
+ * that basis would take out the entire library the first time somebody re-synced a subfolder, which is
+ * the kind of mistake that is only noticed later.
+ *
+ * Safe to run because `derived/` is reproducible by definition — that is what its name has meant since
+ * the day the two folders were called `originals` and `derived` rather than `user` and `treated`.
+ */
+export async function pruneDerived(originalsRoot: string, derivedRoot: string): Promise<string[]> {
+  const alive = new Set(await listOriginals(originalsRoot));
+  const built = await indexDerived(derivedRoot);
+
+  const removed: string[] = [];
+  for (const paths of built.values()) {
+    for (const path of paths) {
+      if (alive.has(path)) continue;
+      await rm(join(derivedRoot, path), { recursive: true, force: true }).catch(() => {});
+      removed.push(path);
+    }
+  }
+  return removed;
+}

api/ledger.ts

@@ -54,6 +54,10 @@ export type Run = {
   total: number;
   built: number;
   skipped: number;
+  /** Renamed into place after a move, rather than rebuilt. */
+  moved: number;
+  /** Removed because the original is gone. */
+  pruned: number;
   errors: SyncError[];
   /** Set when the run stopped for a reason that was not about any single file. */
   fatal: string | null;

api/sync.ts

@@ -1,6 +1,16 @@
-import { mkdir } from 'node:fs/promises';
+import { mkdir, stat } from 'node:fs/promises';
 import { dirname } from 'node:path';
-import { deriveOne, derivedDir, listOriginals, originalsDir, safeScope, targetFor } from './derive';
+import {
+  deriveOne,
+  derivedDir,
+  indexDerived,
+  listOriginals,
+  originalsDir,
+  pruneDerived,
+  relocateDerived,
+  safeScope,
+  targetFor,
+} from './derive';
 import { appendRun, type RunTrigger } from './ledger';
 
 /**
@@ -47,6 +57,10 @@ export type SyncState = {
   done: number;
   built: number;
   skipped: number;
+  /** Ladders that were RENAMED into place because their original moved, rather than rebuilt. */
+  moved: number;
+  /** Derived folders removed because their original is gone. Only on a whole-tree sync. */
+  pruned: number;
   errors: SyncError[];
   /** The files being worked on right now, for somebody watching. Empty when idle. */
   current: string[];
@@ -73,6 +87,8 @@ const idle = (): SyncState => ({
   done: 0,
   built: 0,
   skipped: 0,
+  moved: 0,
+  pruned: 0,
   errors: [],
   current: [],
   startedAt: null,
@@ -123,6 +139,16 @@ async function run(email: string, state: SyncState): Promise<void> {
     const files = await listOriginals(from, state.scope);
     state.total = files.length;
 
+    /*
+      What is already built, indexed by what it was built FROM.
+
+      Built once, before the walk, so a file that has simply MOVED can have its ladder renamed into
+      place instead of converted again — minutes of work to produce bytes that already exist a
+      directory away. Size and mtime survive a move and are already in both the manifest and the stat,
+      so the index costs one pass over derived/ and nothing else.
+    */
+    const derivedIndex = await indexDerived(to);
+
     let next = 0;
     const worker = async (): Promise<void> => {
       for (;;) {
@@ -134,8 +160,24 @@ async function run(email: string, state: SyncState): Promise<void> {
         try {
           const target = targetFor(to, file);
           await mkdir(dirname(target), { recursive: true });
+
+          /*
+            A move, before a build.
+
+            `deriveOne` decides by looking for a manifest at the target, so a file that changed folder
+            has none there and would convert from scratch. This asks the index whether the same bytes
+            were already built somewhere else and, if exactly one folder matches, renames it across.
+            An ambiguous match is refused inside `relocateDerived` — rebuilding is slow, attaching the
+            wrong photographs to a name is wrong.
+          */
+          const info = await stat(`${from}/${file}`).catch(() => null);
+          const relocated = info
+            ? await relocateDerived(derivedIndex, to, file, { bytes: info.size, mtimeMs: Math.round(info.mtimeMs) })
+            : false;
+
           const { built } = await deriveOne(`${from}/${file}`, target, email);
-          if (built) state.built++;
+          if (relocated && !built) state.moved++;
+          else if (built) state.built++;
           else state.skipped++;
         } catch (error) {
           const message = (error as Error).message;
@@ -159,6 +201,18 @@ async function run(email: string, state: SyncState): Promise<void> {
     };
 
     await Promise.all(Array.from({ length: CONCURRENCY }, worker));
+
+    /*
+      Then the orphans — derived folders whose original no longer exists.
+
+      Only on a WHOLE-TREE sync. A scoped one knows about a single folder, so everything outside it
+      looks abandoned, and deleting on that basis would take out the library the first time somebody
+      re-synced one subfolder. Safe otherwise because derived/ is reproducible by definition, which is
+      what the name has meant since these two folders stopped being called `user` and `treated`.
+    */
+    if (!state.scope && !state.fatal) {
+      state.pruned = (await pruneDerived(from, to)).length;
+    }
   } catch (error) {
     state.fatal = (error as Error).message;
   } finally {
@@ -180,6 +234,8 @@ async function run(email: string, state: SyncState): Promise<void> {
       total: state.total ?? state.done,
       built: state.built,
       skipped: state.skipped,
+      moved: state.moved,
+      pruned: state.pruned,
       errors: state.errors,
       fatal: state.fatal,
     });

web/MediaSync.tsx

@@ -46,6 +46,10 @@ type SyncState = {
   done: number;
   built: number;
   skipped: number;
+  /** Ladders renamed into place because their original moved, rather than rebuilt. */
+  moved: number;
+  /** Derived folders removed because their original is gone. Whole-tree syncs only. */
+  pruned: number;
   errors: SyncError[];
   current: string[];
   startedAt: string | null;
@@ -61,6 +65,8 @@ type Run = {
   total: number;
   built: number;
   skipped: number;
+  moved: number;
+  pruned: number;
   errors: SyncError[];
   fatal: string | null;
 };
@@ -251,6 +257,9 @@ export const MediaSync = ({ onSettled }: { onSettled?: (settled: boolean) => voi
                 {run.scope ? `${run.scope} · ` : ''}
                 {run.built} built
                 {run.skipped ? `, ${run.skipped} current` : ''}
+                {/* Only when they happened, so an ordinary run stays one short line. */}
+                {run.moved ? `, ${run.moved} moved` : ''}
+                {run.pruned ? `, ${run.pruned} orphans removed` : ''}
                 {run.errors.length ? `, ${run.errors.length} failed` : ''}
                 {run.fatal ? ` — ${run.fatal}` : ''}
                 {run.trigger === 'watcher' ? ' · on upload' : ''}