Make the pipelining knobs config-file settable (server: section)

CPU_WORKERS / GPU_CONCURRENCY were env-only. Add a `server:` config
section (server.cpu_workers, server.gpu_concurrency) so a lane's
concurrency lives in its yaml alongside device/precision, matching how
model.device already works. Precedence mirrors BGFILTER_DEVICE: config is
the default, the env var overrides per box.

The pool + admission semaphore now build in lifespan (after the config
loads) instead of at import, and PipelineManager reads gpu_concurrency
from the settings. configs/gpu.yaml ships 8 / 2 (its target is the 32 GB
GPU boxes) with an inline VRAM caveat: gpu_concurrency>1 must fit
weights + N × forward, so keep it 1 on ≤16 GB cards.

Verified on a 4080 SUPER: startup logs cpu_workers=8 gpu_concurrency=2
from gpu.yaml with no env set, request returns a valid RGBA.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app.py

@@ -74,12 +74,13 @@ _manager: PipelineManager | None = None
 # overlap, while a GPU mutex inside the pipeline keeps the model forwards mutually
 # exclusive on the single device -- i.e. when one request steps off the GPU to do
 # CPU work, another steps on, keeping the GPU fed instead of idle.
-# BGFILTER_CPU_WORKERS=1 (default) gives a 1-thread pool == the old strictly serial
-# behaviour. A semaphore bounds in-flight requests (hence decoded-image RAM) to the
-# pool size so a burst cannot pile unbounded decoded images before the pool drains.
-CPU_WORKERS = max(1, _int_env("BGFILTER_CPU_WORKERS", 1))
-_executor = ThreadPoolExecutor(max_workers=CPU_WORKERS, thread_name_prefix="bgf")
-_sem = asyncio.Semaphore(CPU_WORKERS)
+# The pool size defaults to config (server.cpu_workers, default 1 == strictly serial)
+# and is overridable by BGFILTER_CPU_WORKERS. Both are resolved in lifespan once the
+# config is loaded; a same-sized semaphore bounds in-flight requests (hence
+# decoded-image RAM) so a burst cannot pile unbounded decoded images before the pool
+# drains.
+_executor: ThreadPoolExecutor | None = None
+_sem: asyncio.Semaphore | None = None
 
 
 def _build_settings():
@@ -105,15 +106,22 @@ def _build_settings():
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    global _manager
+    global _manager, _executor, _sem
     settings = _build_settings()
     preload = os.environ.get("BGFILTER_PRELOAD", "1").strip().lower() not in ("0", "false", "no", "")
+    # Pool size: config default (server.cpu_workers), env override wins.
+    cpu_workers = max(1, _int_env("BGFILTER_CPU_WORKERS", settings.server.cpu_workers))
+    _executor = ThreadPoolExecutor(max_workers=cpu_workers, thread_name_prefix="bgf")
+    _sem = asyncio.Semaphore(cpu_workers)
     logger.info(
-        "starting bgfilter service: device=%s default_seg=%s cross_check=%s preload=%s max_pixels=%d auth=%s",
+        "starting bgfilter service: device=%s default_seg=%s cross_check=%s preload=%s "
+        "cpu_workers=%d gpu_concurrency=%d max_pixels=%d auth=%s",
         settings.model.device,
         settings.segmentation.backend,
         settings.cross_check.enabled,
         preload,
+        cpu_workers,
+        max(1, _int_env("BGFILTER_GPU_CONCURRENCY", settings.server.gpu_concurrency)),
         MAX_IMAGE_PIXELS,
         "enabled" if AUTH_TOKEN else "DISABLED(open)",
     )