searchi/apps/desktop/src-tauri/src/main.rs

#![cfg_attr(not(debug_assertions), windows_subsystem = "windows")]

#[cfg(all(not(debug_assertions), not(feature = "custom-protocol")))]
compile_error!("Release desktop builds require --features custom-protocol to embed the frontend");

mod ai_commands;
mod data_directory;
mod model_download;
mod semantic_commands;
mod settings;

use ai_commands::{generate_ai, prepare_ai_source, AiSession};
use searchi_core::metrics::{MetricsMode, SearchMetrics, SearchResponse, TraceCollector};
use searchi_core::{IndexReport, IndexStats, SearchIndex, SearchOptions, SearchResult};
use semantic_commands::{
    hybrid_search, hybrid_search_measured, index_embeddings, semantic_status, setup_model,
    SemanticState,
};
use serde::{Deserialize, Serialize};
use settings::{Settings, SettingsStore};
use std::{
    path::PathBuf,
    sync::{
        atomic::{AtomicBool, Ordering},
        Arc, Mutex,
    },
};
use tauri::{Emitter, Manager, State};
use tauri_plugin_dialog::DialogExt;
use tauri_plugin_global_shortcut::{GlobalShortcutExt, ShortcutState};
use tauri_plugin_opener::OpenerExt;

struct AppState {
    ai: Arc<AiSession>,
    database: PathBuf,
    lexical: Arc<Mutex<SearchIndex>>,
    indexing: Arc<AtomicBool>,
    settings: Arc<Mutex<SettingsStore>>,
    shortcut_status: String,
    semantic: Arc<SemanticState>,
}

#[derive(Serialize)]
struct MeasuredFailure {
    message: String,
    metrics: SearchMetrics,
}

impl MeasuredFailure {
    fn new(message: impl Into<String>, trace: TraceCollector) -> Self {
        Self {
            message: message.into(),
            metrics: trace.finish(0),
        }
    }

    fn task(message: impl Into<String>, started: std::time::Instant) -> Self {
        Self {
            message: message.into(),
            metrics: SearchMetrics {
                total_ms: started.elapsed().as_secs_f64() * 1000.0,
                result_count: 0,
                trace: None,
                dropped_spans: 1,
            },
        }
    }
}

fn measured_outcome(
    result: Result<Vec<SearchResult>, String>,
    trace: TraceCollector,
) -> Result<SearchResponse<SearchResult>, MeasuredFailure> {
    match result {
        Ok(results) => Ok(SearchResponse {
            metrics: trace.finish(results.len()),
            results,
        }),
        Err(message) => Err(MeasuredFailure::new(message, trace)),
    }
}

#[derive(Serialize)]
struct DesktopStatus {
    settings: Settings,
    indexing: bool,
    shortcut_status: String,
}

#[tauri::command]
fn desktop_status(state: State<'_, AppState>) -> Result<DesktopStatus, String> {
    Ok(DesktopStatus {
        settings: state
            .settings
            .lock()
            .map_err(|_| "Settings are unavailable.")?
            .value
            .clone(),
        indexing: state.indexing.load(Ordering::Acquire),
        shortcut_status: state.shortcut_status.clone(),
    })
}

#[tauri::command]
fn set_cpu_threads(threads: usize, state: State<'_, AppState>) -> Result<Settings, String> {
    if state.indexing.load(Ordering::Acquire) {
        return Err("Wait for indexing to finish before changing resource settings.".into());
    }
    let mut store = state
        .settings
        .lock()
        .map_err(|_| "Settings are unavailable.")?;
    let mut next = store.value.clone();
    next.cpu_threads = threads;
    next.validate()?;
    state
        .semantic
        .change_resources(state.database.clone(), threads, || store.save(next))?;
    Ok(store.value.clone())
}

#[derive(Default, Deserialize)]
struct Filters {
    #[serde(default)]
    code_only: bool,
    folder: Option<PathBuf>,
    extension: Option<String>,
    min_size: Option<u64>,
    max_size: Option<u64>,
    min_duration_ms: Option<u32>,
    max_duration_ms: Option<u32>,
    modified_after_unix_ms: Option<i64>,
    modified_before_unix_ms: Option<i64>,
}

impl From<Filters> for SearchOptions {
    fn from(value: Filters) -> Self {
        Self {
            code_only: value.code_only,
            folder: value.folder,
            extension: value.extension,
            min_size: value.min_size,
            max_size: value.max_size,
            min_duration_ms: value.min_duration_ms,
            max_duration_ms: value.max_duration_ms,
            modified_after_unix_ms: value.modified_after_unix_ms,
            modified_before_unix_ms: value.modified_before_unix_ms,
        }
    }
}

// Each job owns its connection. Slow indexing never holds a desktop mutex.
#[tauri::command]
async fn search(
    query: String,
    filters: Option<Filters>,
    state: State<'_, AppState>,
) -> Result<Vec<SearchResult>, String> {
    let lexical = state.lexical.clone();
    tauri::async_runtime::spawn_blocking(move || {
        lexical
            .try_lock()
            .map_err(|_| "Keyword worker is busy; try the latest query again.".to_owned())?
            .search_with_options(&query, 50, &filters.unwrap_or_default().into())
            .map_err(|e| e.to_string())
    })
    .await
    .map_err(|e| e.to_string())?
}

/// Measured command preserves the legacy array-returning API for integrations.
#[tauri::command]
async fn search_measured(
    query: String,
    filters: Option<Filters>,
    debug_performance: bool,
    state: State<'_, AppState>,
) -> Result<SearchResponse<SearchResult>, MeasuredFailure> {
    let started = std::time::Instant::now();
    let mut trace = TraceCollector::new(if debug_performance {
        MetricsMode::Debug
    } else {
        MetricsMode::Basic
    });
    let queue = trace.begin("desktop.worker_queue", None);
    let lexical = state.lexical.clone();
    tauri::async_runtime::spawn_blocking(move || {
        trace.end(queue, Default::default());
        let result = (|| {
            let index = trace.timed("desktop.lexical_lock", None, |_, _| {
                lexical
                    .try_lock()
                    .map_err(|_| "Keyword worker is busy; try the latest query again.".to_owned())
            })?;
            index
                .search_with_options_traced(
                    &query,
                    50,
                    &filters.unwrap_or_default().into(),
                    &mut trace,
                    None,
                )
                .map_err(|error| error.to_string())
        })();
        measured_outcome(result, trace)
    })
    .await
    .map_err(|error| MeasuredFailure::task(error.to_string(), started))?
}

#[tauri::command]
async fn pick_folder(app: tauri::AppHandle) -> Result<Option<String>, String> {
    tauri::async_runtime::spawn_blocking(move || {
        app.dialog()
            .file()
            .set_title("Choose a folder to index")
            .blocking_pick_folder()
            .map(|path| {
                path.into_path()
                    .map(|path| path.to_string_lossy().into_owned())
                    .map_err(|e| e.to_string())
            })
            .transpose()
    })
    .await
    .map_err(|e| e.to_string())?
}

// No broad opener permission is given to the webview. Every action is checked
// against the index and the current filesystem before invoking a native opener.
fn validated_result(index: &SearchIndex, path: &str) -> Result<PathBuf, String> {
    let canonical = std::fs::canonicalize(path).map_err(|e| format!("File is unavailable: {e}"))?;
    if !canonical.is_file() {
        return Err("Result is no longer a file.".into());
    }
    if !index
        .contains_path(&canonical.to_string_lossy())
        .map_err(|e| e.to_string())?
    {
        return Err("Only files in your search index can be opened.".into());
    }
    Ok(canonical)
}

#[derive(Serialize)]
struct MediaPreview {
    path: String,
    kind: &'static str,
}

// The asset protocol starts with an empty scope. Only a validated indexed
// media file is granted access; the webview receives no general filesystem API.
#[tauri::command]
async fn prepare_media_preview(
    path: String,
    app: tauri::AppHandle,
    state: State<'_, AppState>,
) -> Result<MediaPreview, String> {
    let database = state.database.clone();
    tauri::async_runtime::spawn_blocking(move || {
        let index = SearchIndex::open(database).map_err(|error| error.to_string())?;
        let canonical = validated_result(&index, &path)?;
        let kind = match searchi_media::classify(&canonical) {
            Some(searchi_media::MediaKind::Image) => "image",
            Some(searchi_media::MediaKind::Audio) => "audio",
            Some(searchi_media::MediaKind::Video) => "video",
            None => return Err("This file is not a supported media preview.".into()),
        };
        if kind == "image" {
            let bytes = std::fs::metadata(&canonical)
                .map_err(|error| error.to_string())?
                .len();
            if bytes > 64 * 1024 * 1024 {
                return Err("Image exceeds the 64 MiB preview limit.".into());
            }
            let (width, height) = image::ImageReader::open(&canonical)
                .map_err(|error| error.to_string())?
                .with_guessed_format()
                .map_err(|error| error.to_string())?
                .into_dimensions()
                .map_err(|error| format!("Image preview is unavailable: {error}"))?;
            let jpeg = canonical
                .extension()
                .and_then(|value| value.to_str())
                .is_some_and(|value| matches!(value.to_ascii_lowercase().as_str(), "jpg" | "jpeg"));
            let max_pixels = if jpeg {
                64 * 1024 * 1024
            } else {
                16 * 1024 * 1024
            };
            if width == 0 || height == 0 || u64::from(width) * u64::from(height) > max_pixels {
                return Err("Image exceeds the supported preview dimensions.".into());
            }
        }
        app.asset_protocol_scope()
            .allow_file(&canonical)
            .map_err(|error| error.to_string())?;
        Ok(MediaPreview {
            path: canonical.to_string_lossy().into_owned(),
            kind,
        })
    })
    .await
    .map_err(|error| error.to_string())?
}

#[tauri::command]
async fn open_result(
    path: String,
    reveal: bool,
    app: tauri::AppHandle,
    state: State<'_, AppState>,
) -> Result<(), String> {
    let database = state.database.clone();
    tauri::async_runtime::spawn_blocking(move || {
        let index = SearchIndex::open(database).map_err(|e| e.to_string())?;
        let canonical = validated_result(&index, &path)?;
        if reveal {
            app.opener()
                .reveal_item_in_dir(canonical)
                .map_err(|e| e.to_string())
        } else {
            app.opener()
                .open_path(canonical.to_string_lossy().into_owned(), None::<&str>)
                .map_err(|e| e.to_string())
        }
    })
    .await
    .map_err(|e| e.to_string())?
}

#[tauri::command]
async fn stats(state: State<'_, AppState>) -> Result<IndexStats, String> {
    let database = state.database.clone();
    tauri::async_runtime::spawn_blocking(move || {
        SearchIndex::open(database)
            .and_then(|index| index.stats())
            .map_err(|e| e.to_string())
    })
    .await
    .map_err(|e| e.to_string())?
}

// Reset the gate on every exit, including extractor failures or task panics.
struct IndexGuard(Arc<AtomicBool>);
impl Drop for IndexGuard {
    fn drop(&mut self) {
        self.0.store(false, Ordering::Release);
    }
}

#[tauri::command]
async fn index_folder(root: String, state: State<'_, AppState>) -> Result<IndexReport, String> {
    if state
        .indexing
        .compare_exchange(false, true, Ordering::AcqRel, Ordering::Acquire)
        .is_err()
    {
        return Err("A folder is already being indexed. Wait for it to finish.".into());
    }
    let guard = IndexGuard(state.indexing.clone());
    let database = state.database.clone();
    let settings = state.settings.clone();
    let lexical = state.lexical.clone();
    tauri::async_runtime::spawn_blocking(move || {
        let _guard = guard;
        settings
            .lock()
            .map_err(|_| "Settings are unavailable.")?
            .add_root(std::path::Path::new(&root))?;
        let mut index = SearchIndex::open(database).map_err(|error| error.to_string())?;
        let report = index
            .index_folder(root)
            .map_err(|error| error.to_string())?;
        index.prewarm().map_err(|error| error.to_string())?;
        *lexical
            .lock()
            .map_err(|_| "Keyword engine is unavailable.")? = index;
        Ok(report)
    })
    .await
    .map_err(|e| e.to_string())?
}

fn main() {
    tauri::Builder::default()
        .plugin(tauri_plugin_dialog::init())
        .plugin(tauri_plugin_opener::init())
        .plugin(tauri_plugin_global_shortcut::Builder::new().with_handler(|app, _, event| {
            if event.state == ShortcutState::Pressed {
                if let Some(window) = app.get_webview_window("main") {
                    let result = window.show().and_then(|_| window.unminimize()).and_then(|_| window.set_focus());
                    if let Err(error) = result { eprintln!("Could not focus Searchi: {error}"); }
                    let _ = window.emit("focus-search", ());
                }
            }
        }).build())
        .setup(|app| {
            let directory = data_directory::resolve(
                app.path().app_data_dir()?,
                std::env::var_os("SEARCHI_DATA_DIR"),
            )?;
            std::fs::create_dir_all(&directory)?;
            let database = directory.join("searchi.sqlite");
            let lexical = Arc::new(Mutex::new(SearchIndex::open(&database)?));
            let warm_database = database.clone();
            let warm_target = lexical.clone();
            tauri::async_runtime::spawn_blocking(move || {
                // Prepare a separate reader and swap it in briefly; foreground
                // queries never wait on the long statistics-preparation lock.
                if let Ok(mut index) = SearchIndex::open(warm_database) {
                    if index.prewarm().is_ok() {
                        if let Ok(mut current) = warm_target.lock() { *current = index; }
                    }
                }
            });
            let settings = SettingsStore::load(directory.join("settings.json")).map_err(std::io::Error::other)?;
            let development_root = PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("../../..");
            let development_models = development_root.join(".searchi/models/embeddinggemma2");
            let bundled_models = app.path().resource_dir()?.join("embeddinggemma2");
            let model_directory = if let Some(configured) = settings.value.model_directory.clone() {
                configured
            } else if cfg!(debug_assertions) && development_models.is_dir() {
                development_models.canonicalize().unwrap_or(development_models)
            } else if searchi_assets::has_model_files(&bundled_models)? {
                bundled_models
            } else {
                searchi_assets::default_model_directory().unwrap_or_else(|_| directory.join("Models"))
            };
            let worker_name = if cfg!(windows) { "searchi-gemma-worker.exe" } else { "searchi-gemma-worker" };
            let development_worker = development_root.join(".searchi/runtime/cpu")
                .join(if cfg!(windows) { "Release" } else { "" }).join(worker_name);
            let worker = std::env::var_os("SEARCHI_EMBEDDING_WORKER").map(PathBuf::from)
                .unwrap_or_else(|| {
                    if cfg!(debug_assertions) && development_worker.is_file() {
                        development_worker.canonicalize().unwrap_or(development_worker)
                    } else {
                        app.path().resource_dir().unwrap_or_else(|_| directory.clone()).join(worker_name)
                    }
                });
            let media_tools = (|| -> Result<searchi_media::FfmpegTools, String> {
                if let Some(tools) = searchi_media::FfmpegTools::from_environment()
                    .map_err(|error| error.to_string())? {
                    return Ok(tools);
                }
                let development_media = development_root.join(".searchi/media-runtime/bin");
                let media_directory = if cfg!(debug_assertions) && development_media.is_dir() {
                    development_media
                } else {
                    app.path().resource_dir().map_err(|error| error.to_string())?.join("media-runtime/bin")
                };
                let ffmpeg = media_directory.join(if cfg!(windows) { "ffmpeg.exe" } else { "ffmpeg" });
                let ffprobe = media_directory.join(if cfg!(windows) { "ffprobe.exe" } else { "ffprobe" });
                searchi_media::FfmpegTools::new(ffmpeg, ffprobe).map_err(|_| {
                    "The media decoder is missing from this installation. Repair or reinstall searchi.".into()
                })
            })();
            let semantic = Arc::new(SemanticState::new(model_directory, worker, media_tools));
            semantic.begin_automatic_setup(database.clone(), settings.value.cpu_threads);
            #[cfg(target_os = "macos")]
            let shortcut = "Shift+Super+Space";
            #[cfg(not(target_os = "macos"))]
            let shortcut = "Control+Shift+Space";
            let wayland = cfg!(target_os = "linux") &&
                (std::env::var("XDG_SESSION_TYPE").is_ok_and(|value| value == "wayland") || std::env::var_os("WAYLAND_DISPLAY").is_some());
            let shortcut_status = if wayland {
                "Global shortcut unavailable on Wayland. Open Searchi from your application launcher.".into()
            } else {
                match app.global_shortcut().register(shortcut) {
                    Ok(()) => format!("Global shortcut: {shortcut}"),
                    Err(error) => format!("Global shortcut unavailable: {error}"),
                }
            };
            app.manage(AppState {
                ai: Arc::new(AiSession::default()),
                database,
                lexical,
                indexing: Arc::new(AtomicBool::new(false)),
                settings: Arc::new(Mutex::new(settings)),
                shortcut_status,
                semantic,
            });
            Ok(())
        })
        .invoke_handler(tauri::generate_handler![
            prepare_ai_source,
            generate_ai,
            search,
            search_measured,
            stats,
            index_folder,
            pick_folder,
            open_result,
            prepare_media_preview,
            desktop_status,
            set_cpu_threads,
            semantic_status,
            setup_model,
            index_embeddings,
            hybrid_search,
            hybrid_search_measured
        ])
        .run(tauri::generate_context!())
        .expect("Searchi desktop could not start");
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn code_scope_defaults_off_and_combines_with_other_filters() {
        let legacy: Filters = serde_json::from_str(r#"{"extension":"rs"}"#).unwrap();
        let legacy: SearchOptions = legacy.into();
        assert!(!legacy.code_only);
        let scoped: Filters =
            serde_json::from_str(r#"{"code_only":true,"extension":"rs","min_size":10}"#).unwrap();
        let scoped: SearchOptions = scoped.into();
        assert!(scoped.code_only);
        assert_eq!(scoped.extension.as_deref(), Some("rs"));
        assert_eq!(scoped.min_size, Some(10));
        assert!(serde_json::from_str::<Filters>(r#"{"code_only":"true"}"#).is_err());
    }

    #[test]
    fn code_scope_reaches_real_keyword_search_without_model_readiness() {
        let root = tempfile::tempdir().unwrap();
        std::fs::write(
            root.path().join("parse.rs"),
            "fn parse_configuration() { /* validate config */ }",
        )
        .unwrap();
        std::fs::write(
            root.path().join("notes.md"),
            "parse_configuration validate config",
        )
        .unwrap();
        let mut index = SearchIndex::open(":memory:").unwrap();
        index.index_folder(root.path()).unwrap();
        let all: SearchOptions = Filters::default().into();
        assert_eq!(
            index
                .search_with_options("parse_configuration", 10, &all)
                .unwrap()
                .len(),
            2
        );
        let scoped: SearchOptions = serde_json::from_str::<Filters>(r#"{"code_only":true}"#)
            .unwrap()
            .into();
        let hits = index
            .search_with_options("parse_configuration", 10, &scoped)
            .unwrap();
        assert_eq!(hits.len(), 1);
        assert_eq!(hits[0].filename, "parse.rs");
    }

    #[test]
    fn measured_failure_retains_closed_trace_without_inventing_results() {
        let mut trace = TraceCollector::new(MetricsMode::Debug);
        let parent = trace.begin("desktop.request", None);
        trace.begin("desktop.lexical_lock", parent);
        let failed = measured_outcome(Err("Keyword worker is busy".into()), trace)
            .err()
            .unwrap();
        assert_eq!(failed.message, "Keyword worker is busy");
        assert_eq!(failed.metrics.result_count, 0);
        let spans = failed.metrics.trace.unwrap();
        assert_eq!(spans.len(), 2);
        assert_eq!(spans[1].parent, Some(0));
        assert!(spans[1].start_ms + spans[1].duration_ms <= failed.metrics.total_ms + 0.001);
    }

    #[test]
    fn measured_empty_success_is_distinct_from_failure_and_basic_has_no_trace() {
        let response = measured_outcome(Ok(Vec::new()), TraceCollector::new(MetricsMode::Basic))
            .ok()
            .unwrap();
        assert!(response.results.is_empty());
        assert_eq!(response.metrics.result_count, 0);
        assert!(response.metrics.trace.is_none());
    }

    #[test]
    fn indexing_gate_is_released_when_worker_unwinds() {
        let indexing = Arc::new(AtomicBool::new(true));
        let gate = indexing.clone();
        let result = std::panic::catch_unwind(move || {
            let _guard = IndexGuard(gate);
            panic!("extractor failure");
        });
        assert!(result.is_err());
        assert!(!indexing.load(Ordering::Acquire));
    }

    #[test]
    fn opener_rejects_unindexed_and_deleted_files() {
        let root = tempfile::tempdir().unwrap();
        let indexed = root.path().join("indexed.txt");
        std::fs::write(&indexed, "retrieval fixture").unwrap();
        let mut index = SearchIndex::open(":memory:").unwrap();
        index.index_folder(root.path()).unwrap();
        assert!(validated_result(&index, &indexed.to_string_lossy()).is_ok());
        let unindexed = root.path().join("new.txt");
        std::fs::write(&unindexed, "not indexed").unwrap();
        assert!(validated_result(&index, &unindexed.to_string_lossy()).is_err());
        std::fs::remove_file(&indexed).unwrap();
        assert!(validated_result(&index, &indexed.to_string_lossy()).is_err());
        assert!(validated_result(&index, &root.path().to_string_lossy()).is_err());
    }
}