Migrate embedding pipeline and model download to bread-onnx

OrtEmbedder's tokenize -> tensor build -> mean-pool -> L2-normalize
pipeline was near-byte-identical to breadmill's own OrtEmbedder (same
truncation, same actual_seq.min(mask.len()) padding guard, same 1e-10
epsilon) — now both share bread_onnx::embedding::EmbeddingSession (path
dependency for now, see the TODO in breadarrd/Cargo.toml). This crate
stays CPU-only (Provider::Cpu), matching its existing documented rationale.

ensure_model's reqwest-based download function is replaced with
bread_onnx::download::ensure_file (sync/ureq, matching breadmill's own
downloader and this workspace's bakery convention) dispatched via
spawn_blocking from this async context.

Builds and tests clean across the whole breadarr workspace: 205 passed, 1
pre-existing network-dependent test ignored, 0 failed.

Cargo.lock

@@ -2,6 +2,12 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
+
 [[package]]
 name = "ahash"
 version = "0.8.12"
@@ -160,6 +166,38 @@ version = "2.13.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4388bee8683e3d04af747c73422af53102d2bd24d9eadb6cbc100baef4b43f8"
 
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "bread-onnx"
+version = "0.2.3"
+dependencies = [
+ "anyhow",
+ "bread-utils",
+ "hex",
+ "ort",
+ "sha2",
+ "tokenizers",
+ "tracing",
+ "ureq 2.12.1",
+]
+
+[[package]]
+name = "bread-utils"
+version = "0.2.3"
+dependencies = [
+ "dirs",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "breadarr-shared"
 version = "0.1.0"
@@ -192,6 +230,7 @@ dependencies = [
  "anyhow",
  "async-trait",
  "axum",
+ "bread-onnx",
  "breadarr-shared",
  "chrono",
  "fastrand",
@@ -375,6 +414,24 @@ version = "0.8.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
 
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
+dependencies = [
+ "cfg-if",
+]
+
 [[package]]
 name = "crossbeam-deque"
 version = "0.8.7"
@@ -425,6 +482,16 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
 [[package]]
 name = "cssparser"
 version = "0.31.2"
@@ -590,6 +657,37 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
+[[package]]
+name = "dirs"
+version = "5.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
+dependencies = [
+ "dirs-sys",
+]
+
+[[package]]
+name = "dirs-sys"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
+dependencies = [
+ "libc",
+ "option-ext",
+ "redox_users",
+ "windows-sys 0.48.0",
+]
+
 [[package]]
 name = "displaydoc"
 version = "0.2.6"
@@ -701,6 +799,16 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
 
+[[package]]
+name = "flate2"
+version = "1.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -795,6 +903,16 @@ dependencies = [
  "byteorder",
 ]
 
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
 [[package]]
 name = "getopts"
 version = "0.2.24"
@@ -898,6 +1016,12 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
+[[package]]
+name = "hex"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
+
 [[package]]
 name = "hmac-sha256"
 version = "1.1.14"
@@ -1272,6 +1396,15 @@ version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
 
+[[package]]
+name = "libredox"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c943259e342f1e06ff2da7a83eabdfe7f92ce10262688dbf1895ff0b3e6e4652"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "libsqlite3-sys"
 version = "0.28.0"
@@ -1426,6 +1559,16 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
+[[package]]
+name = "miniz_oxide"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
+dependencies = [
+ "adler2",
+ "simd-adler32",
+]
+
 [[package]]
 name = "mio"
 version = "1.2.1"
@@ -1633,6 +1776,12 @@ dependencies = [
  "vcpkg",
 ]
 
+[[package]]
+name = "option-ext"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d"
+
 [[package]]
 name = "ort"
 version = "2.0.0-rc.12"
@@ -1643,7 +1792,7 @@ dependencies = [
  "ort-sys",
  "smallvec",
  "tracing",
- "ureq",
+ "ureq 3.3.0",
 ]
 
 [[package]]
@@ -1654,7 +1803,7 @@ checksum = "d7b497d21a8b6fbb4b5a544f8fadb77e801a09ae0add9e411d31c6f89e3c1e90"
 dependencies = [
  "hmac-sha256",
  "lzma-rust2",
- "ureq",
+ "ureq 3.3.0",
 ]
 
 [[package]]
@@ -2029,6 +2178,17 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "redox_users"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
+dependencies = [
+ "getrandom 0.2.17",
+ "libredox",
+ "thiserror 1.0.69",
+]
+
 [[package]]
 name = "regex"
 version = "1.13.0"
@@ -2162,7 +2322,9 @@ version = "0.23.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6b92b125634d9b795e7beca796cc790df15a7fb38323bf3196fda83292d06b1f"
 dependencies = [
+ "log",
  "once_cell",
+ "ring",
  "rustls-pki-types",
  "rustls-webpki",
  "subtle",
@@ -2358,6 +2520,17 @@ dependencies = [
  "stable_deref_trait",
 ]
 
+[[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
 [[package]]
 name = "sharded-slab"
 version = "0.1.7"
@@ -2404,6 +2577,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "simd-adler32"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a219298ac11a56ea9a6d2120044824d6f01aeb034955e7af7bc16858527deea"
+
 [[package]]
 name = "siphasher"
 version = "0.3.11"
@@ -2608,13 +2787,33 @@ dependencies = [
  "utf-8",
 ]
 
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -2705,7 +2904,7 @@ dependencies = [
  "serde",
  "serde_json",
  "spm_precompiled",
- "thiserror",
+ "thiserror 2.0.18",
  "unicode-normalization-alignments",
  "unicode-segmentation",
  "unicode_categories",
@@ -2927,6 +3126,12 @@ version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
 
+[[package]]
+name = "typenum"
+version = "1.20.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6f5e870be6c3b371b77fe0ee0bafb859fa4964b4404c27de1d380043c4dda20"
+
 [[package]]
 name = "unicase"
 version = "2.9.0"
@@ -2995,6 +3200,24 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
 
+[[package]]
+name = "ureq"
+version = "2.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02d1a66277ed75f640d608235660df48c8e3c19f3b4edb6a263315626cc3c01d"
+dependencies = [
+ "base64 0.22.1",
+ "flate2",
+ "log",
+ "once_cell",
+ "rustls",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "url",
+ "webpki-roots 0.26.11",
+]
+
 [[package]]
 name = "ureq"
 version = "3.3.0"
@@ -3181,6 +3404,24 @@ dependencies = [
  "rustls-pki-types",
 ]
 
+[[package]]
+name = "webpki-roots"
+version = "0.26.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "521bc38abb08001b01866da9f51eb7c5d647a19260e00054a8c7fd5f9e57f7a9"
+dependencies = [
+ "webpki-roots 1.0.8",
+]
+
+[[package]]
+name = "webpki-roots"
+version = "1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf85cb06032201fa7c6f829d7db5a7e5aa45bcc0655327713065f6f0576731bf"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "winapi"
 version = "0.3.9"
@@ -3273,13 +3514,22 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-sys"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
+dependencies = [
+ "windows-targets 0.48.5",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -3288,7 +3538,7 @@ version = "0.59.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -3300,34 +3550,67 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-targets"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
+]
+
 [[package]]
 name = "windows-targets"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
 dependencies = [
- "windows_aarch64_gnullvm",
+ "windows_aarch64_gnullvm 0.52.6",
- "windows_aarch64_msvc",
+ "windows_aarch64_msvc 0.52.6",
- "windows_i686_gnu",
+ "windows_i686_gnu 0.52.6",
  "windows_i686_gnullvm",
- "windows_i686_msvc",
+ "windows_i686_msvc 0.52.6",
- "windows_x86_64_gnu",
+ "windows_x86_64_gnu 0.52.6",
- "windows_x86_64_gnullvm",
+ "windows_x86_64_gnullvm 0.52.6",
- "windows_x86_64_msvc",
+ "windows_x86_64_msvc 0.52.6",
 ]
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.6"
@@ -3340,24 +3623,48 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.6"

breadarrd/Cargo.toml

@@ -19,6 +19,8 @@ regex.workspace = true
 serde_json.workspace = true
 ort.workspace = true
 tokenizers.workspace = true
+# TODO(owner): switch to tag-pinned git dependency once bread-onnx is merged and tagged, matching the bread-theme pattern
+bread-onnx = { path = "../../bread-ecosystem-fix-worktree/bread-onnx" }
 scraper.workspace = true
 chrono.workspace = true
 fastrand.workspace = true

breadarrd/src/matcher/embed.rs

@@ -1,10 +1,8 @@
 use std::path::Path;
 
 use anyhow::Result;
-use ort::session::builder::GraphOptimizationLevel;
+use bread_onnx::embedding::EmbeddingSession;
-use ort::session::Session;
+use bread_onnx::Provider;
-use ort::value::Tensor;
-use tokenizers::Tokenizer;
 
 /// all-MiniLM-L6-v2's trained max sequence length. Release/show titles are
 /// always far shorter than this, but truncate defensively rather than let a
@@ -12,9 +10,7 @@ use tokenizers::Tokenizer;
 const MAX_SEQ_LEN: usize = 256;
 
 pub struct OrtEmbedder {
-    session: Session,
+    inner: EmbeddingSession,
-    tokenizer: Tokenizer,
-    dim: usize,
 }
 
 impl OrtEmbedder {
@@ -23,130 +19,24 @@ impl OrtEmbedder {
     /// MiniLM-class model is cheap enough on CPU that a multi-backend GPU
     /// setup isn't worth the added complexity for a model this small.
     pub fn load(model_path: &Path, tokenizer_path: &Path, dim: usize) -> Result<Self> {
-        let session = Session::builder()
+        let inner = EmbeddingSession::load(model_path, tokenizer_path, dim, MAX_SEQ_LEN, &[Provider::Cpu])?;
-            .map_err(|e| anyhow::anyhow!("failed to create ort session builder: {e}"))?
+        Ok(Self { inner })
-            .with_optimization_level(GraphOptimizationLevel::Level3)
-            .map_err(|e| anyhow::anyhow!("failed to set optimization level: {e}"))?
-            .commit_from_file(model_path)
-            .map_err(|e| {
-                anyhow::anyhow!("failed to load model from {}: {e}", model_path.display())
-            })?;
-
-        let tokenizer = Tokenizer::from_file(tokenizer_path)
-            .map_err(|e| anyhow::anyhow!("failed to load tokenizer: {e}"))?;
-
-        Ok(Self {
-            session,
-            tokenizer,
-            dim,
-        })
     }
 
     pub fn embed(&mut self, text: &str) -> Result<Vec<f32>> {
-        let encoding = self
+        self.inner.embed(text)
-            .tokenizer
-            .encode(text, true)
-            .map_err(|e| anyhow::anyhow!("tokenization failed: {e}"))?;
-
-        let mut ids: Vec<i64> = encoding.get_ids().iter().map(|&x| x as i64).collect();
-        let mut mask: Vec<i64> = encoding
-            .get_attention_mask()
-            .iter()
-            .map(|&x| x as i64)
-            .collect();
-        let mut type_ids: Vec<i64> = encoding.get_type_ids().iter().map(|&x| x as i64).collect();
-
-        ids.truncate(MAX_SEQ_LEN);
-        mask.truncate(MAX_SEQ_LEN);
-        type_ids.truncate(MAX_SEQ_LEN);
-
-        let seq_len = ids.len() as i64;
-        let id_tensor = Tensor::<i64>::from_array((vec![1i64, seq_len], ids))
-            .map_err(|e| anyhow::anyhow!("failed to build input_ids tensor: {e}"))?;
-        let mask_tensor = Tensor::<i64>::from_array((vec![1i64, seq_len], mask.clone()))
-            .map_err(|e| anyhow::anyhow!("failed to build attention_mask tensor: {e}"))?;
-        let type_tensor = Tensor::<i64>::from_array((vec![1i64, seq_len], type_ids))
-            .map_err(|e| anyhow::anyhow!("failed to build token_type_ids tensor: {e}"))?;
-
-        let outputs = self
-            .session
-            .run(ort::inputs! {
-                "input_ids" => id_tensor,
-                "attention_mask" => mask_tensor,
-                "token_type_ids" => type_tensor,
-            })
-            .map_err(|e| anyhow::anyhow!("ort inference failed: {e}"))?;
-
-        let (shape, data) = outputs["last_hidden_state"]
-            .try_extract_tensor::<f32>()
-            .map_err(|e| anyhow::anyhow!("failed to extract last_hidden_state: {e}"))?;
-
-        let actual_seq = shape[1] as usize;
-        let actual_dim = shape[2] as usize;
-
-        // Mean-pool over non-padded positions only.
-        let mut result = vec![0.0f32; actual_dim];
-        let mut count = 0usize;
-        for t in 0..actual_seq.min(mask.len()) {
-            if mask[t] > 0 {
-                for d in 0..actual_dim {
-                    result[d] += data[t * actual_dim + d];
-                }
-                count += 1;
-            }
-        }
-        if count > 0 {
-            for x in &mut result {
-                *x /= count as f32;
     }
 }
 
-        l2_normalize(&mut result);
+pub use bread_onnx::embedding::cosine_similarity;
-        result.truncate(self.dim);
-        while result.len() < self.dim {
-            result.push(0.0);
-        }
-
-        Ok(result)
-    }
-}
-
-fn l2_normalize(v: &mut [f32]) {
-    let norm: f32 = v.iter().map(|x| x * x).sum::<f32>().sqrt();
-    if norm > 1e-10 {
-        for x in v.iter_mut() {
-            *x /= norm;
-        }
-    }
-}
-
-pub fn cosine_similarity(a: &[f32], b: &[f32]) -> f32 {
-    a.iter().zip(b).map(|(x, y)| x * y).sum()
-}
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
-    #[test]
-    fn l2_normalize_produces_unit_vector() {
-        let mut v = vec![3.0, 4.0];
-        l2_normalize(&mut v);
-        let norm: f32 = v.iter().map(|x| x * x).sum::<f32>().sqrt();
-        assert!((norm - 1.0).abs() < 1e-6);
-    }
-
-    #[test]
-    fn l2_normalize_leaves_zero_vector_untouched() {
-        let mut v = vec![0.0, 0.0, 0.0];
-        l2_normalize(&mut v);
-        assert_eq!(v, vec![0.0, 0.0, 0.0]);
-    }
-
     #[test]
     fn cosine_similarity_of_identical_unit_vectors_is_one() {
-        let mut v = vec![1.0, 2.0, 3.0];
+        let v = vec![0.6, 0.8]; // already unit length
-        l2_normalize(&mut v);
         let sim = cosine_similarity(&v, &v);
         assert!((sim - 1.0).abs() < 1e-6);
     }

breadarrd/src/matcher/mod.rs

@@ -16,6 +16,13 @@ const TOKENIZER_URL: &str =
 /// Downloads the embedding model into `model_dir` if it isn't already
 /// there — keeps setup to "run the daemon," no separate fetch step, in
 /// keeping with the project's minimal-setup goal.
+///
+/// `bread_onnx::download::ensure_file` is sync/blocking (`ureq`, matching
+/// this workspace's `bakery` download convention) — this used to be a
+/// `reqwest`-based async implementation local to this crate, genuinely
+/// duplicating breadmill's own sync/`ureq` downloader. Since this fn is
+/// called from an async context, each call is dispatched via
+/// `spawn_blocking` rather than blocking the async runtime directly.
 pub async fn ensure_model(model_dir: &Path) -> Result<(PathBuf, PathBuf)> {
     std::fs::create_dir_all(model_dir)
         .with_context(|| format!("failed to create {}", model_dir.display()))?;
@@ -25,28 +32,19 @@ pub async fn ensure_model(model_dir: &Path) -> Result<(PathBuf, PathBuf)> {
 
     if !model_path.exists() {
         tracing::info!("downloading title-matching model (~90MB, one-time)");
-        download(MODEL_URL, &model_path).await?;
+        download(MODEL_URL, model_path.clone()).await?;
     }
     if !tokenizer_path.exists() {
-        download(TOKENIZER_URL, &tokenizer_path).await?;
+        download(TOKENIZER_URL, tokenizer_path.clone()).await?;
     }
 
     Ok((model_path, tokenizer_path))
 }
 
-async fn download(url: &str, dest: &Path) -> Result<()> {
+async fn download(url: &'static str, dest: PathBuf) -> Result<()> {
-    let bytes = reqwest::get(url)
+    tokio::task::spawn_blocking(move || bread_onnx::download::ensure_file(url, &dest, None))
         .await
-        .with_context(|| format!("failed to download {url}"))?
+        .context("download task panicked")??;
-        .error_for_status()
-        .with_context(|| format!("{url} returned an error status"))?
-        .bytes()
-        .await
-        .with_context(|| format!("failed to read response body from {url}"))?;
-    let tmp = dest.with_extension("part");
-    std::fs::write(&tmp, &bytes).with_context(|| format!("failed to write {}", tmp.display()))?;
-    std::fs::rename(&tmp, dest)
-        .with_context(|| format!("failed to finalize {}", dest.display()))?;
     Ok(())
 }