chore(hardening): tighten security and footprint defaults

crates/core/src/model_registry.rs

@@ -40,8 +40,8 @@ pub struct ModelFile {
     pub filename: &'static str,
     pub url: &'static str,
     pub size: Megabytes,
-    /// SHA256 hex digest for integrity verification. None to skip check.
-    pub sha256: Option<&'static str>,
+    /// SHA256 hex digest for integrity verification.
+    pub sha256: &'static str,
 }
 
 /// All metadata for a single downloadable model.
@@ -74,27 +74,27 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             files: vec![
                 ModelFile {
                     filename: "encoder-model.int8.onnx",
-                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/main/encoder-model.int8.onnx",
+                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/0bbb45a3365852604aef28b538a8f066f4ccaa85/encoder-model.int8.onnx",
                     size: Megabytes(620),
-                    sha256: None,
+                    sha256: "3e0581fda6ab843888b51e56d7ee78b6d5bc3237ec113af1f732d1d5286aa155",
                 },
                 ModelFile {
                     filename: "decoder_joint-model.int8.onnx",
-                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/main/decoder_joint-model.int8.onnx",
+                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/0bbb45a3365852604aef28b538a8f066f4ccaa85/decoder_joint-model.int8.onnx",
                     size: Megabytes(3),
-                    sha256: None,
+                    sha256: "a449f49acd68979d418651dd2dcb737cc0f1bf0225e009e29ee326354edbf7d3",
                 },
                 ModelFile {
                     filename: "nemo128.onnx",
-                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/main/nemo128.onnx",
+                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/0bbb45a3365852604aef28b538a8f066f4ccaa85/nemo128.onnx",
                     size: Megabytes(1),
-                    sha256: None,
+                    sha256: "a9fde1486ebfcc08f328d75ad4610c67835fea58c73ba57e3209a6f6cf019e9f",
                 },
                 ModelFile {
                     filename: "vocab.txt",
-                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/main/vocab.txt",
+                    url: "https://huggingface.co/istupakov/parakeet-tdt-0.6b-v2-onnx/resolve/0bbb45a3365852604aef28b538a8f066f4ccaa85/vocab.txt",
                     size: Megabytes(1),
-                    sha256: None,
+                    sha256: "ec182b70dd42113aff6c5372c75cac58c952443eb22322f57bbd7f53977d497d",
                 },
             ],
             description: "Fastest local model — near-instant transcription",
@@ -110,9 +110,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-tiny.en.bin",
-                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.en.bin",
+                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-tiny.en.bin",
                 size: Megabytes(75),
-                sha256: None,
+                sha256: "921e4cf8686fdd993dcd081a5da5b6c365bfde1162e72b08d75ac75289920b1f",
             }],
             description: "Bundled with app — works instantly",
         },
@@ -127,9 +127,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-base.en.bin",
-                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin",
+                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-base.en.bin",
                 size: Megabytes(142),
-                sha256: None,
+                sha256: "a03779c86df3323075f5e796cb2ce5029f00ec8869eee3fdfb897afe36c6d002",
             }],
             description: "Good balance of speed and accuracy",
         },
@@ -144,9 +144,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-small.en.bin",
-                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en.bin",
+                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-small.en.bin",
                 size: Megabytes(466),
-                sha256: None,
+                sha256: "c6138d6d58ecc8322097e0f987c32f1be8bb0a18532a3f88f734d1bbf9c41e5d",
             }],
             description: "Accuracy-first English transcription",
         },
@@ -161,9 +161,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-distil-small.en.bin",
-                url: "https://huggingface.co/distil-whisper/distil-small.en/resolve/main/ggml-distil-small.en.bin",
+                url: "https://huggingface.co/distil-whisper/distil-small.en/resolve/9e4a67ca4569c30be43a3fe7fba1621e504f0093/ggml-distil-small.en.bin",
                 size: Megabytes(336),
-                sha256: None,
+                sha256: "7691eb11167ab7aaf6b3e05d8266f2fd9ad89c550e433f86ac266ebdee6c970a",
             }],
             description: "Small accuracy, ~6\u{00d7} faster — distilled variant",
         },
@@ -178,9 +178,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-medium.en.bin",
-                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.en.bin",
+                url: "https://huggingface.co/ggerganov/whisper.cpp/resolve/5359861c739e955e79d9a303bcbc70fb988958b1/ggml-medium.en.bin",
                 size: Megabytes(1500),
-                sha256: None,
+                sha256: "cc37e93478338ec7700281a7ac30a10128929eb8f427dda2e865faa8f6da4356",
             }],
             description: "Best Whisper accuracy — needs 4+ GB RAM",
         },
@@ -195,9 +195,9 @@ static ALL_MODELS: LazyLock<Vec<ModelEntry>> = LazyLock::new(|| {
             languages: LanguageSupport::EnglishOnly,
             files: vec![ModelFile {
                 filename: "ggml-distil-large-v3.bin",
-                url: "https://huggingface.co/distil-whisper/distil-large-v3-ggml/resolve/main/ggml-distil-large-v3.bin",
+                url: "https://huggingface.co/distil-whisper/distil-large-v3-ggml/resolve/0d78dd96ed9fc152325f63b53788fec3b43de031/ggml-distil-large-v3.bin",
                 size: Megabytes(1550),
-                sha256: None,
+                sha256: "2883a11b90fb10ed592d826edeaee7d2929bf1ab985109fe9e1e7b4d2b69a298",
             }],
             description: "Near large-v3 accuracy at ~6\u{00d7} the speed",
         },
@@ -213,3 +213,35 @@ pub fn all_models() -> &'static [ModelEntry] {
 pub fn find_model(id: &ModelId) -> Option<&'static ModelEntry> {
     ALL_MODELS.iter().find(|m| &m.id == id)
 }
+
+#[cfg(test)]
+mod tests {
+    use super::all_models;
+
+    #[test]
+    fn every_model_file_has_sha256_and_pinned_url() {
+        for model in all_models() {
+            for file in &model.files {
+                assert_eq!(
+                    file.sha256.len(),
+                    64,
+                    "{} / {} must carry a SHA256 digest",
+                    model.id,
+                    file.filename
+                );
+                assert!(
+                    file.sha256.chars().all(|c| c.is_ascii_hexdigit()),
+                    "{} / {} SHA256 must be hex",
+                    model.id,
+                    file.filename
+                );
+                assert!(
+                    !file.url.contains("/resolve/main/"),
+                    "{} / {} must pin a Hugging Face revision",
+                    model.id,
+                    file.filename
+                );
+            }
+        }
+    }
+}