searchi/crates/searchi-service/tests/google_cpu.rs

use anyhow::Result;
use searchi_core::SearchIndex;
use searchi_service::{HybridSearch, SearchOptions};
use std::fs;

#[test]
#[ignore = "Requires explicitly provisioned Google model and CPU worker"]
fn real_google_search_persists_and_suppresses_changed_deleted_sources() -> Result<()> {
    assert_eq!(
        std::env::var("SEARCHI_FORCE_CPU").unwrap(),
        "1",
        "VM tests require CPU only"
    );
    let model = std::env::var_os("SEARCHI_GEMMA_MODEL_DIR").expect("Set SEARCHI_GEMMA_MODEL_DIR");
    let worker = std::env::var_os("SEARCHI_GEMMA_WORKER").expect("Set SEARCHI_GEMMA_WORKER");
    let temp = tempfile::tempdir()?;
    let root = temp.path().join("documents");
    fs::create_dir(&root)?;
    let db = temp.path().join("index.db");
    fs::write(
        root.join("agreement.txt"),
        "The supplier partnership may be ended with sixty days written notice.",
    )?;
    fs::write(
        root.join("garden.txt"),
        "Tomatoes need regular watering and lots of sunlight.",
    )?;
    let mut lexical = SearchIndex::open(&db)?;
    lexical.index_folder(&root)?;
    let mut hybrid = HybridSearch::open(&db, &model, &worker, 1)?;
    let report = hybrid.index_embeddings()?;
    assert_eq!(report.passages, 2);
    let hits = hybrid.search(
        "Wie beenden wir die Zusammenarbeit mit dem Lieferanten?",
        10,
        &SearchOptions::default(),
    )?;
    assert_eq!(hits[0].filename, "agreement.txt");
    assert!(hits[0].source.is_some());
    assert!(hits[0].snippet.contains("sixty days"));
    let exact = hybrid.search("garden.txt", 10, &SearchOptions::default())?;
    assert_eq!(exact[0].match_kind, "exact_filename");
    let restricted = hybrid.search(
        "Wie beenden wir die Zusammenarbeit mit dem Lieferanten?",
        10,
        &SearchOptions {
            extension: Some("pdf".into()),
            ..Default::default()
        },
    )?;
    assert!(restricted.is_empty());
    drop(hybrid);
    let mut hybrid = HybridSearch::open(&db, &model, &worker, 1)?;
    assert_eq!(
        hybrid.search(
            "How can we stop working with the vendor?",
            10,
            &SearchOptions::default()
        )?[0]
            .filename,
        "agreement.txt"
    );
    fs::write(root.join("agreement.txt"),"Entirely unrelated replacement content about repainting a kitchen and changing cupboard handles.")?;
    lexical.index_folder(&root)?;
    assert!(hybrid
        .search_semantic(
            "How can we stop working with the vendor?",
            10,
            &SearchOptions::default()
        )?
        .iter()
        .all(|hit| hit.filename != "agreement.txt"));
    fs::remove_file(root.join("garden.txt"))?;
    lexical.index_folder(&root)?;
    assert!(hybrid
        .search_semantic("How do we water vegetables?", 10, &SearchOptions::default())?
        .iter()
        .all(|hit| hit.filename != "garden.txt"));
    Ok(())
}

#[test]
#[ignore = "Requires explicitly provisioned Google model and CPU worker"]
fn real_google_failed_policy_rebuild_preserves_live_reader_and_retry() -> Result<()> {
    use fs2::FileExt;
    use rusqlite::Connection;
    use searchi_service::{FfmpegTools, MediaLimits};
    use std::fs::OpenOptions;

    assert_eq!(std::env::var("SEARCHI_FORCE_CPU")?, "1");
    let model = std::env::var_os("SEARCHI_GEMMA_MODEL_DIR").expect("Set SEARCHI_GEMMA_MODEL_DIR");
    let worker = std::env::var_os("SEARCHI_GEMMA_WORKER").expect("Set SEARCHI_GEMMA_WORKER");
    let temp = tempfile::tempdir()?;
    let root = temp.path().join("documents");
    fs::create_dir(&root)?;
    let db = temp.path().join("index.db");
    fs::write(
        root.join("agreement.txt"),
        "The supplier partnership may be ended with sixty days written notice.",
    )?;
    let mut lexical = SearchIndex::open(&db)?;
    lexical.index_folder(&root)?;
    let mut service = HybridSearch::open(&db, model, worker, 1)?;
    service.index_embeddings()?;
    let connection = Connection::open(&db)?;
    let active = |connection: &Connection| -> Result<(i64, String)> {
        Ok(connection.query_row(
            "SELECT g.id,g.fingerprint FROM semantic_generations g JOIN semantic_meta m ON m.active_generation=g.id",
            [],
            |row| Ok((row.get(0)?, row.get(1)?)),
        )?)
    };
    let assert_reader = |service: &mut HybridSearch| -> Result<()> {
        let hits = service.search_semantic(
            "How can we stop working with the vendor?",
            10,
            &SearchOptions::default(),
        )?;
        assert_eq!(hits.len(), 1);
        assert_eq!(hits[0].filename, "agreement.txt");
        assert!(hits[0].snippet.contains("sixty days"));
        Ok(())
    };
    assert_reader(&mut service)?;
    let original = active(&connection)?;
    // No media files are present: exercise the production media-policy rebuild
    // with genuine document inference, without invoking any decoder fixture.
    let tools = FfmpegTools {
        ffmpeg: std::env::current_exe()?,
        ffprobe: std::env::current_exe()?,
    };
    let limits = MediaLimits::default();
    let lock_path = format!("{}.semantic.lock", db.canonicalize()?.to_string_lossy());
    let lock = OpenOptions::new()
        .read(true)
        .write(true)
        .create(true)
        .truncate(false)
        .open(lock_path)?;
    lock.try_lock_exclusive()?;
    let failure = service
        .index_embeddings_with_media(&tools, &limits)
        .unwrap_err();
    assert!(format!("{failure:#}").contains("Another semantic rebuild"));
    FileExt::unlock(&lock)?;
    assert_eq!(active(&connection)?, original);
    assert_reader(&mut service)?;

    connection.execute_batch("CREATE TRIGGER reject_generation_begin BEFORE INSERT ON semantic_generations BEGIN SELECT RAISE(ABORT,'rejected generation begin'); END;")?;
    assert!(service
        .index_embeddings_with_media(&tools, &limits)
        .is_err());
    assert_eq!(active(&connection)?, original);
    assert_reader(&mut service)?;
    connection.execute_batch("DROP TRIGGER reject_generation_begin;
        CREATE TRIGGER reject_generation_activation BEFORE UPDATE OF active_generation ON semantic_meta BEGIN SELECT RAISE(ABORT,'rejected generation activation'); END;")?;
    let failure = service
        .index_embeddings_with_media(&tools, &limits)
        .unwrap_err();
    assert!(format!("{failure:#}").contains("rejected generation activation"));
    assert_eq!(active(&connection)?, original);
    assert_reader(&mut service)?;
    let generations: i64 =
        connection.query_row("SELECT count(*) FROM semantic_generations", [], |row| {
            row.get(0)
        })?;
    assert_eq!(generations, 1, "Failed activation must discard staging");

    connection.execute_batch("CREATE TRIGGER reject_generation_cleanup BEFORE DELETE ON semantic_generations WHEN old.id != (SELECT active_generation FROM semantic_meta WHERE singleton=1) BEGIN SELECT RAISE(ABORT,'rejected generation cleanup'); END;")?;
    let failure = service
        .index_embeddings_with_media(&tools, &limits)
        .unwrap_err();
    let message = format!("{failure:#}");
    assert!(message.contains("rejected generation activation"));
    assert!(message.contains("rejected generation cleanup"));
    assert_eq!(active(&connection)?, original);
    assert_reader(&mut service)?;
    connection.execute_batch(
        "DROP TRIGGER reject_generation_activation; DROP TRIGGER reject_generation_cleanup;",
    )?;
    let retry = service.index_embeddings_with_media(&tools, &limits)?;
    assert_eq!(retry.passages, 1);
    assert_reader(&mut service)?;
    let media_active = active(&connection)?;
    assert_ne!(media_active.1, original.1);

    // Exercise the reverse media-to-text policy change through the same helper.
    lock.try_lock_exclusive()?;
    assert!(service.index_embeddings().is_err());
    FileExt::unlock(&lock)?;
    assert_eq!(active(&connection)?, media_active);
    assert_reader(&mut service)?;
    connection.execute_batch("CREATE TRIGGER reject_generation_activation BEFORE UPDATE OF active_generation ON semantic_meta BEGIN SELECT RAISE(ABORT,'rejected generation activation'); END;")?;
    assert!(service.index_embeddings().is_err());
    assert_eq!(active(&connection)?, media_active);
    assert_reader(&mut service)?;
    connection.execute_batch("DROP TRIGGER reject_generation_activation;")?;
    service.index_embeddings()?;
    assert_eq!(active(&connection)?.1, original.1);
    assert_reader(&mut service)?;
    Ok(())
}