Compare commits

..
Author SHA1 Message Date
ChuckBuildsandClaude Opus 5 4cf673f3b6 fix(pixlet): resolve the release tag correctly when downloading
Starlark apps render through the pixlet binary, and the installer that
fetches it silently produced nothing, so every app failed with "Pixlet
not available - Starlark apps will not work".

Two compounding defects:

The version lookup parsed the wrong token. GitHub returns the release
JSON on a single line, so `grep '"tag_name"'` matches the whole document
and the greedy `sed 's/.*"([^"]+)".*/\1/'` captures the LAST quoted
string in it. That resolved to "mentions_count", giving a download URL
for a release that does not exist. The `[ -z "$PIXLET_VERSION" ]`
fallback never fired, because the value was not empty -- just wrong.

And `curl -L -o` without `-f` writes a 404 body to the file and exits 0,
so the download was reported as successful and the first sign of trouble
was tar complaining "not in gzip format" about a page of HTML:

    → Downloading linux-arm64...
      Extracting...
    gzip: stdin: not in gzip format
    ✗ Failed to extract archive: .../pixlet_mentions_count_linux-arm64.tar.gz
    Download complete: 0/1 succeeded

Now the tag field is matched directly and the value taken from it, and
the result is checked for a version shape rather than merely being
non-empty -- a wrong-but-non-empty value is exactly what made this
silent. curl gets -f so an HTTP error is a failure, and the archive is
gzip-tested before extraction, since a proxy can return 200 with an
error page.

Verified on an arm64 rig: v0.53.1 resolved, 1/1 downloaded, the binary
runs, and the plugin's own detection finds it at
bin/pixlet/pixlet-linux-arm64.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Udr6MfaFLUPhX5Fgo67Jf5
2026-08-15 21:04:29 -04:00
3 changed files with 45 additions and 228 deletions
+27 -5
View File
@@ -24,9 +24,20 @@ echo "========================================"
# Auto-detect latest version if needed
if [ "$PIXLET_VERSION" = "latest" ]; then
echo "Detecting latest version..."
PIXLET_VERSION=$(curl -s "https://api.github.com/repos/${REPO}/releases/latest" | grep '"tag_name"' | sed -E 's/.*"([^"]+)".*/\1/')
if [ -z "$PIXLET_VERSION" ]; then
echo "Failed to detect latest version, using fallback"
# GitHub returns this JSON on a single line, so `grep '"tag_name"'`
# matches the whole document and a greedy `sed 's/.*"([^"]+)".*/\1/'`
# captures the LAST quoted token in it rather than the tag. That resolved
# to "mentions_count", which built a download URL for a release that does
# not exist. Match the field itself and take the value after it.
PIXLET_VERSION=$(curl -fsSL "https://api.github.com/repos/${REPO}/releases/latest" \
| grep -o '"tag_name"[[:space:]]*:[[:space:]]*"[^"]*"' \
| head -n1 \
| sed -E 's/.*:[[:space:]]*"([^"]*)".*/\1/')
# A wrong-but-non-empty value is what made the old bug silent, so check
# the shape rather than just that something came back.
if ! printf '%s' "$PIXLET_VERSION" | grep -qE '^v?[0-9]+\.[0-9]+'; then
echo "Could not detect the latest version (got: '${PIXLET_VERSION:-<empty>}'), using fallback"
PIXLET_VERSION="v0.50.2"
fi
fi
@@ -67,8 +78,19 @@ download_binary() {
temp_dir=$(mktemp -d -p "$PROJECT_ROOT" -t pixlet_download.XXXXXXXXXX)
local temp_file="$temp_dir/$archive_name"
if ! curl -L -o "$temp_file" "$url" 2>/dev/null; then
echo "✗ Failed to download $arch"
# -f so an HTTP error is a failure. Without it curl writes the 404 body
# to the file and exits 0, and the first sign of trouble is tar saying
# "not in gzip format" about what is actually a page of HTML.
if ! curl -fL -o "$temp_file" "$url" 2>/dev/null; then
echo "✗ Failed to download $arch from $url"
rm -rf "$temp_dir"
return 1
fi
# Belt and braces: a mirror or proxy can return 200 with an error page.
if ! gzip -t "$temp_file" 2>/dev/null; then
echo "✗ Downloaded file is not a gzip archive: $url"
echo " (first bytes: $(head -c 60 "$temp_file" | tr -d '\0' | tr '\n' ' '))"
rm -rf "$temp_dir"
return 1
fi
+18 -41
View File
@@ -116,14 +116,6 @@ class PluginManager:
self._plugin_locks: Dict[str, threading.Lock] = {}
self._plugin_locks_guard = threading.Lock()
self._update_worker: Optional[threading.Thread] = None
# Plugin ids whose update() has finished since the last time anyone
# asked. Updates are dispatched to a worker thread, so a caller that
# wants to know "whose data just changed" cannot learn it by diffing
# plugin_last_update around run_scheduled_updates() -- that call only
# enqueues, and the timestamp is stamped later, on the worker. See
# run_scheduled_updates_with_changes().
self._completed_updates: set = set()
self._completed_updates_lock = threading.Lock()
self._synchronous_updates = False
if self.config_manager is not None:
try:
@@ -948,7 +940,6 @@ class PluginManager:
if success:
with self._plugin_last_update_lock:
self.plugin_last_update[plugin_id] = scheduled_time
self._note_update_completed(plugin_id)
self.state_manager.record_update(plugin_id)
self.state_manager.set_state(plugin_id, PluginState.ENABLED)
if self.health_tracker:
@@ -1015,41 +1006,28 @@ class PluginManager:
def run_scheduled_updates_with_changes(self, current_time: Optional[float] = None) -> List[str]:
"""
Like run_scheduled_updates(), but also reports which plugins have
fresh data -- the ids whose update() has finished since the last
call, not necessarily the ones enqueued by this one.
Like run_scheduled_updates(), but also returns the plugin_ids whose
plugin_last_update timestamp actually advanced during this call.
That distinction is the whole point. This used to snapshot
plugin_last_update, call run_scheduled_updates(), and diff. But
run_scheduled_updates() only *enqueues*: the work runs on the
update worker and the timestamp is stamped there, after this method
has already returned. The two snapshots were therefore always
identical and the result was always empty, so Vegas never learned
that any plugin's data had changed and kept scrolling whatever a
segment was first built from -- last night's live game still drawn
as live the next morning. The only path that ever worked was the
synchronous kill-switch, where update() runs inline.
Reporting completions instead of enqueues costs a poll's worth of
latency (the Vegas tick runs every ~4s) and is correct regardless of
which side of the queue the work lands on.
The before/after snapshots and the update pass itself are each
individually lock-protected against concurrent plugin_last_update
mutation (Vegas mode calls this from its own background
update-tick thread, racing the main render loop's plugin updates),
so callers get an atomic "who got fresh data" answer without
reaching into plugin_last_update themselves. The lock is not held
across the update pass so slow/blocking plugin update() calls don't
serialize against other plugin_last_update readers.
"""
with self._plugin_last_update_lock:
old_times = dict(self.plugin_last_update)
self.run_scheduled_updates(current_time)
return self.drain_completed_updates()
def _note_update_completed(self, plugin_id: str) -> None:
"""Record that a plugin's update() finished, for the next poll."""
with self._completed_updates_lock:
self._completed_updates.add(plugin_id)
def drain_completed_updates(self) -> List[str]:
"""Return and clear the plugin ids whose update() has since finished."""
with self._completed_updates_lock:
if not self._completed_updates:
return []
done = sorted(self._completed_updates)
self._completed_updates.clear()
return done
with self._plugin_last_update_lock:
return [
plugin_id for plugin_id, new_time in self.plugin_last_update.items()
if new_time > old_times.get(plugin_id, 0.0)
]
def update_all_plugins(self) -> None:
"""
@@ -1075,7 +1053,6 @@ class PluginManager:
if success:
with self._plugin_last_update_lock:
self.plugin_last_update[plugin_id] = time.time()
self._note_update_completed(plugin_id)
self.state_manager.record_update(plugin_id)
self.state_manager.set_state(plugin_id, PluginState.ENABLED)
else:
-182
View File
@@ -1,182 +0,0 @@
#!/usr/bin/env python3
"""
Tests that "which plugins have fresh data" survives the async update worker.
Regression under test: run_scheduled_updates_with_changes() snapshotted
plugin_last_update, called run_scheduled_updates(), and diffed the two. But
run_scheduled_updates() only *enqueues* -- the work runs on the update worker
and stamps the timestamp there, after the method has already returned. The
snapshots were therefore always identical and the result always empty.
Vegas depends on that result: it is what calls mark_plugin_updated(), which
drops the cached content for a plugin whose data changed. With it always
empty, a segment kept scrolling whatever it was first built from -- the
"last night's live game still drawn as live the next morning" failure the
coordinator comments describe. Observed on a live rig: zero update ticks in
twenty minutes, with weather, stocks and news all updating.
Run: python -m pytest test/test_update_change_reporting.py -v
"""
import ast
import inspect
import sys
import threading
import unittest
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from src.plugin_system.plugin_manager import PluginManager # noqa: E402
def _manager():
"""A PluginManager with only the update-reporting state initialised."""
manager = PluginManager.__new__(PluginManager)
manager._completed_updates = set()
manager._completed_updates_lock = threading.Lock()
return manager
class DrainCompletedUpdates(unittest.TestCase):
def setUp(self):
self.manager = _manager()
def test_nothing_completed_reports_nothing(self):
self.assertEqual(self.manager.drain_completed_updates(), [])
def test_a_completed_update_is_reported(self):
self.manager._note_update_completed("news")
self.assertEqual(self.manager.drain_completed_updates(), ["news"])
def test_draining_clears_so_the_next_poll_is_empty(self):
self.manager._note_update_completed("news")
self.manager.drain_completed_updates()
self.assertEqual(
self.manager.drain_completed_updates(), [],
"a plugin must be reported once per update, not on every poll, "
"or Vegas would drop its cached content every few seconds")
def test_repeated_completions_between_polls_collapse(self):
for _ in range(5):
self.manager._note_update_completed("weather")
self.assertEqual(self.manager.drain_completed_updates(), ["weather"])
def test_multiple_plugins_are_all_reported(self):
for plugin_id in ("news", "weather", "ledmatrix-stocks"):
self.manager._note_update_completed(plugin_id)
self.assertEqual(self.manager.drain_completed_updates(),
["ledmatrix-stocks", "news", "weather"])
class CompletionReportingIsAsyncSafe(unittest.TestCase):
"""The point of the change: completion may land after the call returns."""
def setUp(self):
self.manager = _manager()
def test_an_update_completing_after_the_call_is_still_reported(self):
"""The exact shape of the bug.
The enqueueing call sees nothing, because the worker has not run yet.
The next poll must report it -- under the old diff it was lost, since
the second snapshot was taken before the worker ever stamped.
"""
first = self.manager.drain_completed_updates()
self.assertEqual(first, [], "nothing has finished yet")
# The worker finishes some time later, on its own thread.
worker = threading.Thread(
target=self.manager._note_update_completed, args=("news",))
worker.start()
worker.join()
self.assertEqual(
self.manager.drain_completed_updates(), ["news"],
"an update that finishes between polls must still be reported")
def test_concurrent_completions_are_not_lost(self):
ids = ["plugin-%02d" % i for i in range(40)]
threads = [threading.Thread(target=self.manager._note_update_completed,
args=(pid,)) for pid in ids]
for thread in threads:
thread.start()
for thread in threads:
thread.join()
self.assertEqual(self.manager.drain_completed_updates(), sorted(ids))
def test_a_completion_during_a_drain_is_not_swallowed(self):
"""A drain must not clear an entry it did not report."""
self.manager._note_update_completed("news")
reported = self.manager.drain_completed_updates()
# ...worker finishes another one immediately afterwards
self.manager._note_update_completed("weather")
self.assertEqual(reported, ["news"])
self.assertEqual(self.manager.drain_completed_updates(), ["weather"])
class EveryStampRecordsACompletion(unittest.TestCase):
"""The ledger is only correct if the production paths actually fill it.
Asserting on the mechanics alone passes even when nothing calls
_note_update_completed -- verified by deleting the call sites, which the
behavioural tests above did not notice. This checks the invariant at the
source: wherever a successful update stamps plugin_last_update, it must
also record the completion, or Vegas silently stops being told.
"""
def test_success_paths_record_the_completion(self):
import src.plugin_system.plugin_manager as pm
tree = ast.parse(inspect.getsource(pm))
stamps = []
for node in ast.walk(tree):
if not isinstance(node, ast.With):
continue
# `with self._plugin_last_update_lock:` blocks that stamp a real
# time on success. Two stamps are deliberately excluded: the 0.0
# written at registration, and the failure path, which backs the
# timestamp off to space out retries -- neither means fresh data.
assigns_time = any(
isinstance(stmt, ast.Assign)
and any(isinstance(t, ast.Subscript)
and getattr(t.value, "attr", None) == "plugin_last_update"
for t in stmt.targets)
and not (isinstance(stmt.value, ast.Constant)
and stmt.value.value == 0.0)
and "failure" not in ast.dump(stmt.value)
for stmt in node.body
)
if assigns_time:
stamps.append(node)
self.assertGreaterEqual(
len(stamps), 2,
"expected the worker and inline success paths to stamp the time; "
"if this drops, the search below is looking at the wrong thing")
for stamp in stamps:
enclosing = self._enclosing_function(tree, stamp)
calls = [n for n in ast.walk(enclosing)
if isinstance(n, ast.Call)
and getattr(n.func, "attr", None) == "_note_update_completed"]
self.assertTrue(
calls,
"%s stamps plugin_last_update on success but never calls "
"_note_update_completed, so a plugin's fresh data would never "
"be reported and Vegas would keep its stale cached content"
% enclosing.name)
@staticmethod
def _enclosing_function(tree, target):
best = None
for node in ast.walk(tree):
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
if node.lineno <= target.lineno <= (node.end_lineno or node.lineno):
if best is None or node.lineno > best.lineno:
best = node
return best
if __name__ == "__main__":
unittest.main(verbosity=2)