Add comprehensive AI test dataset and CI/CD improvements

.gitattributes

@@ -0,0 +1 @@
+tests/fixtures/*.mp4 filter=lfs diff=lfs merge=lfs -text

.github/workflows/ci.yml

@@ -10,7 +10,19 @@ env:
   CARGO_TERM_COLOR: always
 
 jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: clippy, rustfmt
+      - uses: Swatinem/rust-cache@v2
+      - run: cargo fmt -- --check
+      - run: cargo clippy -- -D warnings
+
   test:
+    needs: lint
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
@@ -19,11 +31,42 @@ jobs:
       - uses: actions/checkout@v4
         with:
           lfs: true
+
+      - name: Validate LFS fixtures
+        run: |
+          for f in tests/fixtures/*.mp4; do
+            [ ! -f "$f" ] && continue
+            size=$(wc -c < "$f")
+            if [ "$size" -lt 1000 ]; then
+              echo "ERROR: $f appears to be an LFS pointer (${size} bytes)"
+              exit 1
+            fi
+          done
+
       - uses: dtolnay/rust-toolchain@stable
-        with:
-          components: clippy, rustfmt
       - uses: Swatinem/rust-cache@v2
-      - run: cargo fmt -- --check
-      - run: cargo clippy -- -D warnings
+
+      - name: Install ffmpeg (Ubuntu)
+        if: runner.os == 'Linux'
+        run: sudo apt-get update && sudo apt-get install -y ffmpeg
+
+      - name: Install ffmpeg (macOS)
+        if: runner.os == 'macOS'
+        run: brew install ffmpeg
+
       - run: cargo test
       - run: cargo build --release
+
+  test-deep:
+    needs: lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          lfs: true
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: Swatinem/rust-cache@v2
+      - name: Install ffmpeg
+        run: sudo apt-get update && sudo apt-get install -y ffmpeg
+      - name: Run deep detection tests
+        run: cargo test -- --ignored

tests/audio_detection.rs

@@ -0,0 +1,75 @@
+use assert_cmd::cargo_bin_cmd;
+use predicates::prelude::*;
+
+// --- Suno 2 (ID3 + Filename, MEDIUM) ---
+
+#[test]
+fn suno_2_detected_via_id3() {
+    cargo_bin_cmd!("aic")
+        .args(["--lang", "en", "check", "tests/fixtures/ai_suno_2.mp3"])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("ID3"))
+        .stdout(predicate::str::contains("suno"));
+}
+
+#[test]
+fn suno_2_json_output() {
+    cargo_bin_cmd!("aic")
+        .args([
+            "--lang",
+            "en",
+            "--json",
+            "check",
+            "tests/fixtures/ai_suno_2.mp3",
+        ])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("\"ai_generated\": true"))
+        .stdout(predicate::str::contains("suno"));
+}
+
+#[test]
+fn suno_2_info_shows_id3_tags() {
+    cargo_bin_cmd!("aic")
+        .args(["--lang", "en", "info", "tests/fixtures/ai_suno_2.mp3"])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("ID3"));
+}
+
+// --- ElevenLabs (C2PA, HIGH) ---
+
+#[test]
+fn elevenlabs_detected_via_c2pa() {
+    cargo_bin_cmd!("aic")
+        .args(["--lang", "en", "check", "tests/fixtures/ai_elevenlabs.mp3"])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("C2PA"))
+        .stdout(predicate::str::contains("elevenlabs"));
+}
+
+#[test]
+fn elevenlabs_json_output() {
+    cargo_bin_cmd!("aic")
+        .args([
+            "--lang",
+            "en",
+            "--json",
+            "check",
+            "tests/fixtures/ai_elevenlabs.mp3",
+        ])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("\"ai_generated\": true"));
+}
+
+#[test]
+fn elevenlabs_info_shows_c2pa() {
+    cargo_bin_cmd!("aic")
+        .args(["--lang", "en", "info", "tests/fixtures/ai_elevenlabs.mp3"])
+        .assert()
+        .success()
+        .stdout(predicate::str::contains("C2PA"));
+}