Separate OnlyOffice async handling, add office_previews WS flag, framed worker protocol

- Move OnlyOffice conversion out of worker subprocesses into async event loop
  using httpx.AsyncClient with shared client and clean shutdown hook
- Add OOConversionManager with in-flight deduplication (asyncio.Future) and
  configurable concurrency limit (OO_MAX_CONCURRENT=2)
- Add 10s total timeout for office previews via asyncio.wait_for
- Return 503 when OnlyOffice is unavailable, 504 on timeout
- Remove office handling from worker dispatch(); workers now only do
  images, video, and PDFs
- Replace PNG tempfile bridge with framed binary input protocol on worker
  stdin: (json_size)(data_size)(json)(raw_data)
- Add process_image_buffer() for in-memory AVIF conversion via pyvips
- Add office_previews to WS server message, cached every 30s from OO
  availability check
- Frontend gates only office document previews on office_previews flag;
  images, video, PDFs remain unconditional
- Change default OnlyOffice port from 8080 to 8988
This commit is contained in:
Leo Vasanko
2026-05-01 03:42:03 +00:00
parent cb954db537
commit 49cb4a8255
8 changed files with 396 additions and 91 deletions
+33 -6
View File
@@ -2,9 +2,12 @@
Two modes are supported:
1) Legacy one-shot mode: argv has path/quality/maxsize/maxzoom.
2) Long-lived mode: read JSONL commands from stdin and write framed responses.
2) Long-lived mode: read framed requests from stdin and write framed responses.
Framed response format:
Framed request format (stdin):
(uint32 json size)(uint32 data size)(json)(binary data)
Framed response format (stdout):
(blake3(packet))(uint32 json size)(uint32 payload size)(json)(binary payload)
where packet = (uint32 json size)(uint32 payload size)(json)(binary payload).
"""
@@ -40,6 +43,30 @@ _enc = msgspec.json.Encoder()
_dec_req = msgspec.json.Decoder(PreviewRequest)
def _read_exactly(f, n: int) -> bytes:
buf = b""
while len(buf) < n:
chunk = f.read(n - len(buf))
if not chunk:
raise EOFError
buf += chunk
return buf
def _read_request() -> tuple[PreviewRequest, bytes] | None:
try:
header = _read_exactly(sys.stdin.buffer, 8)
except EOFError:
return None
json_size, data_size = struct.unpack("<II", header)
meta_raw = _read_exactly(sys.stdin.buffer, json_size)
data = b""
if data_size:
data = _read_exactly(sys.stdin.buffer, data_size)
req = _dec_req.decode(meta_raw)
return req, data
def _write_response(resp: PreviewResponse, payload: bytes) -> None:
meta_bytes = _enc.encode(resp)
packet = struct.pack("<II", len(meta_bytes), len(payload)) + meta_bytes + payload
@@ -70,18 +97,18 @@ def _run_loop() -> None:
from cista.preview import dispatch
while True:
line = sys.stdin.buffer.readline()
if not line:
result = _read_request()
if result is None:
return
req, data = result
stderr_capture = io.StringIO()
handler = logging.StreamHandler(stderr_capture)
root_logger = logging.getLogger()
root_logger.addHandler(handler)
try:
with contextlib.redirect_stderr(stderr_capture):
req = _dec_req.decode(line)
result, resp = dispatch(
Path(req.path), req.quality, req.maxsize, req.maxzoom
Path(req.path), req.quality, req.maxsize, req.maxzoom, data
)
if not resp.ok:
captured = stderr_capture.getvalue().strip()