feat(encode): native QSV backend — libvpl-sys + qsv.rs (Phases 0-3 of design/native-qsv-encoder.md)

Vendored MIT VPL dispatcher (static, trimmed tree, pin 674d015b/v2.17.0) built
via cmake+bindgen behind new feature 'qsv' (pf-encode + punktfunk-host forward).
qsv.rs: dispatcher session on the capture adapter (LUID-matched), SetHandle
D3D11, AsyncDepth=1/GopRefDist=1/VDEnc/CBR + HRD-off low-latency config,
GetSurfaceForEncode + GPU CopySubresourceRegion input (zero-copy, no readback
path), bounded sync-point poll, in-place reset with teardown escalation, no-IDR
bitrate retarget (Reset + StartNewSequence=OFF), 10-bit P010 HEVC-Main10/AV1,
HDR mastering/CLL SEI-OBU at IDR + BT.2020/PQ VSI, LTR-RFI via mfxExtRefListCtrl
(AMF slot policy port, Query-gated per codec, wire-index FrameOrder pinning).
Dispatch: native-first with ffmpeg fallback + PUNKTFUNK_QSV_FFMPEG hatch;
probes (can_encode_10bit / windows_codec_support / windows_backend_is_probed)
now answer natively for QSV.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

crates/libvpl-sys/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "libvpl-sys"
+description = "Vendored Intel VPL (libvpl) dispatcher built from source as a static archive + bindgen over the C API — substrate for the native QSV encoder backend (design/native-qsv-encoder.md). Upstream pin recorded in vendor/libvpl/PUNKTFUNK-VENDOR.txt; the tree builds with ONEVPL_EXPERIMENTAL, so bumping the pin re-opens the experimental-ABI check (§3.1)."
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+repository.workspace = true
+links = "vpl"
+
+[build-dependencies]
+# Same CMake-from-vendored-source model as pyrowave-sys/opus: reproducible
+# offline builds (CI, MSVC, flatpak) — no network, no system libvpl.
+cmake = "0.1"
+# Same bindgen configuration as pyrowave-sys (runtime = dlopen libclang).
+bindgen = { version = "0.72", features = ["runtime"], default-features = false }