fix: keep callback faults out of the frame-decode fallback

Review follow-up on the previous two commits.

Widening the control-message except tuple put the callback dispatch
inside it, so an _on_new_cycle() that raised ValueError, TypeError or
AttributeError sent a perfectly good control packet to the legacy PNG
decoder -- which reported it as an image decode error and buried the
real fault. Split the two: whether the payload parses as JSON decides
frame vs control message, a second guard covers reading the fields of an
attacker-shaped body, and the callback fires outside both. It still
cannot kill the receive thread; the loop's own handler catches it, and
now says what actually went wrong.

The logo download's temp file was a fixed "<name>.part". Two plugins
asking for the same logo at once would interleave writes into it,
publish the mixture, or delete each other's partial. mkstemp gives each
download its own name in the same directory, so os.replace stays atomic.
Its descriptor is adopted by fdopen before the request runs, since a
request that raises before the write would otherwise leak the fd --
quietly, because load_logo_with_download swallows that.

Two test fixes: the oversized-frame test replaced PIL.Image.open
process-wide, the same hazard the clock helper documents, and Ruff B007
on an unused loop variable.

Full suite: 3355 passed, coverage 54%.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NohXi78cwsAKtN1sCfxjUh
This commit is contained in:
Claude
2026-08-14 13:13:32 +00:00
parent a653368250
commit bdf4d25c47
4 changed files with 125 additions and 40 deletions
+16 -5
View File
@@ -7,6 +7,7 @@ Extracted from LEDMatrix core to provide reusable functionality for plugins.
import logging
import os
import tempfile
from pathlib import Path
from typing import Dict, List, Optional, Union
@@ -283,12 +284,22 @@ class LogoHelper:
# Ensure directory exists with proper permissions
ensure_directory_permissions(file_path.parent, get_assets_dir_mode())
tmp_path = file_path.with_name(file_path.name + '.part')
# A unique temp name, not a fixed "<name>.part": two plugins can
# ask for the same logo at once, and a shared name would let them
# interleave writes into one file, publish the mixture, or delete
# each other's partial. Same directory, so os.replace stays atomic.
fd, tmp_name = tempfile.mkstemp(
dir=str(file_path.parent), prefix=file_path.name + '.', suffix='.part')
tmp_path = Path(tmp_name)
try:
with self.session.get(url, timeout=30, stream=True) as response:
response.raise_for_status()
downloaded = 0
with open(tmp_path, 'wb') as f:
# fdopen outermost so the descriptor mkstemp handed back is
# always adopted and closed, including when the request itself
# raises — load_logo_with_download swallows that, so a leak
# here would accumulate quietly on a URL that keeps failing.
with os.fdopen(fd, 'wb') as f:
with self.session.get(url, timeout=30, stream=True) as response:
response.raise_for_status()
downloaded = 0
for chunk in response.iter_content(chunk_size=64 * 1024):
if not chunk:
continue
+43 -33
View File
@@ -495,13 +495,43 @@ class DisplaySyncManager:
except Exception as exc:
self.logger.debug("Sync: frame decode error: %s", exc)
else:
# No magic prefix: try control-message JSON, and treat a
# parse failure as a legacy (pre-magic) PNG frame. Both
# wire formats are self-describing, so no size heuristic
# is needed — a >512-byte control message used to be
# misrouted into image decode and silently dropped.
# No magic prefix. Whether the payload parses as JSON
# decides between a control message and a legacy
# (pre-magic) PNG frame — both wire formats are
# self-describing, so no size heuristic is needed. A
# >512-byte control message used to be misrouted into
# image decode and silently dropped.
try:
msg = json.loads(data.decode("utf-8"))
except (json.JSONDecodeError, UnicodeDecodeError):
# Not JSON — try a legacy PNG frame.
try:
img = Image.open(io.BytesIO(data))
if img.width > _MAX_FRAME_W or img.height > _MAX_FRAME_H:
# Same cap the TCP image path applies: decode
# is deferred until load(), so check first.
self.logger.debug(
"Sync: rejected oversized legacy frame %dx%d from %s",
img.width, img.height, sender_ip,
)
continue
img.load()
self._handle_received_frame(img, sender_ip)
except Exception as exc:
self.logger.debug("Sync: frame decode error: %s", exc)
continue
# It parsed, so it is a control message and never a
# frame. Read and validate its fields under a guard —
# a UDP payload is attacker-shaped, so a non-object
# body makes .get() raise AttributeError and an "sx"
# carrying a non-numeric x raises ValueError/TypeError
# — but dispatch the callback *outside* it. Running
# the callback in here would let a fault in someone
# else's code read as a malformed packet and be
# logged as one.
fire_new_cycle = False
try:
t = msg.get("t")
if t == "hello_ack":
self._leader_ip = sender_ip
@@ -525,36 +555,16 @@ class DisplaySyncManager:
sender_ip,
)
self.write_status_file()
if self._on_new_cycle:
self._on_new_cycle() # build initial scroll image
fire_new_cycle = True # build initial scroll image
elif t == "nc":
# Leader started a new scroll cycle — rebuild local image
if self._on_new_cycle:
self._on_new_cycle()
except (json.JSONDecodeError, UnicodeDecodeError, KeyError,
AttributeError, TypeError, ValueError):
# Not a control message — try legacy PNG frame.
# The tuple is wide because a UDP payload is
# attacker-shaped: valid-but-non-object JSON makes
# msg.get() raise AttributeError, and an "sx" with a
# non-numeric x raises ValueError/TypeError from
# float(). Those must land here, not in the outer
# handler, which would skip this fallback and pay
# the error backoff for one malformed packet.
try:
img = Image.open(io.BytesIO(data))
if img.width > _MAX_FRAME_W or img.height > _MAX_FRAME_H:
# Same cap the TCP image path applies: decode
# is deferred until load(), so check first.
self.logger.debug(
"Sync: rejected oversized legacy frame %dx%d from %s",
img.width, img.height, sender_ip,
)
continue
img.load()
self._handle_received_frame(img, sender_ip)
except Exception as exc:
self.logger.debug("Sync: frame decode error: %s", exc)
fire_new_cycle = True
except (KeyError, AttributeError, TypeError, ValueError) as exc:
self.logger.debug("Sync: malformed control message: %s", exc)
continue
if fire_new_cycle and self._on_new_cycle:
self._on_new_cycle()
except socket.timeout:
continue