Land release blocker fixes and workspace cleanup

crates/storage/src/migrations.rs

@@ -215,6 +215,125 @@ const MIGRATIONS: &[(i64, &str, &str)] = &[
             ON transcripts(profile_id);
         "#,
     ),
+    (
+        9,
+        "transcript_profile_fk",
+        r#"
+        INSERT OR IGNORE INTO profiles (id, name, initial_prompt, created_at)
+        VALUES ('00000000-0000-0000-0000-000000000001', 'Default', '', datetime('now'));
+
+        DROP TRIGGER IF EXISTS transcripts_ai;
+        DROP TRIGGER IF EXISTS transcripts_ad;
+        DROP TRIGGER IF EXISTS transcripts_au;
+        DROP TABLE IF EXISTS transcripts_fts;
+        DROP INDEX IF EXISTS idx_segments_transcript;
+        DROP INDEX IF EXISTS idx_transcripts_created;
+        DROP INDEX IF EXISTS idx_transcripts_profile_id;
+
+        ALTER TABLE segments RENAME TO segments_old;
+        ALTER TABLE transcripts RENAME TO transcripts_old;
+
+        CREATE TABLE transcripts (
+            id TEXT PRIMARY KEY,
+            text TEXT NOT NULL DEFAULT '',
+            source TEXT NOT NULL DEFAULT 'microphone',
+            title TEXT,
+            audio_path TEXT,
+            duration REAL NOT NULL DEFAULT 0.0,
+            engine TEXT,
+            model_id TEXT,
+            inference_ms INTEGER,
+            sample_rate INTEGER,
+            audio_channels INTEGER,
+            format_mode TEXT,
+            remove_fillers INTEGER NOT NULL DEFAULT 0,
+            british_english INTEGER NOT NULL DEFAULT 0,
+            anti_hallucination INTEGER NOT NULL DEFAULT 0,
+            created_at TEXT NOT NULL DEFAULT (datetime('now')),
+            starred INTEGER NOT NULL DEFAULT 0,
+            manual_tags TEXT NOT NULL DEFAULT '',
+            template TEXT NOT NULL DEFAULT '',
+            language TEXT NOT NULL DEFAULT '',
+            segments_json TEXT NOT NULL DEFAULT '',
+            profile_id TEXT NOT NULL DEFAULT '00000000-0000-0000-0000-000000000001'
+                REFERENCES profiles(id) ON DELETE RESTRICT
+        );
+
+        CREATE INDEX idx_transcripts_created
+            ON transcripts(created_at);
+        CREATE INDEX idx_transcripts_profile_id
+            ON transcripts(profile_id);
+
+        INSERT INTO transcripts (
+            id, text, source, title, audio_path, duration, engine, model_id,
+            inference_ms, sample_rate, audio_channels, format_mode,
+            remove_fillers, british_english, anti_hallucination, created_at,
+            starred, manual_tags, template, language, segments_json, profile_id
+        )
+        SELECT
+            id, text, source, title, audio_path, duration, engine, model_id,
+            inference_ms, sample_rate, audio_channels, format_mode,
+            remove_fillers, british_english, anti_hallucination, created_at,
+            starred, manual_tags, template, language, segments_json,
+            CASE
+                WHEN profile_id IS NOT NULL
+                 AND EXISTS (
+                    SELECT 1 FROM profiles
+                    WHERE id = transcripts_old.profile_id
+                 )
+                    THEN profile_id
+                ELSE '00000000-0000-0000-0000-000000000001'
+            END
+        FROM transcripts_old;
+
+        CREATE TABLE segments (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            transcript_id TEXT NOT NULL REFERENCES transcripts(id) ON DELETE CASCADE,
+            start_time REAL NOT NULL,
+            end_time REAL NOT NULL,
+            text TEXT NOT NULL DEFAULT ''
+        );
+
+        CREATE INDEX idx_segments_transcript
+            ON segments(transcript_id);
+
+        INSERT INTO segments (id, transcript_id, start_time, end_time, text)
+        SELECT id, transcript_id, start_time, end_time, text
+        FROM segments_old;
+
+        DROP TABLE segments_old;
+        DROP TABLE transcripts_old;
+
+        CREATE VIRTUAL TABLE transcripts_fts USING fts5(
+            text,
+            title,
+            content='transcripts',
+            content_rowid='rowid',
+            tokenize='porter unicode61 remove_diacritics 2'
+        );
+
+        CREATE TRIGGER transcripts_ai AFTER INSERT ON transcripts BEGIN
+            INSERT INTO transcripts_fts(rowid, text, title)
+            VALUES (new.rowid, new.text, COALESCE(new.title, ''));
+        END;
+
+        CREATE TRIGGER transcripts_ad AFTER DELETE ON transcripts BEGIN
+            INSERT INTO transcripts_fts(transcripts_fts, rowid, text, title)
+            VALUES ('delete', old.rowid, old.text, COALESCE(old.title, ''));
+        END;
+
+        CREATE TRIGGER transcripts_au AFTER UPDATE ON transcripts BEGIN
+            INSERT INTO transcripts_fts(transcripts_fts, rowid, text, title)
+            VALUES ('delete', old.rowid, old.text, COALESCE(old.title, ''));
+            INSERT INTO transcripts_fts(rowid, text, title)
+            VALUES (new.rowid, new.text, COALESCE(new.title, ''));
+        END;
+
+        INSERT INTO transcripts_fts(rowid, text, title)
+        SELECT rowid, text, COALESCE(title, '')
+        FROM transcripts;
+        "#,
+    ),
 ];
 
 /// Split SQL into individual statements, respecting BEGIN...END trigger blocks.
@@ -281,10 +400,7 @@ pub async fn run_migrations(pool: &SqlitePool) -> Result<()> {
 /// implicitly commits (`VACUUM`, `REINDEX`, `ATTACH`), it must be split
 /// out into its own non-transactional migration — reviewer's job to
 /// flag.
-async fn run_migrations_slice(
-    pool: &SqlitePool,
-    migrations: &[(i64, &str, &str)],
-) -> Result<()> {
+async fn run_migrations_slice(pool: &SqlitePool, migrations: &[(i64, &str, &str)]) -> Result<()> {
     sqlx::query(
         "CREATE TABLE IF NOT EXISTS schema_version (
             version INTEGER PRIMARY KEY,
@@ -344,12 +460,22 @@ mod tests {
     use sqlx::sqlite::SqlitePoolOptions;
     use sqlx::Row;
 
-    #[tokio::test]
-    async fn test_migrations_run_on_empty_db() {
+    async fn fk_test_pool() -> SqlitePool {
         let pool = SqlitePoolOptions::new()
+            .max_connections(1)
             .connect("sqlite::memory:")
             .await
-            .unwrap();
+            .expect("pool");
+        sqlx::query("PRAGMA foreign_keys = ON")
+            .execute(&pool)
+            .await
+            .expect("enable foreign keys");
+        pool
+    }
+
+    #[tokio::test]
+    async fn test_migrations_run_on_empty_db() {
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
 
@@ -357,7 +483,7 @@ mod tests {
             .fetch_one(&pool)
             .await
             .unwrap();
-        assert_eq!(count, 8);
+        assert_eq!(count, 9);
 
         sqlx::query("INSERT INTO settings (key, value) VALUES ('test', 'value')")
             .execute(&pool)
@@ -367,10 +493,7 @@ mod tests {
 
     #[tokio::test]
     async fn test_migrations_idempotent() {
-        let pool = SqlitePoolOptions::new()
-            .connect("sqlite::memory:")
-            .await
-            .unwrap();
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
         run_migrations(&pool).await.unwrap();
@@ -379,7 +502,7 @@ mod tests {
             .fetch_one(&pool)
             .await
             .unwrap();
-        assert_eq!(count, 8);
+        assert_eq!(count, 9);
     }
 
     #[tokio::test]
@@ -440,11 +563,7 @@ mod tests {
 
     #[tokio::test]
     async fn migration_transcript_profile_provenance_adds_profile_id() {
-        let pool = SqlitePoolOptions::new()
-            .max_connections(1)
-            .connect("sqlite::memory:")
-            .await
-            .expect("pool");
+        let pool = fk_test_pool().await;
         run_migrations(&pool).await.expect("migrate");
 
         let info = sqlx::query("PRAGMA table_info(transcripts)")
@@ -459,11 +578,108 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn test_parent_task_id_cascade_delete() {
-        let pool = SqlitePoolOptions::new()
-            .connect("sqlite::memory:")
+    async fn migration_v9_reconciles_orphaned_transcript_profiles_and_adds_fk() {
+        let pool = fk_test_pool().await;
+        run_migrations_up_to(&pool, 8).await.expect("migrate to v8");
+
+        sqlx::query(
+            "INSERT INTO profiles (id, name, initial_prompt, created_at)
+             VALUES ('profile-valid', 'Valid', '', datetime('now'))",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed valid profile");
+
+        sqlx::query(
+            "INSERT INTO transcripts (
+                id, text, source, title, audio_path, duration, engine, model_id,
+                inference_ms, sample_rate, audio_channels, format_mode,
+                remove_fillers, british_english, anti_hallucination, created_at,
+                starred, manual_tags, template, language, segments_json, profile_id
+            ) VALUES (
+                't-orphan', 'orphan body', 'microphone', 'Orphan', NULL, 0.0, NULL, NULL,
+                NULL, NULL, NULL, NULL, 0, 0, 0, datetime('now'),
+                0, '', '', '', '', 'profile-missing'
+            )",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed orphan transcript");
+        sqlx::query(
+            "INSERT INTO transcripts (
+                id, text, source, title, audio_path, duration, engine, model_id,
+                inference_ms, sample_rate, audio_channels, format_mode,
+                remove_fillers, british_english, anti_hallucination, created_at,
+                starred, manual_tags, template, language, segments_json, profile_id
+            ) VALUES (
+                't-valid', 'valid body', 'microphone', 'Valid', NULL, 0.0, NULL, NULL,
+                NULL, NULL, NULL, NULL, 0, 0, 0, datetime('now'),
+                0, '', '', '', '', 'profile-valid'
+            )",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed valid transcript");
+        sqlx::query(
+            "INSERT INTO segments (transcript_id, start_time, end_time, text)
+             VALUES ('t-orphan', 0.0, 1.0, 'segment')",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed segment");
+
+        run_migrations(&pool).await.expect("migrate to v9");
+
+        let orphan_profile: String =
+            sqlx::query_scalar("SELECT profile_id FROM transcripts WHERE id = 't-orphan'")
+                .fetch_one(&pool)
+                .await
+                .expect("read healed orphan");
+        assert_eq!(orphan_profile, crate::DEFAULT_PROFILE_ID);
+
+        let valid_profile: String =
+            sqlx::query_scalar("SELECT profile_id FROM transcripts WHERE id = 't-valid'")
+                .fetch_one(&pool)
+                .await
+                .expect("read preserved profile");
+        assert_eq!(valid_profile, "profile-valid");
+
+        let segment_count: i64 =
+            sqlx::query_scalar("SELECT COUNT(*) FROM segments WHERE transcript_id = 't-orphan'")
+                .fetch_one(&pool)
+                .await
+                .expect("read migrated segments");
+        assert_eq!(segment_count, 1, "segments must survive transcript rebuild");
+
+        let fk_rows = sqlx::query("PRAGMA foreign_key_list(transcripts)")
+            .fetch_all(&pool)
             .await
-            .unwrap();
+            .expect("read transcript foreign keys");
+        assert!(
+            fk_rows.iter().any(|row| {
+                row.get::<String, _>("table") == "profiles"
+                    && row.get::<String, _>("from") == "profile_id"
+                    && row.get::<String, _>("to") == "id"
+                    && row.get::<String, _>("on_delete") == "RESTRICT"
+            }),
+            "transcripts.profile_id must reference profiles(id) with ON DELETE RESTRICT"
+        );
+
+        let fts_hits: i64 = sqlx::query_scalar(
+            "SELECT COUNT(*) FROM transcripts_fts WHERE transcripts_fts MATCH 'orphan'",
+        )
+        .fetch_one(&pool)
+        .await
+        .expect("query rebuilt fts");
+        assert_eq!(
+            fts_hits, 1,
+            "fts index must be rebuilt for existing transcripts"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_parent_task_id_cascade_delete() {
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
 
@@ -656,7 +872,7 @@ mod tests {
         run_migrations(&pool).await.expect("baseline migrate");
 
         const POISON: &[(i64, &str, &str)] = &[(
-            9,
+            10,
             "rb-02 atomicity poison",
             r#"
             CREATE TABLE poison_marker (id INTEGER PRIMARY KEY);
@@ -680,15 +896,14 @@ mod tests {
             "poison_marker must not exist; got: {marker:?}"
         );
 
-        // `schema_version` must not include v9 — version insert is part
+        // `schema_version` must not include v10 — version insert is part
         // of the same transaction that rolled back.
-        let max: i64 =
-            sqlx::query_scalar("SELECT COALESCE(MAX(version), 0) FROM schema_version")
-                .fetch_one(&pool)
-                .await
-                .expect("read schema_version");
+        let max: i64 = sqlx::query_scalar("SELECT COALESCE(MAX(version), 0) FROM schema_version")
+            .fetch_one(&pool)
+            .await
+            .expect("read schema_version");
         assert_eq!(
-            max, 8,
+            max, 9,
             "schema_version must not advance past the failed migration"
         );
     }