fix(store): serialize concurrent updates per plugin, check cleanup results

CodeRabbit review on #405 flagged two things in
_reinstall_with_rollback, both verified against current code:

- Real race: the web UI runs Flask with threaded=True and there's a
  single update route, so two overlapping requests for the same
  plugin_id (double-click, two tabs) can interleave. The loser could
  rename the winner's in-progress install aside mid-download, deleting
  its own rollback safety net — worse than the bug this function
  exists to fix. Added a lazy per-plugin_id lock dict (mirrors the
  plugin_manager per-plugin lock pattern) held for the whole function.
- _safe_remove_directory's return value was ignored at both call
  sites. Stale-aside cleanup failure now aborts cleanly instead of
  falling through to a rename that would fail anyway with a less
  useful error; post-success backup-removal failure now logs instead
  of failing silently (still returns True — the update itself
  succeeded, and the next update self-heals the leftover aside).

Left the third nitpick (test_stale_aside_from_previous_crash_is_cleared)
addressed by asserting the stale dir is actually gone and that
install_plugin was reached, rather than just the end-to-end result.

Added a concurrency regression test asserting install_plugin never
runs for the same plugin_id while another call is in flight.

src/display_manager.py

@@ -33,8 +33,7 @@ else:
 from contextlib import contextmanager
 from PIL import Image, ImageDraw, ImageFont
 import time
-from collections import OrderedDict
-from typing import Dict, Any, List, Optional, Tuple
+from typing import Dict, Any, List, Optional
 import logging
 import math
 import freetype
@@ -181,25 +180,14 @@ class DisplayManager:
         # the logical image is blitted to the matrix unchanged.
         self._double_sided = None  # dict {copies, axis, logical_width, logical_height} or None
         self._physical_image = None  # full-chain buffer reused each frame when tiling
-        # Text-width measurement cache: (text, id(font)) -> (width, font_ref)
+        # Text-width measurement cache: (text, id(font)) -> pixel_width
         # Avoids re-measuring the same string+font on every display() call.
-        # LRU-bounded: keys embed the TEXT, so changing strings (a clock, a
-        # live score) would otherwise grow it forever on a 24/7 service.
-        # Entries hold a strong reference to the font so its id() can't be
-        # recycled by a different font object — an id-keyed cache without
-        # the reference can return the WRONG width after garbage collection.
         # Cleared on _load_fonts() so stale entries don't survive a font reload.
-        self._text_width_cache: "OrderedDict[tuple, Tuple[int, Any]]" = OrderedDict()
-        self._TEXT_WIDTH_CACHE_MAX = 1024
+        self._text_width_cache: Dict[tuple, int] = {}
         # Snapshot settings for web preview integration (service writes, web reads)
         self._snapshot_path = "/tmp/led_matrix_preview.png"  # nosec B108 - fixed path intentional; web UI reads same path
         self._snapshot_min_interval_sec = 0.2  # max ~5 fps
         self._last_snapshot_ts = 0.0
-        # Snapshot failures are logged as warnings, rate-limited so a
-        # persistent failure (e.g. an unwritable file) can't spam the log —
-        # but is never silent: the snapshot's mtime doubles as the web UI's
-        # hardware-liveness signal, so a quiet failure makes health checks lie.
-        self._snapshot_fail_log_ts = 0.0
         
         # Scrolling state tracking for graceful updates
         self._scrolling_state = {
@@ -711,15 +699,12 @@ class DisplayManager:
 
         Results are cached by (text, font identity) so plugins that measure
         the same string every frame (e.g. to centre a score) pay only one
-        measurement per unique (text, font) pair. The entry keeps the font
-        alive so its id() can't be recycled, and the cache is LRU-bounded so
-        ever-changing text (clocks, tickers) can't grow it without limit.
+        measurement per unique (text, font) pair.
         """
         cache_key = (text, id(font))
         cached = self._text_width_cache.get(cache_key)
         if cached is not None:
-            self._text_width_cache.move_to_end(cache_key)
-            return cached[0]
+            return cached
 
         try:
             if isinstance(font, freetype.Face):
@@ -734,9 +719,7 @@ class DisplayManager:
             logger.error("Error getting text width: %s", e)
             return 0
 
-        self._text_width_cache[cache_key] = (width, font)
-        while len(self._text_width_cache) > self._TEXT_WIDTH_CACHE_MAX:
-            self._text_width_cache.popitem(last=False)
+        self._text_width_cache[cache_key] = width
         return width
 
     def get_font_height(self, font):
@@ -1181,15 +1164,5 @@ class DisplayManager:
                 pass
             self._last_snapshot_ts = now
         except Exception as e:
-            # Snapshot failures must never break display — but they must not
-            # be silent either: the snapshot's mtime is the web UI's display
-            # mirror AND its hardware-liveness proxy, so a quietly failing
-            # write freezes the mirror and makes health checks lie (seen in
-            # the field: a stale root-owned /tmp file froze it for a day).
-            # Warn at most once per 5 minutes to avoid log spam.
-            if (now - self._snapshot_fail_log_ts) > 300:
-                self._snapshot_fail_log_ts = now
-                logger.warning("Snapshot write failing (web preview/health "
-                               "mirror is stale): %s", e)
-            else:
-                logger.debug(f"Snapshot write skipped: {e}")
+            # Snapshot failures should never break display; log at debug to avoid noise
+            logger.debug(f"Snapshot write skipped: {e}")

src/font_manager.py

@@ -35,7 +35,6 @@ import urllib.request
 import zipfile
 import tempfile
 import time
-from collections import OrderedDict
 from pathlib import Path
 from PIL import ImageFont
 from typing import Dict, Tuple, Optional, Union, Any, List
@@ -59,13 +58,7 @@ class FontManager:
         # Font discovery and catalog
         self.font_catalog: Dict[str, str] = {}  # family_name -> file_path
         self.font_cache: Dict[str, Union[ImageFont.FreeTypeFont, freetype.Face]] = {}  # (family, size) -> font
-        # (text, id(font)) -> ((width, height, baseline), font_ref).
-        # LRU-bounded — keys embed the measured TEXT, so changing strings
-        # (clocks, live scores) would otherwise grow it forever. Entries
-        # keep the font alive so its id() can't be recycled by a different
-        # font object (which would silently return wrong metrics).
-        self.metrics_cache: "OrderedDict[Any, Tuple[Tuple[int, int, int], Any]]" = OrderedDict()
-        self._METRICS_CACHE_MAX = 1024
+        self.metrics_cache: Dict[str, Tuple[int, int, int]] = {}  # (text, font_id) -> (width, height, baseline)
 
         # Plugin font management
         self.plugin_fonts: Dict[str, Dict[str, Any]] = {}  # plugin_id -> font_manifest
@@ -514,14 +507,10 @@ class FontManager:
         Returns:
             Tuple of (width, height, baseline_offset)
         """
-        # Key on the text itself (hash(text) could collide) + font identity;
-        # the entry below keeps the font referenced so the id stays valid.
-        cache_key = (text, id(font))
+        cache_key = f"{hash(text)}_{id(font)}"
 
-        cached = self.metrics_cache.get(cache_key)
-        if cached is not None:
-            self.metrics_cache.move_to_end(cache_key)
-            return cached[0]
+        if cache_key in self.metrics_cache:
+            return self.metrics_cache[cache_key]
 
         try:
             if isinstance(font, freetype.Face):
@@ -558,9 +547,7 @@ class FontManager:
             baseline = 10
 
         result = (width, height, baseline)
-        self.metrics_cache[cache_key] = (result, font)
-        while len(self.metrics_cache) > self._METRICS_CACHE_MAX:
-            self.metrics_cache.popitem(last=False)
+        self.metrics_cache[cache_key] = result
         return result
 
     def get_font_height(self, font: Union[ImageFont.FreeTypeFont, freetype.Face]) -> int:

src/plugin_system/store_manager.py

@@ -142,9 +142,28 @@ class PluginStoreManager:
         # then get the result from the warm cache (double-checked locking).
         self._registry_fetch_lock = threading.Lock()
 
+        # Per-plugin locks for _reinstall_with_rollback: the web UI runs
+        # Flask with threaded=True, so two overlapping requests for the
+        # same plugin_id (double-click, two browser tabs) would otherwise
+        # both rename the same directory aside — one succeeds, and the
+        # loser can end up renaming the winner's in-progress install aside
+        # mid-download, stealing its own rollback safety net. Keyed by
+        # plugin_id so unrelated plugins still update concurrently.
+        self._reinstall_locks: Dict[str, threading.Lock] = {}
+        self._reinstall_locks_guard = threading.Lock()
+
         # Ensure plugins directory exists
         self.plugins_dir.mkdir(exist_ok=True)
 
+    def _get_reinstall_lock(self, plugin_id: str) -> threading.Lock:
+        """Lazily create (or fetch) the per-plugin reinstall lock."""
+        with self._reinstall_locks_guard:
+            lock = self._reinstall_locks.get(plugin_id)
+            if lock is None:
+                lock = threading.Lock()
+                self._reinstall_locks[plugin_id] = lock
+            return lock
+
     def _record_cache_backoff(self, cache_dict: Dict, cache_key: str,
                               cache_timeout: int, payload: Any) -> None:
         """Bump a cache entry's timestamp so subsequent lookups hit the
@@ -2263,6 +2282,74 @@ class PluginStoreManager:
             self.logger.error(f"Error uninstalling plugin {plugin_id}: {e}")
             return False
     
+    def _reinstall_with_rollback(self, plugin_id: str, plugin_path: Path) -> bool:
+        """Replace an installed plugin with a fresh install, atomically.
+
+        The old install is renamed aside (not deleted) until the new install
+        succeeds, then removed; on ANY install failure the old directory is
+        restored. This is the difference between a failed update and a
+        destroyed plugin: the previous delete-then-install flow permanently
+        removed plugins whenever the download failed mid-update (seen in the
+        field during the monorepo migration on a Pi with broken DNS — every
+        old-remote plugin was deleted and none could be re-downloaded).
+
+        The aside name embeds '.standalone-backup-' so plugin discovery
+        (plugin_manager._scan_directory_for_plugins) ignores it even though
+        it still contains a manifest.json.
+
+        Held for the whole operation under a per-plugin_id lock: two
+        overlapping requests for the same plugin (double-click, two
+        browser tabs — the web UI runs Flask with threaded=True) must not
+        interleave their renames, or the second could steal the first's
+        rollback safety net mid-install. Other plugin_ids are unaffected.
+        """
+        with self._get_reinstall_lock(plugin_id):
+            backup_path = plugin_path.with_name(
+                f"{plugin_path.name}.standalone-backup-migrating")
+            # A stale aside from a previous crash would block the rename
+            if backup_path.exists():
+                if not self._safe_remove_directory(backup_path):
+                    self.logger.error(
+                        f"Could not clear stale backup for {plugin_id} at "
+                        f"{backup_path}; leaving old install in place")
+                    return False
+            try:
+                plugin_path.rename(backup_path)
+            except OSError as e:
+                self.logger.error(
+                    f"Could not set aside old plugin directory for {plugin_id}: {e}")
+                return False
+
+            try:
+                installed = self.install_plugin(plugin_id)
+            except Exception as e:
+                self.logger.error(f"Reinstall of {plugin_id} raised: {e}")
+                installed = False
+
+            if installed:
+                if not self._safe_remove_directory(backup_path):
+                    self.logger.warning(
+                        f"Update of {plugin_id} succeeded but the old backup "
+                        f"at {backup_path} could not be removed; it will be "
+                        f"cleared on the next update")
+                return True
+
+            # Install failed (bad network, registry error...) — put the old
+            # version back so the user still has a working plugin.
+            self.logger.error(
+                f"Reinstall of {plugin_id} failed; restoring previous version")
+            try:
+                if plugin_path.exists():
+                    # partial download debris from the failed install
+                    self._safe_remove_directory(plugin_path)
+                backup_path.rename(plugin_path)
+                self.logger.info(f"Restored previous install of {plugin_id}")
+            except OSError as e:
+                self.logger.error(
+                    f"CRITICAL: could not restore {plugin_id} from {backup_path}: {e}. "
+                    f"The previous install is preserved there — rename it back manually.")
+            return False
+
     def update_plugin(self, plugin_id: str) -> bool:
         """
         Update a plugin to the latest commit on its upstream branch.
@@ -2325,10 +2412,7 @@ class PluginStoreManager:
                             f"Plugin {resolved_id} git remote ({local_remote}) differs from registry ({registry_repo}). "
                             f"Reinstalling from registry to migrate to new source."
                         )
-                        if not self._safe_remove_directory(plugin_path):
-                            self.logger.error(f"Failed to remove old plugin directory for {resolved_id}")
-                            return False
-                        return self.install_plugin(resolved_id)
+                        return self._reinstall_with_rollback(resolved_id, plugin_path)
 
                     # Check if already up to date
                     if remote_sha and local_sha and remote_sha.startswith(local_sha):
@@ -2632,11 +2716,11 @@ class PluginStoreManager:
             # Plugin is not a git repo but is in registry and has a newer version - reinstall
             self.logger.info(f"Plugin {plugin_id} not installed via git; re-installing latest archive (registry id: {registry_id})")
 
-            # Remove directory and reinstall fresh
-            if not self._safe_remove_directory(plugin_path):
-                self.logger.error(f"Failed to remove old plugin directory for {plugin_id}")
-                return False
-            return self.install_plugin(registry_id)
+            # Reinstall with the old version kept aside until the new
+            # download succeeds — this is the path every routine store
+            # update takes, and a mid-update network failure must not
+            # destroy the user's plugin.
+            return self._reinstall_with_rollback(registry_id, plugin_path)
 
         except Exception as e:
             import traceback

test/conftest.py

@@ -38,11 +38,7 @@ def mock_cache_manager():
     mock._memory_cache_timestamps = {}
     mock.cache_dir = "/tmp/test_cache"
     
-    def mock_get(key: str, max_age: Optional[int] = 300,
-                 memory_ttl: Optional[int] = None) -> Optional[Dict]:
-        # Signature mirrors CacheManager.get — keep in sync or callers
-        # passing keyword args (health tracker, resource monitor) break
-        # only in tests, hiding real-API compatibility.
+    def mock_get(key: str, max_age: int = 300) -> Optional[Dict]:
         return mock._memory_cache.get(key)
     
     def mock_set(key: str, data: Dict, ttl: Optional[int] = None) -> None:

test/test_store_update_rollback.py

@@ -0,0 +1,171 @@
+"""Tests for atomic plugin updates (store_manager._reinstall_with_rollback).
+
+Regression for a field data-loss incident: update_plugin's reinstall paths
+(monorepo migration AND routine archive updates) deleted the installed
+plugin BEFORE downloading its replacement — a mid-update network failure
+permanently destroyed the plugin. Seen live: a Pi with broken DNS lost 12
+plugins from one update pass.
+"""
+
+import json
+import os
+import sys
+import threading
+import time
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+from src.plugin_system.store_manager import PluginStoreManager  # noqa: E402
+
+PLUGIN_ID = "rollback-test-plugin"
+
+
+@pytest.fixture
+def store(tmp_path):
+    mgr = PluginStoreManager(plugins_dir=str(tmp_path))
+    plugin_dir = tmp_path / PLUGIN_ID
+    plugin_dir.mkdir()
+    (plugin_dir / "manifest.json").write_text(json.dumps(
+        {"id": PLUGIN_ID, "name": "Rollback Test", "version": "1.0.0"}))
+    (plugin_dir / "manager.py").write_text("# old version marker\n")
+    return mgr, plugin_dir
+
+
+class TestReinstallWithRollback:
+    def test_failed_install_restores_old_version(self, store):
+        """The whole point: a failed download must leave the old install."""
+        mgr, plugin_dir = store
+        with patch.object(mgr, "install_plugin", return_value=False):
+            ok = mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir)
+        assert ok is False
+        assert plugin_dir.exists()
+        assert "old version marker" in (plugin_dir / "manager.py").read_text()
+        # no aside debris left behind
+        leftovers = [p for p in plugin_dir.parent.iterdir()
+                     if "standalone-backup" in p.name]
+        assert leftovers == []
+
+    def test_install_exception_restores_old_version(self, store):
+        mgr, plugin_dir = store
+        with patch.object(mgr, "install_plugin",
+                          side_effect=RuntimeError("network down")):
+            ok = mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir)
+        assert ok is False
+        assert plugin_dir.exists()
+        assert "old version marker" in (plugin_dir / "manager.py").read_text()
+
+    def test_successful_install_removes_aside(self, store):
+        mgr, plugin_dir = store
+
+        def fake_install(plugin_id):
+            new_dir = plugin_dir  # same path, new content
+            new_dir.mkdir(exist_ok=True)
+            (new_dir / "manager.py").write_text("# new version\n")
+            (new_dir / "manifest.json").write_text(json.dumps(
+                {"id": PLUGIN_ID, "name": "Rollback Test", "version": "2.0.0"}))
+            return True
+
+        with patch.object(mgr, "install_plugin", side_effect=fake_install):
+            ok = mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir)
+        assert ok is True
+        assert "new version" in (plugin_dir / "manager.py").read_text()
+        leftovers = [p for p in plugin_dir.parent.iterdir()
+                     if "standalone-backup" in p.name]
+        assert leftovers == []
+
+    def test_partial_download_debris_is_replaced_by_old_version(self, store):
+        """A failed install that left a partial directory must still roll back."""
+        mgr, plugin_dir = store
+
+        def fake_partial_install(plugin_id):
+            plugin_dir.mkdir(exist_ok=True)
+            (plugin_dir / "half-downloaded.tmp").write_text("junk")
+            return False
+
+        with patch.object(mgr, "install_plugin", side_effect=fake_partial_install):
+            ok = mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir)
+        assert ok is False
+        assert "old version marker" in (plugin_dir / "manager.py").read_text()
+        assert not (plugin_dir / "half-downloaded.tmp").exists()
+
+    def test_stale_aside_from_previous_crash_is_cleared(self, store):
+        mgr, plugin_dir = store
+        stale = plugin_dir.parent / f"{PLUGIN_ID}.standalone-backup-migrating"
+        stale.mkdir()
+        (stale / "old.txt").write_text("stale")
+        with patch.object(mgr, "install_plugin", return_value=False) as mock_install:
+            ok = mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir)
+        # The reinstall itself still fails (mocked) and the old install is
+        # restored, but the stale aside must not have survived — otherwise
+        # it would have blocked this run's own rename (or a future one).
+        assert not stale.exists()
+        mock_install.assert_called_once_with(PLUGIN_ID)
+        assert ok is False
+        assert plugin_dir.exists()
+        assert "old version marker" in (plugin_dir / "manager.py").read_text()
+
+    def test_concurrent_updates_for_same_plugin_are_serialized(self, store):
+        """Two overlapping requests for the same plugin_id (double-click,
+        two browser tabs — the web UI runs Flask with threaded=True) must
+        not interleave: the loser must wait for the winner to finish
+        rather than renaming the winner's in-progress install aside and
+        stealing its rollback safety net."""
+        mgr, plugin_dir = store
+
+        active = 0
+        max_active = 0
+        guard = threading.Lock()
+
+        def fake_install(plugin_id):
+            nonlocal active, max_active
+            with guard:
+                active += 1
+                max_active = max(max_active, active)
+            time.sleep(0.05)
+            plugin_dir.mkdir(exist_ok=True)
+            (plugin_dir / "manager.py").write_text("# new version\n")
+            (plugin_dir / "manifest.json").write_text(json.dumps(
+                {"id": PLUGIN_ID, "name": "Rollback Test", "version": "2.0.0"}))
+            with guard:
+                active -= 1
+            return True
+
+        results = []
+
+        def worker():
+            results.append(mgr._reinstall_with_rollback(PLUGIN_ID, plugin_dir))
+
+        with patch.object(mgr, "install_plugin", side_effect=fake_install):
+            threads = [threading.Thread(target=worker) for _ in range(2)]
+            for t in threads:
+                t.start()
+            for t in threads:
+                t.join(timeout=5)
+
+        assert max_active == 1, "install_plugin ran concurrently for the same plugin_id"
+        assert results == [True, True]
+        assert plugin_dir.exists()
+        assert "new version" in (plugin_dir / "manager.py").read_text()
+        leftovers = [p for p in plugin_dir.parent.iterdir()
+                     if "standalone-backup" in p.name]
+        assert leftovers == []
+
+    def test_aside_name_is_invisible_to_discovery(self, store, tmp_path):
+        """The aside still contains a manifest.json — discovery must skip it
+        (relies on the existing '.standalone-backup-' exclusion)."""
+        mgr, plugin_dir = store
+        from src.plugin_system.plugin_manager import PluginManager
+        aside = plugin_dir.parent / f"{PLUGIN_ID}.standalone-backup-migrating"
+        plugin_dir.rename(aside)
+        pm = PluginManager(plugins_dir=str(tmp_path), config_manager=None,
+                           display_manager=None, cache_manager=None)
+        found = pm._scan_directory_for_plugins(Path(tmp_path))
+        assert PLUGIN_ID not in found
+
+
+if __name__ == "__main__":
+    sys.exit(pytest.main([__file__, "-v"]))