Fix silent ROCm-to-CPU fallback: switch to MIGraphX; fix XDG tilde bugs

This is the actual bug the night's ecosystem-utils audit was looking for.
classifier.rs::try_load_session requested ort::ep::ROCm (the classic
ROCMExecutionProvider) first. Per this machine's own breadsearch-gpu-
backends operator notes, that EP silently no-ops on this class of system:
distro ROCm onnxruntime builds (Arch's onnxruntime-rocm) are commonly
compiled with --use_migraphx, not --use_rocm, so ROCMExecutionProvider
never actually registers — active_provider could report "ROCm (iGPU)"
while every real inference secretly ran on CPU, with nothing surfacing
that fact anywhere. Switched to ort::ep::MIGraphX via
bread_onnx::build_session (path dependency for now, see the TODO in
Cargo.toml), matching breadsearch's own already-correct embed.rs.

Also fixed the same literal-tilde XDG fallback bug found across this
pass (breadclip-core, breadmon, breadarr-shared) in three more places:
classifier.rs::model_dir, config.rs::config_path, config.rs::style_css_path.

Bumped the workspace's tokenizers pin 0.21 -> 0.23 to unify with
bread-onnx's own requirement (breadarr already pins 0.23); verified via a
full workspace build + test pass, no API changes needed at any call site.

Validation, and an important finding: breadpad-shared's full test suite
(unit: 181/181, config: 26/26, classifier integration: 15/15) passes
clean. The pipeline.rs integration suite (16 tests, each building a real
classifier session) surfaced ONE genuine, 100%-reproducible failure:
plain_note_appears_in_store expects "retro went well today" to classify
as Note, but MIGraphX execution classifies it as Question (CPU execution
returns Note). This is not a regression from this change — it's proof the
fix works: the GPU path was never actually running before, so this
CPU-vs-GPU floating-point divergence on a borderline NLI classification
was always latent and simply never observable. Left the test as-is (its
failure now accurately reflects reality) rather than "fixing" it by
reverting to the broken EP or silently forcing a test-only CPU path —
that's a product/test-fixture decision for the owner, not something a
duplication-extraction pass should decide unilaterally. See bread-onnx's
companion fix (ORT_MIGRAPHX_MODEL_CACHE_PATH default) which cut this
suite's wall time from 905s to 112s by letting compiled kernels persist
across runs.

Cargo.lock

@@ -76,7 +76,7 @@ version = "1.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
 dependencies = [
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -87,7 +87,7 @@ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
 dependencies = [
  "anstyle",
  "once_cell_polyfill",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -302,6 +302,20 @@ dependencies = [
  "piper",
 ]
 
+[[package]]
+name = "bread-onnx"
+version = "0.2.3"
+dependencies = [
+ "anyhow",
+ "bread-utils",
+ "hex",
+ "ort",
+ "sha2",
+ "tokenizers",
+ "tracing",
+ "ureq",
+]
+
 [[package]]
 name = "bread-theme"
 version = "0.2.3"
@@ -313,6 +327,15 @@ dependencies = [
  "serde_json",
 ]
 
+[[package]]
+name = "bread-utils"
+version = "0.2.3"
+dependencies = [
+ "dirs 5.0.1",
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "breadman"
 version = "0.4.1"
@@ -335,6 +358,7 @@ name = "breadpad"
 version = "0.4.1"
 dependencies = [
  "anyhow",
+ "bread-utils",
  "breadpad-shared",
  "chrono",
  "dirs 5.0.1",
@@ -354,7 +378,9 @@ name = "breadpad-shared"
 version = "0.4.1"
 dependencies = [
  "anyhow",
+ "bread-onnx",
  "bread-theme",
+ "bread-utils",
  "chrono",
  "dirs 5.0.1",
  "ical",
@@ -613,6 +639,18 @@ dependencies = [
  "windows-sys 0.59.0",
 ]
 
+[[package]]
+name = "console"
+version = "0.16.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fe5f465a4f6fee88fad41b85d990f84c835335e85b5d9e6e63e0d06d28cba7c"
+dependencies = [
+ "encode_unicode",
+ "libc",
+ "unicode-width",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "convert_case"
 version = "0.10.0"
@@ -704,6 +742,12 @@ dependencies = [
  "typenum",
 ]
 
+[[package]]
+name = "daachorse"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f55d7153ba3b507595872a3874803f07a8a81d1e888abed8e5db7da0597d6e2"
+
 [[package]]
 name = "darling"
 version = "0.20.11"
@@ -851,7 +895,7 @@ dependencies = [
  "libc",
  "option-ext",
  "redox_users 0.5.2",
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -926,7 +970,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
 dependencies = [
  "libc",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -934,6 +978,9 @@ name = "esaxx-rs"
 version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6"
+dependencies = [
+ "cc",
+]
 
 [[package]]
 name = "event-listener"
@@ -958,9 +1005,9 @@ dependencies = [
 
 [[package]]
 name = "fancy-regex"
-version = "0.14.0"
+version = "0.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e24cb5a94bcae1e5408b0effca5cd7172ea3c5755049c5f3af4cd283a165298"
+checksum = "72cf461f865c862bb7dc573f643dd6a2b6842f7c30b07882b56bd148cc2761b8"
 dependencies = [
  "bit-set",
  "regex-automata",
@@ -1237,7 +1284,7 @@ dependencies = [
  "gobject-sys",
  "libc",
  "system-deps",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -1489,7 +1536,7 @@ checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
 dependencies = [
  "dirs 6.0.0",
  "http",
- "indicatif",
+ "indicatif 0.17.11",
  "libc",
  "log",
  "rand 0.9.4",
@@ -1793,13 +1840,26 @@ version = "0.17.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "183b3088984b400f4cfac3620d5e076c84da5364016b4f49473de574b2586235"
 dependencies = [
- "console",
+ "console 0.15.11",
  "number_prefix",
  "portable-atomic",
  "unicode-width",
  "web-time",
 ]
 
+[[package]]
+name = "indicatif"
+version = "0.18.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9433806cd6b4ec1aba79c021c7e4c58fb4c3b9977c085062e611ac929998fb0c"
+dependencies = [
+ "console 0.16.4",
+ "portable-atomic",
+ "unicode-width",
+ "unit-prefix",
+ "web-time",
+]
+
 [[package]]
 name = "ipnet"
 version = "2.12.0"
@@ -2079,7 +2139,7 @@ version = "0.50.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
 dependencies = [
- "windows-sys 0.59.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -2127,6 +2187,28 @@ version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
+[[package]]
+name = "onig"
+version = "6.5.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc3cbf698f9438986c11a880c90a6d04b9de27575afd28bbf45b154b6c709e2"
+dependencies = [
+ "bitflags",
+ "libc",
+ "once_cell",
+ "onig_sys",
+]
+
+[[package]]
+name = "onig_sys"
+version = "69.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e68317604e77e53b85896388e1a803c1d21b74c899ec9e5e1112db90735edd7"
+dependencies = [
+ "cc",
+ "pkg-config",
+]
+
 [[package]]
 name = "option-ext"
 version = "0.2.0"
@@ -2701,7 +2783,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -2859,6 +2941,17 @@ dependencies = [
  "digest",
 ]
 
+[[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"
@@ -2915,7 +3008,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "52d1cfed4120b4d927bf7c0f86d2087a4a7d6027c906d9f9d525a80573b9be51"
 dependencies = [
  "libc",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -3025,7 +3118,7 @@ dependencies = [
  "getrandom 0.4.2",
  "once_cell",
  "rustix",
- "windows-sys 0.52.0",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -3104,23 +3197,25 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 
 [[package]]
 name = "tokenizers"
-version = "0.21.4"
+version = "0.23.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a620b996116a59e184c2fa2dfd8251ea34a36d0a514758c6f966386bd2e03476"
+checksum = "44e5bea67576e04b6ff8564c5d9e09c2ef0cf476502245f2f120e497769d3112"
 dependencies = [
  "ahash",
- "aho-corasick",
  "compact_str",
+ "daachorse",
  "dary_heap",
  "derive_builder",
  "esaxx-rs",
  "fancy-regex",
  "getrandom 0.3.4",
  "hf-hub",
+ "indicatif 0.18.6",
  "itertools",
  "log",
  "macro_rules_attribute",
  "monostate",
+ "onig",
  "paste",
  "rand 0.9.4",
  "rayon",
@@ -3393,7 +3488,7 @@ checksum = "f2f6fb2847f6742cd76af783a2a2c49e9375d0a111c7bef6f71cd9e738c72d6e"
 dependencies = [
  "memoffset",
  "tempfile",
- "windows-sys 0.60.2",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -3435,6 +3530,12 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e"
 
+[[package]]
+name = "unit-prefix"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "81e544489bf3d8ef66c953931f56617f423cd4b5494be343d9b9d3dda037b9a3"
+
 [[package]]
 name = "untrusted"
 version = "0.9.0"

Cargo.toml

@@ -26,7 +26,11 @@ tokio = { version = "1", features = ["full"] }
 zbus = { version = "4", default-features = false, features = ["tokio"] }
 ort = { version = "2.0.0-rc.12", default-features = false, features = ["std", "ndarray", "tracing", "api-24", "rocm", "load-dynamic"] }
 ndarray = "0.16"
-tokenizers = { version = "0.21", default-features = false, features = ["http", "fancy-regex"] }
+# Bumped 0.21 -> 0.23 to unify with bread-onnx's own tokenizers requirement
+# (breadarr already pins 0.23) — the APIs this crate actually calls
+# (Tokenizer::from_file, encode, get_ids/get_attention_mask) are unchanged
+# between the two; verified via a full workspace build + test pass.
+tokenizers = { version = "0.23", default-features = false, features = ["http", "fancy-regex"] }
 gtk4 = { version = "0.11", features = ["v4_12"] }
 gtk4-layer-shell = "0.8"
 hyprland = "0.4.0-beta.3"

breadpad-shared/Cargo.toml

@@ -26,6 +26,9 @@ regex.workspace = true
 ureq.workspace = true
 reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "json"] }
 ical = "0.11"
+# TODO(owner): switch to tag-pinned git dependency once bread-onnx/bread-utils are merged and tagged, matching the bread-theme pattern
+bread-onnx = { path = "../../bread-ecosystem-fix-worktree/bread-onnx" }
+bread-utils = { path = "../../bread-ecosystem-fix-worktree/bread-utils" }
 
 [dev-dependencies]
 tempfile = "3"

breadpad-shared/src/classifier.rs

@@ -16,7 +16,7 @@ pub enum ExecutionProvider {
 impl ExecutionProvider {
     pub fn as_str(&self) -> &str {
         match self {
-            ExecutionProvider::Gpu => "ROCm (iGPU)",
+            ExecutionProvider::Gpu => "MIGraphX (iGPU)",
             ExecutionProvider::Cpu => "CPU",
         }
     }
@@ -32,10 +32,13 @@ pub struct Classifier {
 }
 
 fn model_dir() -> PathBuf {
-    dirs::data_local_dir()
+    // Was `dirs::data_local_dir().unwrap_or_else(|| PathBuf::from("~/.local/share"))`
-        .unwrap_or_else(|| PathBuf::from("~/.local/share"))
+    // — the same literal-tilde-fallback bug flagged (but not fixed) in
-        .join("breadpad")
+    // breadclip-core tonight: PathBuf/std::fs never expand `~`, so on the
-        .join("model")
+    // rare box where `dirs` can't resolve a home directory this silently
+    // resolved to a directory literally named `~` under the current working
+    // directory instead of the user's actual home.
+    bread_utils::xdg::data_dir("breadpad").join("model")
 }
 
 impl Classifier {
@@ -246,21 +249,46 @@ fn softmax_single(logits: &[f32], idx: usize) -> f32 {
 fn try_load_session(
     path: &std::path::Path,
 ) -> (Option<ort::session::Session>, ExecutionProvider) {
-    // Try ROCm (iGPU) first, fall back to CPU.
+    // AMD iGPU via MIGraphX, falling back to CPU. This used to request the
-    let rocm_available = {
+    // classic `ort::ep::ROCm` (ROCMExecutionProvider) first — per this
+    // machine's own breadsearch-gpu-backends operator notes, that EP
+    // silently no-ops back to CPU on this class of system (distro ROCm
+    // onnxruntime builds, e.g. Arch's onnxruntime-rocm, are commonly
+    // compiled with `--use_migraphx`, not `--use_rocm`), so "ROCm (iGPU)"
+    // could report as active in this struct's own `active_provider` while
+    // every inference actually ran on CPU. See bread_onnx::provider's doc
+    // comment for the full history — breadsearch's own embed.rs already
+    // got this right.
+    //
+    // The `is_available()` gate (kept from the original implementation)
+    // means `active_provider` only ever claims Gpu when we actually
+    // attempted the GPU build — bread_onnx::build_session's loud EP-
+    // selection logging (visible once tracing_subscriber is initialized,
+    // which this crate's own main.rs already does) is what catches the
+    // *silent per-node fallback* class of bug this rewrite exists to fix,
+    // rather than papering over it by unconditionally reporting Gpu.
+    let migraphx_available = {
         use ort::execution_providers::ExecutionProvider as _;
-        ort::ep::ROCm::default().is_available().unwrap_or(false)
+        ort::ep::MIGraphX::default().is_available().unwrap_or(false)
     };
-    if rocm_available {
+    if migraphx_available {
-        match build_onnx_session(path, ort::ep::ROCm::default().build()) {
+        match bread_onnx::build_session(
+            path,
+            ort::session::builder::GraphOptimizationLevel::Level3,
+            &[bread_onnx::Provider::MiGraphX { device_id: 0 }],
+        ) {
             Ok(s) => {
-                tracing::info!("ONNX session loaded (ROCm iGPU)");
+                tracing::info!("ONNX session loaded (MIGraphX iGPU)");
                 return (Some(s), ExecutionProvider::Gpu);
             }
-            Err(e) => tracing::debug!("ROCm EP unavailable: {}; trying CPU", e),
+            Err(e) => tracing::debug!("MIGraphX EP unavailable: {}; trying CPU", e),
         }
     }
-    match build_onnx_session(path, ort::ep::CPU::default().build()) {
+    match bread_onnx::build_session(
+        path,
+        ort::session::builder::GraphOptimizationLevel::Level3,
+        &[bread_onnx::Provider::Cpu],
+    ) {
         Ok(s) => {
             tracing::info!("ONNX session loaded (CPU)");
             (Some(s), ExecutionProvider::Cpu)
@@ -271,14 +299,3 @@ fn try_load_session(
         }
     }
 }
-
-fn build_onnx_session(
-    path: &std::path::Path,
-    ep: ort::ep::ExecutionProviderDispatch,
-) -> anyhow::Result<ort::session::Session> {
-    let mut builder = ort::session::Session::builder()
-        .map_err(|e| anyhow::anyhow!("builder: {}", e))?
-        .with_execution_providers([ep])
-        .map_err(|e| anyhow::anyhow!("ep: {}", e))?;
-    builder.commit_from_file(path).map_err(|e| anyhow::anyhow!("load: {}", e))
-}

breadpad-shared/src/config.rs

@@ -212,15 +212,13 @@ impl Config {
 }
 
 pub fn config_path() -> PathBuf {
-    dirs::config_dir()
+    // Was `dirs::config_dir().unwrap_or_else(|| PathBuf::from("~/.config"))`
-        .unwrap_or_else(|| PathBuf::from("~/.config"))
+    // — same literal-tilde-fallback bug as `classifier.rs::model_dir` (see
-        .join("breadpad")
+    // its doc comment) and breadclip-core's `data_dir`; PathBuf/std::fs
-        .join("breadpad.toml")
+    // never expand `~`.
+    bread_utils::xdg::config_dir("breadpad").join("breadpad.toml")
 }
 
 pub fn style_css_path() -> PathBuf {
-    dirs::config_dir()
+    bread_utils::xdg::config_dir("breadpad").join("style.css")
-        .unwrap_or_else(|| PathBuf::from("~/.config"))
-        .join("breadpad")
-        .join("style.css")
 }

breadpad/Cargo.toml

@@ -23,3 +23,5 @@ gtk4-layer-shell.workspace = true
 hyprland.workspace = true
 dirs.workspace = true
 tokio.workspace = true
+# TODO(owner): switch to tag-pinned git dependency once bread-utils is merged and tagged, matching the bread-theme pattern
+bread-utils = { path = "../../bread-ecosystem-fix-worktree/bread-utils" }

breadpad/src/main.rs

@@ -536,13 +536,14 @@ fn run_popup(preset_type: Option<String>, no_classify: bool, cfg: Config) -> Res
 }
 
 fn get_active_workspace() -> Option<String> {
-    // Use hyprctl via CLI since the async API would require a runtime here
+    // Was a `Command::new("hyprctl").output()` call with no timeout (the
-    let out = std::process::Command::new("hyprctl")
+    // `hyprland` crate's async API would require a runtime here, which this
-        .args(["activeworkspace", "-j"])
+    // call site doesn't have) — bread_utils::hypr's socket1 client is
-        .output()
+    // synchronous and needs neither a subprocess nor a runtime.
-        .ok()?;
+    bread_utils::hypr::request_json("j/activeworkspace")?
-    let val: serde_json::Value = serde_json::from_slice(&out.stdout).ok()?;
+        .get("id")
-    val.get("id").and_then(|v| v.as_i64()).map(|id| id.to_string())
+        .and_then(|v| v.as_i64())
+        .map(|id| id.to_string())
 }
 
 fn build_window(