Merge branch 'fix/wizard-apps-and-progress'

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013XSohfUQQiaE77qyFLgSv3

1 files changed, 49 insertions, 16 deletions

diff --git a/packages/meshbay-node/src/meshbay_node/indexer/indexer.py b/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
index 10981c0..f78465b 100644
--- a/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
+++ b/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
@@ -139,6 +139,27 @@ def _walk_root(root: Root) -> list[Path]:
     return [p for p in root.path.rglob("*") if p.is_file()]
 
 
+def _size_files(files: list[Path]) -> list[tuple[Path, int]]:
+    """
+    Blocking: stat() every file from an already-completed walk — run via an
+    executor for the same reason `_walk_root` is (its own docstring above).
+    Previously a plain loop straight on the asyncio event loop thread: for a
+    root with many thousands of files (a real personal library, not a
+    hypothetical — docs/musicbay.md's own "several thousand files" example)
+    that blocked the entire daemon, every WebRTC session and the admin UI
+    included, for as long as the stat() calls took — and did so *before*
+    `_scan_root` had even set `progress.scanning`, so a consumer polling it
+    saw "not scanning" the whole time real, blocking work was happening.
+    """
+    sized: list[tuple[Path, int]] = []
+    for p in files:
+        try:
+            sized.append((p, p.stat().st_size))
+        except OSError:
+            continue
+    return sized
+
+
 def _scan_file(root: Root, file_path: Path) -> IndexEntry | None:
     """Compute IndexEntry for a file. Blocking — run in executor.
     Uses streaming blake3 so arbitrarily large files (ISOs, VM images, etc.)
@@ -304,26 +325,38 @@ class DirectoryIndexer:
         log.info("Scanning %s (root %r) ...", root.path, root.name)
         count = 0
         loop = asyncio.get_event_loop()
-        try:
-            files = await loop.run_in_executor(self._executor, _walk_root, root)
-        except OSError as e:
-            log.warning("Cannot scan root %r: %s", root.name, e)
-            return 0
-
-        # Sizes up front, off the same listing that already walked the tree —
-        # the progress bar's denominator, not a second pass over the disk.
-        sized: list[tuple[Path, int]] = []
-        for p in files:
-            try:
-                sized.append((p, p.stat().st_size))
-            except OSError:
-                continue
 
+        # `scanning` flips on here, before the walk — not after it and the
+        # sizing pass, which for a large or slow (network/USB) root can
+        # themselves take a long time despite running off-loop. A consumer
+        # polling IndexProgress (index-status; the Create Group wizard's
+        # own progress bar) must see "scanning" the moment real work starts,
+        # not only once the file list and its total size are known. Found
+        # live (2026-08-25): the wizard's post-creation "add extra roots"
+        # step gave up waiting after a short grace period because the flag
+        # had not yet turned on, even though the node was already several
+        # seconds into walking and sizing a large root — total_bytes is
+        # unknown at this point, so it starts at 0 and is corrected below.
         self.progress.scanning = True
         self.progress.scanned_bytes = 0
-        self.progress.total_bytes = sum(size for _, size in sized)
-        self.progress.current_dir = ""
+        self.progress.total_bytes = 0
+        self.progress.current_dir = root.name
         try:
+            try:
+                files = await loop.run_in_executor(self._executor, _walk_root, root)
+            except OSError as e:
+                log.warning("Cannot scan root %r: %s", root.name, e)
+                return 0
+
+            # Sizes up front, off the same listing that already walked the
+            # tree — the progress bar's denominator, not a second pass over
+            # the disk. Off-loop for the same reason the walk itself is
+            # (_size_files's own docstring: this used to be a synchronous
+            # loop right here, blocking the whole daemon for a large root).
+            sized = await loop.run_in_executor(self._executor, _size_files, files)
+
+            self.progress.total_bytes = sum(size for _, size in sized)
+            self.progress.current_dir = ""
             for file_path, size in sized:
                 self.progress.current_dir = file_path.parent.name
                 entry = await self._hash_or_cached(root, file_path)