Let the model say what a thing is and the watershed say where it ends

Local masking needs to know where an image's regions are. The watershed
spike (S15 arm A) found the boundaries but had no idea what any of them
enclosed; its coarse levels were geometric accidents. This adds the other
half and the thing that joins them.

`core/dr-segment` is where region reasoning now lives — the hierarchy moves
out of `dr-gpu`, which keeps only the pixel passes that are genuinely
shaders. The new crate is device-free and, without its default features,
model-free too: 20 of its tests need neither an adapter nor 11 MB of
weights.

Arm B runs YOLO26n-seg through `ort`. D13 framed inference as a choice
between `ort`'s C++ runtime and the pure-Rust dependency policy; that was a
false choice. `ort`'s `alternative-backend` feature unlinks the C entirely
and `ort-tract` supplies the API from tract, which is pure Rust. Measured
before committing to it: zero unsupported operators, 420 ms for 640x640,
and correct masks on bus.jpg. No NDK problem to solve, so D13's largest
tolerated exception is not needed.

Arm C is `prior.rs`, and it ships because the two arms fail in opposite
directions. Instance membership re-weights the merge saddles, so region
pairs the model believes share an object merge early and pairs straddling
its edge merge late. No boundary moves — only the order in which they
dissolve — which is how the result stays pixel-accurate at every level
while its coarse levels become named things.

Two things the spec assumed that turned out to be false, both recorded in
models/LICENCE.md: there is no usable ADE20K-trained YOLO, so the shipped
vocabulary is COCO's 80 subjects and *stuff* like sky and foliage must come
from arm A; and tract cannot parse a dynamic-shape export, so the graph's
input is fixed and tiling is the only route to more semantic resolution.

Weights are AGPL-3.0, which GPLv3 §13 permits and which makes the combined
work effectively AGPL. Deliberate, not accidental. They live in Git LFS,
and a build script fails with an instruction rather than embedding a
pointer file when the clone lacks them.

core/dr-segment/build.rs

@@ -0,0 +1,58 @@
+//! Check the model is a model and not an LFS pointer.
+//!
+//! `models/*.onnx` is stored in Git LFS (see `.gitattributes`). A clone made
+//! without git-lfs installed, or with `GIT_LFS_SKIP_SMUDGE` set, leaves a
+//! ~130-byte text pointer at that path instead of the weights.
+//!
+//! Without this check `include_bytes!` would happily embed the pointer, the
+//! crate would compile, and the failure would surface much later as an opaque
+//! ONNX parse error from inside tract — at which point the connection back to
+//! a missing `git lfs pull` is not one anybody would make quickly. Failing
+//! here costs one file read and turns that into a sentence.
+
+use std::path::Path;
+
+const MODEL: &str = "models/yolo26n-seg.onnx";
+
+fn main() {
+    println!("cargo:rerun-if-changed={MODEL}");
+    println!("cargo:rerun-if-changed=build.rs");
+
+    // Only the embedded path needs the file present; a build without it is
+    // watershed-only by choice and should not be blocked on weights.
+    if std::env::var_os("CARGO_FEATURE_EMBEDDED_MODEL").is_none() {
+        return;
+    }
+
+    let path = Path::new(MODEL);
+    let Ok(bytes) = std::fs::read(path) else {
+        panic!(
+            "\n\n{MODEL} is missing.\n\
+             It ships in Git LFS. Run `git lfs install && git lfs pull`, or build \
+             with `--no-default-features` for a watershed-only build.\n"
+        );
+    };
+
+    // ONNX is protobuf, which has no magic number; an LFS pointer is short
+    // ASCII beginning with a version URL. Testing for the pointer is the
+    // reliable direction — it has a known shape, where "valid protobuf" does
+    // not, and this check only has to catch the one failure that actually
+    // happens in practice.
+    if bytes.starts_with(b"version https://git-lfs") {
+        panic!(
+            "\n\n{MODEL} is a Git LFS pointer, not the model ({} bytes).\n\
+             Run `git lfs install && git lfs pull` to fetch the real file.\n",
+            bytes.len()
+        );
+    }
+
+    // A model that parses as a pointer-sized file is not one either. The real
+    // export is ~11 MB; anything under a megabyte is a truncated checkout.
+    if bytes.len() < 1_000_000 {
+        panic!(
+            "\n\n{MODEL} is only {} bytes — expected ~11 MB.\n\
+             The checkout looks incomplete; try `git lfs pull`.\n",
+            bytes.len()
+        );
+    }
+}