//! The live session registry. Every session mutation -- spawn, delete, //! token changes -- funnels through [`SessionManager`] under one lock, so //! in-memory state and `config.ron` can't come apart (the same pattern as //! dev-updater's `registry.rs`). //! //! A live session is a driver plus one event pump: the driver reports //! [`Event`]s into an mpsc channel; the pump assigns each a sequence //! number, appends it to the session's transcript file, and fans it out to //! SSE subscribers. The transcript is the source of truth -- subscribers //! that fall behind or reconnect catch up from the file by cursor. pub mod claude; pub mod driver; pub mod echo; pub mod import; pub mod llama; pub mod process; pub mod transcript; pub mod transport; use std::collections::{HashMap, VecDeque}; use std::path::{Path, PathBuf}; use std::sync::{Arc, Mutex, RwLock}; use std::time::{SystemTime, UNIX_EPOCH}; use anyhow::{Context, Result, bail}; use serde::Serialize; use tokio::sync::{broadcast, mpsc}; use crate::config::{ Config, DriverKind, ProviderConfig, SessionConfig, SetupConfig, SshConfig, TokenEntry, }; use claude::ClaudeDriver; use driver::{Driver, Event, EventSink, ImageRef, SessionCommand, SessionStatus, context_after}; use echo::EchoDriver; use llama::LlamaDriver; use transcript::{SeqEvent, Transcript}; use transport::Transport; /// Fan-out buffer per session. A subscriber that falls further behind than /// this is caught up from the transcript file instead (see `routes`), so /// the size only bounds memory, not correctness. const EVENT_BUFFER: usize = 256; /// Fan-out buffer for notifications, across every session. /// /// Small, and deliberately: a subscriber that falls this far behind on a /// stream carrying two events per turn is not one whose backlog is worth /// delivering. Lagging drops the oldest, which is the right end to lose -- /// the newest "your turn" is the one still true. const NOTIFICATION_BUFFER: usize = 64; pub fn now() -> f64 { SystemTime::now() .duration_since(UNIX_EPOCH) .unwrap_or_default() .as_secs_f64() } /// What the phone needs to spawn a session -- the spawn screen's fields. pub struct SpawnSpec { /// Which machine, and which of its providers. pub setup: String, pub provider: String, pub title: Option, pub model: Option, pub cwd: Option, pub permission_mode: Option, /// Driver-interpreted settings; see `SessionConfig::params`. pub params: std::collections::BTreeMap, } /// A moment worth interrupting somebody for, as `GET /notifications` /// sends it. /// /// Two kinds, and the pair is the whole feature: a session that has *asked* /// something cannot continue until it is answered, and one that has /// *finished* is work somebody walked away from. Everything else a session /// does is progress they did not ask to be told about. /// /// Carries the title rather than only the id, so the phone can write the /// notification without a round trip -- it may well be showing no screen at /// all when this arrives. #[derive(Debug, Clone, Serialize)] #[serde(rename_all = "camelCase")] pub struct Notification { pub session_id: String, pub title: String, pub kind: NotificationKind, /// Epoch seconds, so a phone that was asleep can say how long ago. pub at: f64, } #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize)] #[serde(rename_all = "camelCase")] pub enum NotificationKind { /// The session is waiting on a person: a question, or a permission. AwaitingInput, /// A turn ended without one. Only ever sent for a session that was /// *seen* running -- see `notification_for`. Finished, } /// One row of `GET /sessions`. #[derive(Debug, Clone, Serialize)] #[serde(rename_all = "camelCase")] pub struct SessionInfo { pub id: String, pub provider: String, /// Id of the machine it runs on, which is what the session stored. pub setup: String, /// That machine's current label, resolved when this row is built -- /// so renaming a setup renames it everywhere it appears, rather than /// leaving old sessions showing the old name. pub setup_name: String, pub title: String, #[serde(skip_serializing_if = "Option::is_none")] pub model: Option, /// Whether the conversation would survive deleting this session -- /// see [`DriverKind::keeps_own_transcript`]. /// /// Reported rather than worked out on the phone, because the phone /// has the provider's *name* and this is a property of its *kind*: a /// provider can be called anything, so a client deciding by name /// would get the answer wrong for anyone who renamed one. It decides /// what the delete confirmation says will happen, so it is not a /// field to guess at. pub keeps_own_transcript: bool, /// How much this session asks before acting. Reported so the phone can /// *show* the current mode rather than assume one -- a picker that /// guesses its own value is how you end up changing something you /// thought you were confirming. #[serde(skip_serializing_if = "Option::is_none")] pub permission_mode: Option, /// Whether this session continues one the machine already had. /// /// Reported because it changes what deleting *means*: an imported /// session's real transcript belongs to the CLI and survives, so /// removing it here is undoing a view. A session started here has no /// copy anywhere else, and removing it ends the conversation. Saying /// "this cannot be undone" of both makes the warning worthless on the /// one where it is true. pub imported: bool, #[serde(skip_serializing_if = "Option::is_none")] pub cwd: Option, /// How much context this session is holding, so a phone does not have /// to fold a transcript it only holds part of. /// /// Absent rather than zero where nothing has been measured -- a /// session that has not run a turn, a dialect that does not report /// usage, or a clear nobody has run a turn since. "Empty" and "we did /// not find out" are different answers and the phone draws them /// differently. #[serde(skip_serializing_if = "Option::is_none")] pub context_tokens: Option, /// The longest edge an image should have by the time it gets here, or /// absent where this provider has no limit -- see /// [`DriverKind::max_image_edge`]. Absent rather than a large number, /// because "no limit" and "a limit that happens to be big" are different /// answers and only one of them stays true. #[serde(skip_serializing_if = "Option::is_none")] pub max_image_edge: Option, /// Whether this session announces itself -- reported for the same /// reason `permission_mode` is: a switch that guesses its own position /// is how you turn something off while believing you are reading it. pub notify: bool, pub status: SessionStatus, pub last_activity: f64, pub created: f64, } /// What is running a session at this moment. /// /// Behind a lock because a session outlives its process: stopping one and /// starting it again replaces the driver while the transcript, the event /// pump and the stream every open phone is reading stay exactly where they /// were. Shared with [`Commands`] rather than copied into it, because two /// holders of "the driver" are two answers to that question the moment one /// of them is replaced. type DriverCell = Arc>>; /// A running session: its driver plus the shared state the event pump /// keeps current. Cheap to clone-by-`Arc` into request handlers. pub struct LiveSession { meta: SessionConfig, driver: DriverCell, /// Commands asked for and not yet run, oldest first, with the pump /// that will run them. Shared with that pump, which is what notices /// the boundary. commands: Arc, /// The same channel the driver reports into; the manager injects /// `UserMessage`/`Answered` here so they take a sequence number in /// order with everything else. sink: mpsc::UnboundedSender, events: broadcast::Sender, transcript_path: PathBuf, shared: Arc, } /// Commands waiting for the session to be between turns. /// /// One implementation for every provider, because the rule is about /// sessions rather than about a dialect: a line written into a running /// turn is read by the model, so anything meant for the *session* waits /// for the turn to end. Drivers therefore never have to think about it, /// and a new provider cannot get it wrong by omission. struct Commands { driver: DriverCell, sink: EventSink, waiting: Mutex>, } impl Commands { /// Whatever is driving the session now -- see [`DriverCell`]. fn driver(&self) -> Arc { self.driver.lock().unwrap().clone() } /// Runs `command` now if the session is between turns, holds it until /// it is, and refuses it outright if there will never be one. Whichever /// happened, the phone is told. /// /// "Between turns" is asked of the *driver*, not of `status`. They are /// two views of the same fact and only one of them is current: the /// driver sets its flag the instant it writes a line, while `status` is /// built from what has been recorded, so it still reads idle for the /// whole round trip of a command that produces no assistant text. Two /// commands in a row therefore both went out, the second landing inside /// the turn the first had started, where the CLI reads it as text /// instead of running it -- silently, since a message read as text /// looks like a message. /// /// `status` is still passed, for the one question the driver's flag /// cannot answer: whether there will ever *be* another boundary. fn submit(&self, command: SessionCommand, status: SessionStatus) { let id = random_hex(); let text = command.label(); // A session whose process is gone has no next boundary, so holding // this would hold it forever: the phone draws a waiting bubble that // nothing will ever resolve, and nothing anywhere says why. The // message path has always answered this case -- see // `ClaudeDriver::send_user_message` -- and a command owes the same // answer, since what makes it unanswerable is the same fact. // // `Unknown` is not refused. It means nobody could find out whether // the process is alive, and it resolves itself, so refusing on it // would turn "we don't know" into "it's gone". if status == SessionStatus::Exited { let _ = self.sink.send(Event::Error { message: format!("this session's process has exited, so it can't run {text}"), }); return; } let driver = self.driver(); if driver.between_turns() { let _ = self.sink.send(Event::CommandSent { id, text }); command.apply(driver.as_ref()); return; } let _ = self.sink.send(Event::CommandQueued { id: id.clone(), text, }); self.waiting.lock().unwrap().push_back((id, command)); } /// The turn ended, so the oldest waiting command can go. One, not all /// of them: running a command starts a turn of its own, and the next /// boundary is where the one after it belongs. /// /// Asks the driver again rather than trusting the idle that called this. /// The recorded idle is a moment in the past by the time it gets here, /// and the driver may have started something since -- a turn the CLI /// began by itself, which it does: a background task finishing makes it /// pick the conversation back up with nothing written to it. fn take_one(&self) { let driver = self.driver(); if !driver.between_turns() { return; } let Some((id, command)) = self.waiting.lock().unwrap().pop_front() else { return; }; let _ = self.sink.send(Event::CommandSent { id, text: command.label(), }); command.apply(driver.as_ref()); } /// Gives up on everything held, because the session cannot run them. /// /// Reported rather than dropped, for the reason the message queue in /// `claude.rs` reports its own: somebody asked for these and nothing /// else would ever say they did not happen. fn abandon(&self, why: &str) { let lost: Vec = self .waiting .lock() .unwrap() .drain(..) .map(|(_, command)| command.label()) .collect(); if lost.is_empty() { return; } let _ = self.sink.send(Event::Error { message: format!("{why}, so {} never ran", lost.join(" and ")), }); } } /// The pump-maintained view of a session, read by the list endpoint. /// `model` also lives here (not in the immutable meta) because it can /// change mid-session via `set_model`. struct Shared { status: Mutex, /// What this conversation is called. Here rather than in `meta` for /// the same reason the model is: `meta` is how the session was /// *launched*, so reporting a name from it would show the one a /// rename had already replaced. title: Mutex, last_activity: Mutex, model: Mutex>, /// Beside the model and for the same reason: `meta` is the shape the /// session was *launched* with, so reporting from it would show the /// mode a change had already replaced. permission_mode: Mutex>, /// How much context this session is holding. /// /// Kept here because only the pump sees every event, and reported on /// the session row so a phone opening a long conversation has the real /// figure rather than whatever its newest page happens to mention. context_tokens: Mutex>, /// Whether this session's attention-wanting moments are announced. /// /// Mirrored out of the config so the pump can read it without taking /// the manager's lock -- the pump runs underneath the manager and /// reaching back up for a field would invert that. `set_session_notify` /// writes both, in that order, which is the same shape every other /// live-and-persisted setting here uses. notify: Mutex, /// How many events this session has ever recorded. /// /// Only the import sync reads it, and only to answer one question: /// "did *we* write anything since I last looked?" A session and a /// terminal append to the same file, so that is the whole of what /// separates lines worth replaying from lines already shown. Status /// cannot answer it -- a turn that starts and finishes between two /// polls is idle at both, and its output then gets replayed on top of /// itself. written: Mutex, } impl LiveSession { /// Whatever is driving this session now -- see [`DriverCell`]. fn driver(&self) -> Arc { self.driver.lock().unwrap().clone() } /// Hands the user's message to the driver, which records it in the /// transcript by reporting that it has taken it -- see `MessageTaken`. /// /// The message is deliberately not recorded here. Sent into a running /// turn it waits, and writing it down on the way past would put it /// above output that happened before the session ever saw it. pub fn send_message(&self, text: String, images: Vec) { // The attachments ride *on* the message rather than as `Image` // events emitted just before it. They used to be the latter, which // drew a person's screenshot as a row floating above the bubble // that sent it, and left the phone inferring from adjacency which // message an image went with -- a thing the sender already knew. self.driver().send_user_message(text, images); } pub fn answer_question(&self, question_id: &str, answers: &[String]) { let _ = self.sink.send(Event::Answered { id: question_id.to_string(), answers: answers.to_vec(), }); self.driver().answer_question(question_id, answers); } /// Asks the session to run a command on itself, now or at the next /// boundary. See [`Commands`] for why it may not be now. pub fn run_command(&self, command: SessionCommand) { self.commands .submit(command, *self.shared.status.lock().unwrap()); } pub fn interrupt(&self) { self.driver().interrupt(); } /// Leaves this session's process running and stops attending to it, /// for a server that is going away and means to come back. See /// [`Driver::detach`]. pub fn detach(&self) { self.driver().detach(); } /// Compacts at the next boundary. Through the command queue like /// every other instruction to the session, so pressing it during a /// turn holds rather than writing into that turn. pub fn compact(&self) { self.run_command(SessionCommand::Compact); } pub fn subscribe(&self) -> broadcast::Receiver { self.events.subscribe() } pub fn transcript_path(&self) -> &Path { &self.transcript_path } /// The session's directory (attachments in, produced files out live in /// `attachments/` and `files/` under it). pub fn dir(&self) -> &Path { self.transcript_path .parent() .expect("transcript lives in the session dir") } /// Stores one uploaded attachment, returning the id `POST /message` /// references it by. Removed with the session directory on delete -- /// the same path out as everything else in it. pub fn save_attachment(&self, bytes: &[u8], content_type: &str) -> Result { // An unrecognized type is almost always a phone photo whose // content type the picker didn't set; jpg is the useful guess. let extension = crate::media::extension_for(content_type).unwrap_or("jpg"); let name = format!("{}.{extension}", random_hex()); let dir = self.dir().join("attachments"); wg_app_link::private::create_dir(&dir)?; std::fs::write(dir.join(&name), bytes) .with_context(|| format!("write attachment {name}"))?; Ok(name) } /// `setup_name` is passed in rather than stored: only the manager /// holds the config, and the label can change under a running session. /// `kind` rather than the facts derived from it: two of this row's /// fields are answers about the provider's *kind*, and passing them /// separately meant every caller deriving each one and a third arriving /// as a third parameter. `None` where the provider has been edited away, /// which is a session that cannot run -- so both answers are the /// cautious one rather than a guess. fn info(&self, setup_name: &str, imported: bool, kind: Option) -> SessionInfo { SessionInfo { id: self.meta.id.clone(), provider: self.meta.provider.clone(), setup: self.meta.setup.clone(), setup_name: setup_name.to_string(), title: self.shared.title.lock().unwrap().clone(), model: self.shared.model.lock().unwrap().clone(), permission_mode: self.shared.permission_mode.lock().unwrap().clone(), context_tokens: *self.shared.context_tokens.lock().unwrap(), notify: *self.shared.notify.lock().unwrap(), max_image_edge: kind.and_then(DriverKind::max_image_edge), imported, keeps_own_transcript: kind.is_some_and(DriverKind::keeps_own_transcript), cwd: self.meta.cwd.clone(), status: *self.shared.status.lock().unwrap(), last_activity: *self.shared.last_activity.lock().unwrap(), created: self.meta.created, } } } struct Inner { config: Config, live: HashMap>, } pub struct SessionManager { config_path: PathBuf, /// Per-session directories (transcript, attachments, produced images) /// live under here, each named by session id. data_dir: PathBuf, /// Downloaded GGUF models, shared by every session that names one -- /// which is why they live beside the session directories rather than /// inside one. models_dir: PathBuf, /// Where every session's pump sends what a phone should be told about. /// Held here rather than per session for the reason /// [`SessionManager::subscribe_notifications`] gives. notifications: broadcast::Sender, inner: RwLock, } impl SessionManager { /// Loads the config and relaunches a driver for every persisted /// session -- for the real drivers that is the `--resume`/session-file /// crash-recovery story; the echo driver just starts fresh over the /// same transcript. Must be called inside a tokio runtime (each /// session spawns its event pump). pub fn new(config_path: PathBuf, data_dir: PathBuf, models_dir: PathBuf) -> Result { let config = Config::load(&config_path)?; wg_app_link::private::create_dir(&data_dir)?; let (notifications, _) = broadcast::channel(NOTIFICATION_BUFFER); let mut live = HashMap::new(); for meta in &config.sessions { // One unlaunchable session -- a corrupt transcript, an // unreachable ssh host, a provider that was edited away -- // shows as exited rather than taking the whole server down // with it, and can still be deleted from the phone. match resolve(&config, meta).and_then(|(setup, provider)| { launch( meta.clone(), &setup, &provider, &data_dir, &models_dir, None, notifications.clone(), ) }) { Ok(session) => { live.insert(meta.id.clone(), session); } Err(err) => { tracing::error!("couldn't relaunch session {}: {err:#}", meta.id); } } } let manager = Self { config_path, data_dir, models_dir, notifications, inner: RwLock::new(Inner { config, live }), }; Ok(manager) } /// Writes this machine into a config that has no setups, with the /// providers actually found on it. /// /// Discovered rather than assumed. Until 2026-08-28 this wrote a /// `claude-cli` provider unconditionally, so a fresh install on a /// machine without `claude` -- which is every machine but the dev VM /// -- offered a spawn option that could not work, and said so with the /// same confidence as a provider that had been checked for. Providers /// are discovered by asking the machine, and the local machine is not /// an exception to that. /// /// A discovery that fails seeds only `echo`, which is true wherever /// this server runs, and says so in the log. Seeding the hardcoded /// list on failure would be the original bug with an extra step, and /// seeding nothing would leave a fresh install with nothing to prove /// the pipe with. pub async fn seed_setup(&self) -> Result<()> { if !self.inner.read().unwrap().config.setups.is_empty() { return Ok(()); } let providers = match crate::setups::discover(&transport::Transport::Here).await { Ok(found) => found, Err(err) => { tracing::warn!( "couldn't ask this machine what it has ({err}); seeding {} only -- \ re-probe the setup from the app once that is fixed", crate::config::ECHO_PROVIDER ); vec![Config::echo_provider()] } }; let names: Vec<&str> = providers.iter().map(|p| p.name.as_str()).collect(); let mut inner = self.inner.write().unwrap(); if !inner.config.setups.is_empty() { return Ok(()); } let mut candidate = inner.config.clone(); candidate.setups.push(Config::seed(providers.clone())); candidate.save(&self.config_path)?; inner.config = candidate; tracing::info!( "no setups configured -- added \"{}\" with: {}", crate::config::LOCAL_SETUP, names.join(", ") ); Ok(()) } /// The one path by which the config changes. /// /// Clone, apply, save, and only then commit: a failed write leaves /// what was already there and reports why, so what this server /// believes and what is on disk cannot come apart. The ordering is /// the whole trick -- mutating in place and then saving would leave a /// server that had accepted a change nothing on disk records. fn update(&self, apply: impl FnOnce(&mut Config) -> Result) -> Result { let mut inner = self.inner.write().unwrap(); let mut candidate = inner.config.clone(); let outcome = apply(&mut candidate)?; candidate.save(&self.config_path)?; inner.config = candidate; Ok(outcome) } /// Adds a machine with the providers it was found to have. /// /// `providers` comes from probing rather than from the caller (see /// `crate::setups`), which is why this takes them as an argument: the /// probe is async and this is not, so the route does the asking and /// this does the writing. pub fn add_setup( &self, name: &str, ssh: Option, providers: Vec, ) -> Result { let name = name.trim().to_string(); if name.is_empty() { bail!("a setup needs a name"); } self.update(|config| { if config.setup_named(&name).is_some() { bail!("there is already a setup called \"{name}\""); } // Ids are derived once and then fixed, so a label can be // edited later without orphaning the sessions that named it. let mut id = crate::setups::id_from(&name); while config.setup(&id).is_some() { id = format!("{id}-{}", &random_hex()[..4]); } let setup = SetupConfig { id, name: name.clone(), ssh, providers, }; config.setups.push(setup.clone()); Ok(setup) }) } /// Renames a machine, or replaces what was discovered on it. pub fn update_setup( &self, id: &str, name: Option<&str>, providers: Option>, ) -> Result { self.update(|config| { if let Some(name) = name { let name = name.trim(); if name.is_empty() { bail!("a setup needs a name"); } if config.setups.iter().any(|s| s.name == name && s.id != id) { bail!("there is already a setup called \"{name}\""); } } let setup = config .setups .iter_mut() .find(|setup| setup.id == id) .with_context(|| format!("no setup with id \"{id}\""))?; if let Some(name) = name { setup.name = name.trim().to_string(); } if let Some(providers) = providers { setup.providers = providers; } Ok(setup.clone()) }) } /// Removes a machine, provided nothing is still running on it. /// /// Refused rather than cascaded: deleting a machine should not /// silently kill conversations, and the person asking is better placed /// to decide which of those sessions they still want. pub fn delete_setup(&self, id: &str) -> Result<()> { self.update(|config| { if config.setup(id).is_none() { bail!("no setup with id \"{id}\""); } let using: Vec<&str> = config .sessions .iter() .filter(|session| session.setup == id) .map(|session| session.title.as_str()) .collect(); if !using.is_empty() { bail!( "{} session(s) still run on it: {}. Delete them first.", using.len(), using.join(", "), ); } config.setups.retain(|setup| setup.id != id); Ok(()) }) } pub fn tokens(&self) -> Vec { self.inner.read().unwrap().config.tokens.clone() } /// Replaces the enrolled token list. With one device this is rotation: /// the old hash is invalidated the moment the new config is saved. pub fn set_tokens(&self, tokens: Vec) -> Result<()> { let mut inner = self.inner.write().unwrap(); let mut candidate = inner.config.clone(); candidate.tokens = tokens; candidate.save(&self.config_path)?; inner.config = candidate; Ok(()) } /// Lets go of every session's process, for a server that is going /// away and means to adopt them again when it comes back. /// /// Deliberately not a shutdown, and this is the load-bearing half of /// it: a backend restart -- a rebuild, a service restart, a crash -- /// must not end a turn somebody is waiting on. Each process keeps its /// record in the session directory, and `launch` finds it there rather /// than starting a second one against the same conversation. /// /// What this did before was ask them all to stop and then exit /// immediately, which stopped nothing reliably -- the grace timer died /// with the runtime -- and orphaned whatever survived with nothing /// written down to find it by. Processes leaked either way; what is /// different now is that they are left on purpose and can be picked /// back up. pub fn detach_all(&self) { let inner = self.inner.read().unwrap(); for session in inner.live.values() { session.detach(); } tracing::info!( "left {} session process(es) running to be reattached to", inner.live.len() ); } /// The session already driving `source`, if there is one. /// /// Two `--resume` processes on one transcript each see the other's /// writes as work done elsewhere and replay them, so both sessions /// show a conversation neither is having -- worse than a refusal. /// /// Two ways to already be driving one, and only the first used to /// count. An **imported** session records a cursor naming the file it /// follows. A session this app **spawned** has no cursor at all, but /// it has a resume token, which is the CLI's own id for the /// conversation and is exactly the thing being asked about. Matching /// only the cursor left every spawned session looking like somebody /// else's: it appeared in the import list, marked as in use, telling /// the reader to go and close it somewhere -- and the somewhere was /// this app. pub fn session_driving(&self, source: &str) -> Option { let inner = self.inner.read().unwrap(); inner.config.sessions.iter().find_map(|meta| { let dir = self.data_dir.join(&meta.id); let followed = import::read_cursor(&dir).and_then(|cursor| { cursor .path .rsplit('/') .next() .and_then(|name| name.strip_suffix(".jsonl")) .map(str::to_string) }); let resuming = claude::read_resume_token(&dir); (followed.as_deref() == Some(source) || resuming.as_deref() == Some(source)) .then(|| meta.id.clone()) }) } /// Every session, in config order, with live status joined in. A /// session that failed to relaunch reports as exited. pub fn sessions(&self) -> Vec { let inner = self.inner.read().unwrap(); inner .config .sessions .iter() .map(|meta| match inner.live.get(&meta.id) { Some(session) => session.info( label_of(&inner.config, &meta.setup), import::read_cursor(&self.data_dir.join(&meta.id)).is_some(), kind_of(&inner.config, &meta.setup, &meta.provider), ), None => SessionInfo { id: meta.id.clone(), setup: meta.setup.clone(), setup_name: label_of(&inner.config, &meta.setup).to_string(), provider: meta.provider.clone(), title: meta.title.clone(), model: meta.model.clone(), permission_mode: meta.permission_mode.clone(), context_tokens: None, max_image_edge: kind_of(&inner.config, &meta.setup, &meta.provider) .and_then(DriverKind::max_image_edge), notify: meta.notify, imported: import::read_cursor(&self.data_dir.join(&meta.id)).is_some(), keeps_own_transcript: keeps_own_transcript( &inner.config, &meta.setup, &meta.provider, ), cwd: meta.cwd.clone(), status: status_of_unlaunched(&self.data_dir.join(&meta.id)), last_activity: meta.created, created: meta.created, }, }) .collect() } /// Every session's attention-wanting moments, on one stream. /// /// One connection for the whole backend rather than one per session: /// the phone subscribes to this while showing no session at all, and a /// connection per session would mean opening one for every session that /// exists in order to hear about any of them. pub fn subscribe_notifications(&self) -> broadcast::Receiver { self.notifications.subscribe() } pub fn session(&self, id: &str) -> Option> { self.inner.read().unwrap().live.get(id).cloned() } /// Every provider this server offers, built-in echo included. /// Every machine this server can run something on, each with what it /// can run. One list rather than two, because the pair is the choice. pub fn setups(&self) -> Vec { self.inner.read().unwrap().config.setups.clone() } pub fn spawn_session(&self, spec: SpawnSpec) -> Result { self.spawn_seeded(spec, None) } /// Spawns a session that continues one the machine already had. /// /// The same path as any other spawn, with a [`Seed`] written into the /// session directory before the driver starts -- which is all an /// import is, because `claude.rs` already resumes when it finds a /// resume token. A separate spawn path would be a second way to start /// a session, and the driver would have to learn which one it was. pub fn spawn_imported(&self, spec: SpawnSpec, seed: Seed) -> Result { self.spawn_seeded(spec, Some(seed)) } fn spawn_seeded(&self, spec: SpawnSpec, seed: Option) -> Result { let mut inner = self.inner.write().unwrap(); let setup = inner .config .setup(&spec.setup) .with_context(|| { format!( "no setup with id \"{}\" -- configured: {}", spec.setup, // Ids, since that is what was looked up. Listing the // labels made the failure read as a contradiction: // "no setup named X -- configured: X", when X was a // label and the id was something else. names(inner.config.setups.iter().map(|s| s.id.as_str())), ) })? .clone(); let provider = setup .provider(&spec.provider) .with_context(|| { format!( "setup \"{}\" has no provider named \"{}\" -- it offers: {}", spec.setup, spec.provider, names(setup.providers.iter().map(|p| p.name.as_str())), ) })? .clone(); let id = unique_id(&inner.config); let title = spec .title .filter(|title| !title.trim().is_empty()) .unwrap_or_else(|| format!("{} session", provider.name)); let meta = SessionConfig { id: id.clone(), setup: setup.id.clone(), provider: provider.name.clone(), title, // No model unless one was chosen. This used to fall back to // the provider's first listed model, which sounds like a // default and is not one: that list is a shortcut for the // spawn screen, written in whatever order somebody typed it, // and its first entry happened to be `fable`. Every session // spawned without a model -- every import, since importing // asks for none -- silently became a fable session. Absent // means absent, and the CLI then uses whatever the person // configured for themselves. model: spec.model, cwd: spec.cwd, permission_mode: spec.permission_mode, params: spec.params, // On by default -- see `SessionConfig::notify`. Not offered at // spawn: a session's first turn is exactly the one somebody is // waiting for, and a switch on the spawn screen would be a // decision asked before there is anything to decide about. notify: true, created: now(), }; let session = launch( meta.clone(), &setup, &provider, &self.data_dir, &self.models_dir, seed, self.notifications.clone(), )?; let mut candidate = inner.config.clone(); candidate.sessions.push(meta); if let Err(err) = candidate.save(&self.config_path) { // The path out of everything the launch created, taken in the // same change: drop the session and its directory so a failed // save leaves no orphan. drop(session); let _ = std::fs::remove_dir_all(self.data_dir.join(&id)); return Err(err); } inner.config = candidate; // Whether this one was seeded, which is the same question the // listing asks of the directory a moment later. let info = session.info( &setup.name, import::read_cursor(&self.data_dir.join(&id)).is_some(), Some(provider.kind), ); inner.live.insert(id, session); Ok(info) } /// Changes a session's model: persisted (so a respawn keeps it and the /// list shows it) and handed to the driver, which switches in place /// where its dialect can. Through the manager, not the session, so the /// config and the live view can't disagree. /// Changes how much a session asks before acting, live and persisted. /// /// Alongside the model rather than folded into it: they are set at the /// same moment and by the same screen, but they answer different /// questions, and a caller changing one must not have to restate the /// other. pub fn set_session_permission_mode(&self, id: &str, mode: &str) -> Result<()> { let mut inner = self.inner.write().unwrap(); if !inner.config.sessions.iter().any(|meta| meta.id == id) { bail!("no session {id}"); } let mut candidate = inner.config.clone(); for meta in candidate.sessions.iter_mut().filter(|meta| meta.id == id) { meta.permission_mode = Some(mode.to_string()); } candidate.save(&self.config_path)?; inner.config = candidate; if let Some(session) = inner.live.get(id) { // Asked for, not recorded: what the session is actually set to // comes back as an `Event::Settings` if the driver makes the // change, and as an error if it cannot. The config above is a // different question -- what to launch this session with next // time -- and it is answered by the request. session.driver().set_permission_mode(mode); } Ok(()) } /// Turns this session's notifications on or off, live and persisted. /// /// Both, in that order, for the reason every setting here writes both: /// the config decides what a restart believes and the live copy decides /// what the running pump does, and a change that lands in one of them is /// a switch that moves back on its own. /// /// Nothing is told to the driver. Unlike the model or the permission /// mode, this changes nothing about how the session runs -- it is about /// who gets told, and the session is not the one being told. pub fn set_session_notify(&self, id: &str, notify: bool) -> Result<()> { let mut inner = self.inner.write().unwrap(); if !inner.config.sessions.iter().any(|meta| meta.id == id) { bail!("no session {id}"); } let mut candidate = inner.config.clone(); for meta in candidate.sessions.iter_mut().filter(|meta| meta.id == id) { meta.notify = notify; } candidate.save(&self.config_path)?; inner.config = candidate; if let Some(session) = inner.live.get(id) { *session.shared.notify.lock().unwrap() = notify; } Ok(()) } /// Renames a session: persisted, shown, and passed on to whatever is /// running it. /// /// The name is this server's own -- it is what a phone lists, it /// exists before any process does, and every provider has one. So /// unlike the model and the permission mode, this is settled here and /// the driver is *told*, rather than asked and believed: see /// [`Driver::set_title`]. pub fn rename_session(&self, id: &str, title: &str) -> Result<()> { let title = title.trim(); // An empty name is not a name, and it is what a cleared field // sends. Refused rather than accepted and papered over with the // provider's name, which would look like the rename was ignored. if title.is_empty() { bail!("a session needs a name"); } let mut inner = self.inner.write().unwrap(); if !inner.config.sessions.iter().any(|meta| meta.id == id) { bail!("no session {id}"); } let mut candidate = inner.config.clone(); for meta in candidate.sessions.iter_mut().filter(|meta| meta.id == id) { meta.title = title.to_string(); } candidate.save(&self.config_path)?; inner.config = candidate; if let Some(session) = inner.live.get(id) { // The name is this server's and changes now. Telling whatever // runs the session is a command, and commands wait for the // turn to end -- so the list shows the new name immediately // and the CLI is told at the next boundary. *session.shared.title.lock().unwrap() = title.to_string(); session.run_command(SessionCommand::SetTitle(title.to_string())); } Ok(()) } pub fn set_session_model(&self, id: &str, model: &str) -> Result<()> { let mut inner = self.inner.write().unwrap(); if !inner.config.sessions.iter().any(|meta| meta.id == id) { bail!("no session {id}"); } let mut candidate = inner.config.clone(); for meta in candidate.sessions.iter_mut().filter(|meta| meta.id == id) { meta.model = Some(model.to_string()); } candidate.save(&self.config_path)?; inner.config = candidate; if let Some(session) = inner.live.get(id) { // See `set_session_permission_mode`: the driver reports what // it is set to, this only asks. session.driver().set_model(model); } Ok(()) } /// Ends this session's process, leaving the session -- its transcript, /// its place in the list, everything a phone is watching -- exactly /// where it is. [`SessionManager::start_session`] is the way back. /// /// The signal is all this does. Whether the process actually went, what /// it said on the way out, and the `Exited` that follows are reported by /// the path a session that died on its own already takes: the driver's /// own reader notices within a poll, drains what was still unread, and /// records it. Announcing it from here would be this side's guess /// arriving ahead of the measurement, and it would be wrong for the five /// seconds a process that ignores SIGTERM keeps running. /// /// Deliberately not routed through the driver. The record is the /// session's rather than any dialect's -- `session::process` writes it /// for every provider that has a process at all -- so asking it here /// stops a session whose driver is in no state to be asked, and adds no /// method a new driver could implement wrongly. pub fn stop_session(&self, id: &str) -> Result<()> { if !self .inner .read() .unwrap() .config .sessions .iter() .any(|meta| meta.id == id) { bail!("no session {id}"); } // Three answers, and they are three different things to tell // somebody: it is running (stop it), it is not (nothing to do), and // nobody could find out (nothing was signalled, and saying "nothing // is running" would be inventing the answer). let record = match process::recorded(&self.data_dir.join(id)) { Some((record, process::Liveness::Alive)) => record, Some((_, process::Liveness::Unknown)) => bail!( "this machine won't say whether this session's process is still running, so it \ wasn't signalled" ), Some((_, process::Liveness::Dead)) | None => { bail!("this session has no process running") } }; tracing::info!("stopping session {id} (pid {})", record.pid); process::stop(&record, process::STOP_GRACE); Ok(()) } /// Starts a process for a session whose process has ended, continuing /// the same conversation -- for Claude Code, the `--resume` that crash /// recovery already uses. /// /// Only the driver is new. The transcript, the event pump and the stream /// every open phone is reading stay as they were, so this is not a /// reconnect for anybody watching -- and there is still exactly one /// writer of the transcript, which relaunching the whole session would /// not be. /// /// Refused unless the session is *known* to have exited. `Unknown` means /// nobody could find out whether the process is alive, and starting one /// on that is precisely the second-CLI-on-one-conversation fault that /// `session::process` exists to prevent. pub fn start_session(&self, id: &str) -> Result<()> { let mut inner = self.inner.write().unwrap(); let meta = inner .config .sessions .iter() .find(|meta| meta.id == id) .with_context(|| format!("no session {id}"))? .clone(); let existing = inner.live.get(id).cloned(); let status = match &existing { Some(session) => *session.shared.status.lock().unwrap(), None => status_of_unlaunched(&self.data_dir.join(id)), }; match status { SessionStatus::Exited => {} SessionStatus::Unknown => bail!( "this machine won't say whether this session's process is still running, so \ nothing was started" ), _ => bail!("this session is already running"), } // Fresh from the config, like every other launch: a model or a // permission mode changed while the session was stopped is what it // starts with. let (setup, provider) = resolve(&inner.config, &meta)?; let session = match existing { Some(session) => { *session.driver.lock().unwrap() = make_driver( &meta, &setup, &provider, &self.models_dir, session.dir(), session.transcript_path(), &session.sink, )?; session } // Nothing is live for this one -- a session whose launch failed // when the server started, which has no pump either. That is the // whole of `launch`, and the same call the server start makes. None => { let session = launch( meta, &setup, &provider, &self.data_dir, &self.models_dir, None, self.notifications.clone(), )?; inner.live.insert(id.to_string(), Arc::clone(&session)); session } }; // The recorded status is `Exited` and this has just made it untrue. // Said here because nothing else will say it: a CLI that has been // given no work writes nothing, so the session would sit at // `Exited` -- refusing every command, refusing every message, and // showing a phone an offer to start a second process against the // conversation this one is already running. let _ = session.sink.send(Event::Status { state: SessionStatus::Idle, }); Ok(()) } /// Kills the process, releases everything the spawn created, and /// deletes the transcript and files -- the complete path out. pub fn delete_session(&self, id: &str) -> Result<()> { let mut inner = self.inner.write().unwrap(); if !inner.config.sessions.iter().any(|meta| meta.id == id) { bail!("no session {id}"); } let mut candidate = inner.config.clone(); candidate.sessions.retain(|meta| meta.id != id); candidate.save(&self.config_path)?; inner.config = candidate; if let Some(session) = inner.live.remove(id) { // Stopped, not detached: this is the one exit where the // process must not survive, because the conversation it // belongs to is being removed. See `Driver::stop`. session.driver().stop(); } let dir = self.data_dir.join(id); if dir.exists() { std::fs::remove_dir_all(&dir).with_context(|| format!("remove {}", dir.display()))?; } Ok(()) } } /// What to report for a session that is in the config but has no live /// entry -- one that failed to relaunch, or whose process this server /// never took charge of. /// /// This said `Exited` for all of them, which is the enumeration mistake in /// its most consequential form. `Exited` reads as "this conversation is /// over", and the thing a reader does about it is start a new session -- /// which, if the process is in fact still running, is a second CLI against /// a conversation that already has one. That is the fault the whole /// `process` module exists to prevent, arriving through the status field. /// /// So it is only said when the process is known to be gone. A record that /// cannot be checked reports `Unknown`, and a record that is still alive /// reports `Unknown` too: this server is not driving it, so it genuinely /// does not know what it is doing -- and that is worth a word that means /// "wait", not one that means "act". fn status_of_unlaunched(session_dir: &Path) -> SessionStatus { match process::recorded(session_dir) { // Nothing was ever recorded: an echo session, or one whose // process was stopped and cleaned up. Gone, and known to be. None => SessionStatus::Exited, Some((_, process::Liveness::Dead)) => SessionStatus::Exited, Some((_, process::Liveness::Alive | process::Liveness::Unknown)) => SessionStatus::Unknown, } } /// The provider and host a session's config names, or a message saying /// which one is missing. Both are looked up fresh at every launch, so /// editing either takes effect on the next respawn. fn resolve(config: &Config, meta: &SessionConfig) -> Result<(SetupConfig, ProviderConfig)> { let setup = config .setup(&meta.setup) .with_context(|| format!("no setup named \"{}\"", meta.setup))?; let provider = setup.provider(&meta.provider).with_context(|| { format!( "setup \"{}\" has no provider named \"{}\"", meta.setup, meta.provider ) })?; Ok((setup.clone(), provider.clone())) } /// A setup's current label, or its id when the setup has been deleted -- /// which is what a session left behind by a removed machine shows, and is /// better than an empty column or a guess at what it used to be called. fn label_of<'a>(config: &'a Config, id: &'a str) -> &'a str { config.setup(id).map_or(id, |setup| setup.name.as_str()) } /// Whether this session's provider keeps the conversation somewhere this /// app's delete cannot reach. /// /// False when the provider can't be found, which is the safe way round: a /// setup or provider removed from the config leaves sessions naming one /// that is gone, and the warning that then shows is the strong one. Saying /// "this can be brought back" on no evidence is the answer that loses /// somebody's conversation. fn keeps_own_transcript(config: &Config, setup: &str, provider: &str) -> bool { kind_of(config, setup, provider).is_some_and(DriverKind::keeps_own_transcript) } /// What a session's provider is, for the questions answered by its *kind* /// rather than by its name. `None` for a provider that has been edited away, /// which is a session that cannot run at all. fn kind_of(config: &Config, setup: &str, provider: &str) -> Option { config .setup(setup) .and_then(|setup| setup.providers.iter().find(|it| it.name == provider)) .map(|provider| provider.kind) } /// Names for a failure message: what there is, so the reader can see what /// they meant instead of only that they were wrong. fn names<'a>(all: impl Iterator) -> String { let all: Vec<_> = all.collect(); if all.is_empty() { "none".to_string() } else { all.join(", ") } } /// 8 random bytes, hex -- short enough for a URL, unique enough forever at /// this scale. pub fn random_hex() -> String { use rand::Rng; let mut bytes = [0u8; 8]; rand::rng().fill_bytes(&mut bytes); bytes.iter().map(|b| format!("{b:02x}")).collect() } /// A [`random_hex`] id not already taken -- checked out of caution. fn unique_id(config: &Config) -> String { loop { let id = random_hex(); if !config.sessions.iter().any(|meta| meta.id == id) { return id; } } } /// Creates the session directory, opens its transcript (continuing the /// sequence numbering if one exists), starts the driver, and spawns the /// event pump connecting them. /// Keeps an imported session's transcript level with the file the CLI /// writes. /// /// Both this app and a terminal append to one file -- `--resume` continues /// the same transcript rather than forking, measured rather than assumed /// -- so the only hard question is which new lines are *ours*. They are /// already in the transcript, having arrived through the driver, and /// replaying them shows every message twice. /// /// Answered by counting what this session has recorded rather than by /// looking at its status. Status is the obvious signal and it is wrong: a /// turn that begins and ends between two polls reads as idle at both, and /// its output is then replayed on top of itself. The count cannot miss /// that, because the events went through the same pump either way. /// /// Its path out: the sink belongs to the session, so once that is dropped /// every send fails and this returns. Nothing else has to remember it. fn spawn_import_sync( transport: Transport, dir: PathBuf, mut cursor: import::Cursor, sink: EventSink, shared: Arc, ) { tokio::spawn(async move { // What the session had recorded when the cursor was last correct. let mut written_at_cursor = *shared.written.lock().unwrap(); loop { tokio::time::sleep(import::SYNC_INTERVAL).await; if sink.is_closed() { return; } let Ok(lines) = import::line_count(&transport, &cursor.path).await else { // A file that cannot be counted is not worth reporting: it // is usually a machine briefly away, and the next poll asks // again. continue; }; let written_now = *shared.written.lock().unwrap(); if written_now != written_at_cursor { // This session produced something since the cursor was set, // so the new lines are its own. Skip them and resynchronise. cursor.lines = lines; written_at_cursor = written_now; import::write_cursor(&dir, &cursor); continue; } if lines <= cursor.lines { continue; } match import::replay_after(&transport, &cursor.path, cursor.lines, &dir).await { Ok(events) => { tracing::info!( "{} grew by {} lines with nothing from here; replaying {} events", cursor.path, lines - cursor.lines, events.len(), ); let count = events.len() as u64; for event in events { if sink.send(event).is_err() { return; } } cursor.lines = lines; // The pump is about to record exactly these, so account // for them rather than reading a count that may not have // caught up yet. written_at_cursor = written_now + count; import::write_cursor(&dir, &cursor); } Err(err) => tracing::warn!("couldn't read new lines of {}: {err:#}", cursor.path), } } }); } /// What an imported session starts life with: the token that makes the CLI /// continue rather than begin, and the conversation so far. pub struct Seed { /// The CLI's own session id, written where `claude.rs` looks for it. pub resume: String, /// Where that session's file is and how much of it has been shown, so /// the session can keep itself up to date afterwards. pub cursor: import::Cursor, /// The tail of that session's file, as the raw JSONL. /// /// Turned into events in `launch`, not before, because doing so writes /// out the images the records carry and that needs the session /// directory to write them into -- which does not exist until the /// session does. The CLI reads the real file itself, so this only ever /// decides what the *reader* sees. pub records: String, } fn launch( meta: SessionConfig, setup: &SetupConfig, provider: &ProviderConfig, data_dir: &Path, models_dir: &Path, seed: Option, notifications: broadcast::Sender, ) -> Result> { let dir = data_dir.join(&meta.id); wg_app_link::private::create_dir(&dir)?; let transcript_path = dir.join("transcript.jsonl"); let mut transcript = Transcript::open(&transcript_path)?; // Before the driver starts, so the token is there when it looks and // the history is already in the transcript a phone will read. if let Some(seed) = seed { claude::write_resume_token(&dir, &seed.resume); import::write_cursor(&dir, &seed.cursor); let at = now(); for event in import::events_from(&seed.records, &dir) { transcript.append(event, at)?; } } let (sink, source) = mpsc::unbounded_channel(); let (events, _) = broadcast::channel(EVENT_BUFFER); let shared = Arc::new(Shared { // What it was last known to be doing, not an assumption. A driver // that has something to say corrects this within its first poll; // one adopting a process that has been quiet says nothing, and // this is then the only true answer available. status: Mutex::new(transcript.last_status().unwrap_or(SessionStatus::Idle)), title: Mutex::new(meta.title.clone()), // What the transcript last recorded, not the clock: this server has // just been told nothing, and `now()` claimed every relaunched // session had been active this instant -- see // `Transcript::last_activity`. last_activity: Mutex::new(transcript.last_activity().unwrap_or_else(now)), model: Mutex::new(meta.model.clone()), permission_mode: Mutex::new(meta.permission_mode.clone()), context_tokens: Mutex::new(transcript.context_tokens()), notify: Mutex::new(meta.notify), written: Mutex::new(0), }); // Nothing here has measured this session's context: the transcript // predates the figure being recorded, or the last turn happened before // this server was watching. The CLI wrote it down at the time, so ask // its file rather than leaving the row saying "unknown" until somebody // sends a message. In the background, because it is a file read on a // machine that may be at the other end of an ssh connection, and a // server start must not wait on one. if provider.kind == DriverKind::ClaudeCli && shared.context_tokens.lock().unwrap().is_none() && let Some(session_id) = claude::read_resume_token(&dir) { let transport = Transport::for_setup(setup); let shared = Arc::clone(&shared); tokio::spawn(async move { if let Some(context) = import::context_of(&transport, &session_id).await { // Only if nothing else has answered in the meantime: a turn // that finished while this was in flight measured the // context after the one this read. let mut held = shared.context_tokens.lock().unwrap(); if held.is_none() { *held = Some(context); } } }); } // An imported session shares its transcript file with the CLI -- // `--resume` appends to the same one rather than forking, measured // rather than assumed -- so work done at a terminal belongs in this // session too, and arrives without anybody pressing anything. if let Some(cursor) = import::read_cursor(&dir) { spawn_import_sync( Transport::for_setup(setup), dir.clone(), cursor, sink.clone(), Arc::clone(&shared), ); } let driver = Arc::new(Mutex::new(make_driver( &meta, setup, provider, models_dir, &dir, &transcript_path, &sink, )?)); // The transcript's last word is what this session was doing when // something was last watching it, and building the driver above may have // just made it untrue: a session recorded as `Exited` with a process // running again is one this launch has started. Carrying `Exited` // forward is not merely stale -- it is the word that refuses every // command sent to the session, and the word that invites somebody to // start a *second* process against a conversation that already has one, // which is the fault `session::process` exists to prevent. It reached a // phone as a play button on a session that was already running. // // Idle is what is true: there is a process, and nothing has asked it for // anything. Written rather than announced, because nobody watched a // transition -- this is the state the session is being restored in, and // an event would put a status change in the transcript that never // happened. A record nobody could check stays as it was and is corrected // by the driver's first poll, which reports `Unknown` for it. { let mut status = shared.status.lock().unwrap(); if *status == SessionStatus::Exited && process::live(&dir).is_some() { *status = SessionStatus::Idle; } } let commands = Arc::new(Commands { driver: Arc::clone(&driver), sink: sink.clone(), waiting: Mutex::new(VecDeque::new()), }); tokio::spawn(pump( meta.id.clone(), transcript, source, Arc::clone(&shared), events.clone(), Arc::clone(&commands), notifications, )); Ok(Arc::new(LiveSession { meta, driver, commands, sink, events, transcript_path, shared, })) } /// Whatever runs this session's provider, pointed at the session's own /// directory and reporting into `sink`. /// /// Split out of [`launch`] because a session outlives its process: it is /// also what [`SessionManager::start_session`] builds when somebody starts a /// stopped session again. That path replaces the driver and nothing else, so /// it has to construct one the same way rather than becoming a second answer /// to "what runs this". fn make_driver( meta: &SessionConfig, setup: &SetupConfig, provider: &ProviderConfig, models_dir: &Path, dir: &Path, transcript_path: &Path, sink: &EventSink, ) -> Result> { Ok(match provider.kind { DriverKind::Echo => Arc::new(EchoDriver::new(sink.clone(), dir.to_path_buf())), DriverKind::LlamaCpp => Arc::new(LlamaDriver::launch( meta, provider, &Transport::for_setup(setup), models_dir, transcript_path, dir, sink.clone(), )?), DriverKind::ClaudeCli => Arc::new(ClaudeDriver::launch( meta, provider, &Transport::for_setup(setup), dir, sink.clone(), )?), }) } /// The one writer of a session's transcript: assigns sequence numbers, /// appends, updates the shared status/activity view, fans out. Ends when /// every sender is dropped -- i.e. when the session is deleted and its /// last in-flight task finishes. /// /// The appends are synchronous file writes from an async task, /// deliberately: each is one small line on a local disk, and funneling /// them through one task is what makes the sequence numbering safe. /// Whether this event tells anyone anything they do not already know. /// /// Only the two events that report state rather than something that /// happened can fail this: everything else is an occurrence, and an /// occurrence is news by existing. A `Settings` naming one field is /// judged on that field alone, since the other is not a claim that it is /// unset. fn is_news(event: &Event, shared: &Shared) -> bool { match event { Event::Status { state } => *shared.status.lock().unwrap() != *state, Event::Settings { model, permission_mode, } => { let model_changed = model.is_some() && *shared.model.lock().unwrap() != *model; let mode_changed = permission_mode.is_some() && *shared.permission_mode.lock().unwrap() != *permission_mode; model_changed || mode_changed } _ => true, } } /// Whether moving from `was` to `now` is worth interrupting somebody for. /// /// The asymmetry is the point. *Waiting on a person* is worth saying however /// the session got there -- it is a question that will sit unanswered until /// somebody sees it. *Finished* is only worth saying when this server /// watched the work happen: a session settling into idle because it was /// adopted at startup, or because a driver announced itself, is not news /// that anything ended, and sending it would put "finished" on the phone for /// every session in the config every time the backend restarts. fn notification_for(was: SessionStatus, now: SessionStatus) -> Option { match (was, now) { (_, SessionStatus::AwaitingInput) => Some(NotificationKind::AwaitingInput), (SessionStatus::Running | SessionStatus::Compacting, SessionStatus::Idle) => { Some(NotificationKind::Finished) } _ => None, } } async fn pump( id: String, mut transcript: Transcript, mut source: mpsc::UnboundedReceiver, shared: Arc, events: broadcast::Sender, commands: Arc, notifications: broadcast::Sender, ) { while let Some(event) = source.recv().await { let ts = now(); // Taking a message is how it enters the conversation, and the // conversation is what a phone renders -- so the event becomes the // message here rather than being carried alongside it. One rule // for where a user's message sits: where the session read it. let event = match event { Event::MessageTaken { id, text, images } => Event::UserMessage { id, text, images }, other => other, }; // Where the session row's figure comes from. Kept here rather than // at each driver because a clear and a compaction move it as much // as a turn does, and only the pump sees all three. { let mut context = shared.context_tokens.lock().unwrap(); *context = context_after(*context, &event); } // Nothing changed, so there is nothing to record. Both of these // repeat: an imported session reads the turn state off its file's // newest record on every sync and mostly finds the answer it found // last time, and the CLI restates its model and mode at every // `init`, which includes the one after every compaction. Recording // those would be a transcript entry, a broadcast and a // recomposition on every phone, several times a minute, to say // nothing at all. if !is_news(&event, &shared) { continue; } if let Event::Settings { model, permission_mode, } = &event { // The session's own account of what it is set to, which is // what the list and the session screen show. Not written // where the change is *asked for* -- see `Event::Settings`. if let Some(model) = model { *shared.model.lock().unwrap() = Some(model.clone()); } if let Some(mode) = permission_mode { *shared.permission_mode.lock().unwrap() = Some(mode.clone()); } } match transcript.append(event, ts) { Ok(entry) => { if let Event::Status { state } = &entry.event { // Read before it is overwritten: what makes a status // worth announcing is the transition, not the value. let was = std::mem::replace(&mut *shared.status.lock().unwrap(), *state); if let Some(kind) = notification_for(was, *state).filter(|_| *shared.notify.lock().unwrap()) { // No subscribers is the ordinary case -- nobody has // the app open -- and it is not an error. let _ = notifications.send(Notification { session_id: id.clone(), title: shared.title.lock().unwrap().clone(), kind, at: ts, }); } } *shared.last_activity.lock().unwrap() = ts; *shared.written.lock().unwrap() += 1; // The boundary a held command was waiting for, and the one // place that sees every driver's. Done after the status is // recorded, so the command that runs next sees an idle // session and goes out rather than queueing behind itself. match &entry.event { Event::Status { state: SessionStatus::Idle, } => commands.take_one(), Event::Status { state: SessionStatus::Exited, } => commands.abandon("this session's process has exited"), _ => {} } // No subscribers is fine; the transcript already has it. let _ = events.send(entry); } Err(err) => tracing::error!("transcript append failed: {err:#}"), } } } #[cfg(test)] mod tests { use super::*; use std::time::Duration; fn echo_spec() -> SpawnSpec { SpawnSpec { params: Default::default(), setup: crate::config::LOCAL_SETUP_ID.to_string(), provider: crate::config::ECHO_PROVIDER.to_string(), title: None, model: None, cwd: None, permission_mode: None, } } /// Reads events from `rx` until `stop` matches one (returning all seen /// so far) or five seconds pass (panicking with what was seen). async fn collect_until( rx: &mut broadcast::Receiver, mut stop: impl FnMut(&Event) -> bool, ) -> Vec { let mut seen = Vec::new(); let deadline = tokio::time::Instant::now() + Duration::from_secs(5); loop { let entry = tokio::time::timeout_at(deadline, rx.recv()) .await .unwrap_or_else(|_| panic!("timed out; events so far: {seen:?}")) .expect("event stream closed"); let done = stop(&entry.event); seen.push(entry); if done { return seen; } } } fn is_idle(event: &Event) -> bool { matches!( event, Event::Status { state: SessionStatus::Idle } ) } /// Collects one full echo turn: everything up to the idle that follows /// the turn's `UsageDelta`. Stopping at the first idle would be racy -- /// the driver emits an idle at construction, and a subscriber attached /// just before the pump processes it would stop there, mid-spawn. async fn collect_turn(rx: &mut broadcast::Receiver) -> Vec { let mut saw_usage = false; collect_until(rx, |event| { saw_usage |= matches!(event, Event::UsageDelta { .. }); saw_usage && is_idle(event) }) .await } /// Writes this machine into `config_path` with echo and nothing else. /// /// Explicit rather than letting the manager seed itself: seeding now /// asks the machine what it has, so a test that relied on it would /// pass or fail depending on whether `claude` happens to be installed /// on whoever is running it. Echo is the only provider that is true /// everywhere, and the only one these tests need. fn seed_echo_only(config_path: &std::path::Path) { Config { setups: vec![Config::seed(vec![Config::echo_provider()])], ..Config::default() } .save(config_path) .expect("seed config"); } /// Deleting an echo session ends the conversation; deleting a /// claude-cli one does not, because the CLI keeps its own transcript /// whether this app spawned the session or imported it. /// /// The delete confirmation is worded off this, so getting it backwards /// either loses a conversation somebody was told they could recover, /// or cries wolf about one they can. #[test] fn only_a_driver_that_keeps_its_own_record_survives_deletion() { assert!(DriverKind::ClaudeCli.keeps_own_transcript()); assert!(!DriverKind::Echo.keeps_own_transcript()); assert!(!DriverKind::LlamaCpp.keeps_own_transcript()); } /// A command sent to a session whose process is gone says so, rather /// than waiting for a boundary that will never come. /// /// Held commands drain at the next boundary, and an exited session has /// none -- so this used to leave a `/clear` in the queue forever, drawn /// on the phone as a waiting bubble with nothing to resolve it and /// nothing anywhere saying why. A *message* sent to the same session /// reported the exit at once, which is what made the silence on the /// command path visible: one session answered one and swallowed the /// other. /// /// `Unknown` still waits, deliberately: nobody could find out whether /// the process is there, and refusing on it would turn "we don't know" /// into "it's gone". #[test] fn a_command_is_refused_when_there_can_be_no_boundary() { let dir = tempfile::tempdir().expect("tempdir"); let (sink, mut events) = mpsc::unbounded_channel(); let commands = Commands { driver: Arc::new(Mutex::new(Arc::new(EchoDriver::new( sink.clone(), dir.path().to_path_buf(), )))), sink, waiting: Mutex::new(VecDeque::new()), }; // The driver announces itself when it is built; not what this is about. while events.try_recv().is_ok() {} commands.submit(SessionCommand::Clear, SessionStatus::Exited); assert!( matches!(events.try_recv(), Ok(Event::Error { .. })), "an exited session held the command instead of refusing it" ); assert!(commands.waiting.lock().unwrap().is_empty()); // Not exited and the driver is between turns, so it goes now. commands.submit(SessionCommand::Clear, SessionStatus::Unknown); assert!(matches!(events.try_recv(), Ok(Event::CommandSent { .. }))); } /// A command waits for the *driver* to be between turns, not for the /// recorded status to say idle. /// /// The two are the same fact seen at different moments, and only the /// driver's is current: it moves when a line is written, while the /// status moves when output comes back. Gating on the status meant two /// commands in a row both went out, the second landing inside the turn /// the first had started -- where the CLI reads it as text instead of /// running it, which looks exactly like nothing happening. #[tokio::test] async fn a_command_waits_for_the_driver_rather_than_the_recorded_status() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live"); let mut rx = session.subscribe(); // A turn long enough to submit into. session.send_message("/slow 2".to_string(), Vec::new()); collect_until(&mut rx, |event| { matches!( event, Event::Status { state: SessionStatus::Running } ) }) .await; session.run_command(SessionCommand::Clear); let held = collect_until(&mut rx, |event| { matches!( event, Event::CommandQueued { .. } | Event::CommandSent { .. } ) }) .await; assert!( matches!( held.last().map(|entry| &entry.event), Some(Event::CommandQueued { .. }) ), "a command went out into a running turn: {held:?}" ); // And it is released when the turn actually ends. let after = collect_until(&mut rx, |event| matches!(event, Event::CommandSent { .. })).await; assert!( after .iter() .any(|entry| matches!(entry.event, Event::CommandSent { .. })) ); } /// The two transitions worth interrupting somebody for, and the ones /// that look like them and are not. /// /// The idle cases are the whole reason this is a function rather than a /// pair of `if`s at the callsite. A session settles into idle for /// several reasons that are not "your work finished": it was adopted at /// startup, its driver announced itself, it came back from a state /// nobody could read. Announcing those would put "finished" on the phone /// for every session in the config every time the backend restarts, /// which is the failure that makes somebody turn the whole feature off. #[test] fn only_a_watched_turn_ending_counts_as_finished() { use NotificationKind::{AwaitingInput, Finished}; use SessionStatus::{Compacting, Exited, Idle, Running, Unknown}; // Waiting on a person is worth saying however it was reached: it // will sit unanswered until somebody is told. assert_eq!( notification_for(Running, SessionStatus::AwaitingInput), Some(AwaitingInput) ); assert_eq!( notification_for(Idle, SessionStatus::AwaitingInput), Some(AwaitingInput) ); // A turn this server watched run, ending. assert_eq!(notification_for(Running, Idle), Some(Finished)); assert_eq!(notification_for(Compacting, Idle), Some(Finished)); // Idle arrived at from anywhere else is not an ending. assert_eq!(notification_for(Idle, Idle), None); assert_eq!(notification_for(Unknown, Idle), None); assert_eq!(notification_for(Exited, Idle), None); assert_eq!(notification_for(SessionStatus::AwaitingInput, Idle), None); // Everything else a session does is progress nobody asked to hear. assert_eq!(notification_for(Idle, Running), None); assert_eq!(notification_for(Running, Compacting), None); assert_eq!(notification_for(Running, Exited), None); } /// The switch reaches the running pump, not just the config file. /// /// The failure this exists for is silent in the direction that matters: /// a `set_session_notify(false)` that wrote only the config would look /// correct on the settings screen and in the file, and keep notifying /// until the backend was restarted. Nothing on screen would say so, and /// the person who turned it off is by definition not watching. #[tokio::test] async fn turning_notifications_off_stops_them_without_a_restart() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live"); let mut notifications = manager.subscribe_notifications(); session.send_message("hello".to_string(), Vec::new()); let first = tokio::time::timeout(Duration::from_secs(5), notifications.recv()) .await .expect("a notification within five seconds") .expect("channel open"); assert_eq!(first.kind, NotificationKind::Finished); assert_eq!(first.session_id, info.id); // The title travels with it, because the phone may have no screen // open to look one up on. assert_eq!(first.title, session.info("m", false, None).title); manager.set_session_notify(&info.id, false).expect("off"); // Subscribed before the message, or the turn can finish in the gap // and leave this waiting for an event that has already gone past. let mut events = session.subscribe(); session.send_message("hello again".to_string(), Vec::new()); // The turn still happens -- this is a switch about being told, not // about running -- so wait for the turn's own event and then check // that nothing was announced alongside it. collect_until(&mut events, |event| { matches!( event, Event::Status { state: SessionStatus::Idle } ) }) .await; assert!( notifications.try_recv().is_err(), "a session with notifications off still announced itself" ); } /// A session this app *spawned* is one it is driving, and used to look /// like somebody else's. /// /// Only imported sessions leave an import cursor, so matching on that /// alone missed every spawned session: each one stayed in the import /// list, marked in use, telling the reader to close it wherever it was /// open -- and it was open here. The resume token is the CLI's own id /// for the conversation, which both kinds have. #[tokio::test] async fn a_spawned_session_counts_as_one_we_are_already_driving() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), data_dir.clone(), data_dir.join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); // No cursor -- nothing was imported -- so this is the case the old // check could not see. assert!(import::read_cursor(&data_dir.join(&info.id)).is_none()); assert_eq!(manager.session_driving("5ecf21da-d53f"), None); // What a claude session records once the CLI names itself. claude::write_resume_token(&data_dir.join(&info.id), "5ecf21da-d53f"); assert_eq!( manager.session_driving("5ecf21da-d53f").as_deref(), Some(info.id.as_str()) ); assert_eq!(manager.session_driving("some-other-session"), None); } #[test] fn a_session_we_are_not_driving_says_exited_only_when_it_is_gone() { let dir = tempfile::tempdir().expect("tempdir"); let session = dir.path().join("s1"); std::fs::create_dir_all(&session).expect("mkdir"); // Nothing recorded: an echo session, or one already cleaned up. assert_eq!(status_of_unlaunched(&session), SessionStatus::Exited); // A record naming a process that is definitely gone. process::write( &session, &process::Record { pid: 0, started: 1, detail: process::Detail::Stdio { stdout_read: 0 }, }, ); assert_eq!(status_of_unlaunched(&session), SessionStatus::Exited); // A record naming a process that is definitely there, which this // server is nonetheless not driving. `Exited` here would invite // starting a second one against the same conversation. let live = process::Record::of( std::process::id(), process::Detail::Stdio { stdout_read: 0 }, ) .expect("start time"); process::write(&session, &live); assert_eq!(status_of_unlaunched(&session), SessionStatus::Unknown); } #[tokio::test] async fn spawn_message_and_delete_round_trip() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), data_dir.clone(), data_dir.join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); // Untitled sessions are named after the provider that runs them. assert_eq!(info.title, "echo session"); // Persisted: a fresh load of the config file knows the session. let persisted = Config::load(&config_path).expect("reload config"); assert_eq!(persisted.sessions.len(), 1); assert_eq!(persisted.sessions[0].id, info.id); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); session.send_message("hello there".to_string(), Vec::new()); let seen = collect_turn(&mut rx).await; // The user's message is in the stream, before the echoed reply. let user_at = seen .iter() .position(|entry| { matches!(&entry.event, Event::UserMessage { text, .. } if text == "hello there") }) .expect("user message in the stream"); let echoed: String = seen[user_at..] .iter() .filter_map(|entry| match &entry.event { Event::AssistantText { delta } => Some(delta.as_str()), _ => None, }) .collect(); assert_eq!(echoed, "You said: hello there"); // The transcript replays the same events by cursor. let replay = transcript::read_after(session.transcript_path(), 0).expect("replay"); assert!(replay.len() >= seen.len()); let cursor = seen[user_at].seq; let after = transcript::read_after(session.transcript_path(), cursor).expect("replay"); assert_eq!(after.first().map(|entry| entry.seq), Some(cursor + 1)); // Delete is the complete path out: config, registry, and files. manager.delete_session(&info.id).expect("delete"); assert!(manager.sessions().is_empty()); assert!(manager.session(&info.id).is_none()); assert!(!data_dir.join(&info.id).exists()); assert!( Config::load(&config_path) .expect("reload") .sessions .is_empty() ); assert!(manager.delete_session(&info.id).is_err()); } #[tokio::test] async fn renaming_a_session_persists_and_shows() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), dir.path().join("sessions"), dir.path().join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); assert_eq!(info.title, "echo session"); manager .rename_session(&info.id, " the one about paging ") .expect("rename"); // Trimmed, and reported by the live session rather than by the // record it was launched with. let listed = manager.sessions(); assert_eq!(listed[0].title, "the one about paging"); assert_eq!( Config::load(&config_path).expect("reload").sessions[0].title, "the one about paging" ); // A name that is only spaces is not a name. assert!(manager.rename_session(&info.id, " ").is_err()); assert!(manager.rename_session("no-such-session", "x").is_err()); // And the refusal changed nothing. assert_eq!(manager.sessions()[0].title, "the one about paging"); } #[tokio::test] async fn a_command_waits_for_the_turn_to_end() { let dir = tempfile::tempdir().expect("tempdir"); seed_echo_only(&dir.path().join("config.ron")); let manager = SessionManager::new( dir.path().join("config.ron"), dir.path().join("sessions"), dir.path().join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); // A turn that will still be going when the command arrives. session.send_message("/slow 1".to_string(), Vec::new()); collect_until(&mut rx, |event| { matches!( event, Event::Status { state: SessionStatus::Running } ) }) .await; session.run_command(SessionCommand::Raw("/tool held".to_string())); let seen = collect_until(&mut rx, |event| { matches!(event, Event::CommandQueued { .. }) }) .await; let Some(Event::CommandQueued { id, text }) = seen.iter().map(|entry| entry.event.clone()).next_back() else { panic!("expected the command to be held: {seen:?}"); }; assert_eq!(text, "/tool held"); // Held, not run: nothing of the command has reached the session. assert!( !seen .iter() .any(|entry| matches!(entry.event, Event::ToolStart { .. })), "a held command must not have run yet" ); // The turn ends, and it goes. let seen = collect_until(&mut rx, |event| matches!(event, Event::ToolStart { .. })).await; assert!( seen.iter().any(|entry| matches!( &entry.event, Event::CommandSent { id: sent, .. } if *sent == id )), "the same command has to be reported as sent: {seen:?}" ); } #[tokio::test] async fn a_command_on_an_idle_session_goes_straight_out() { let dir = tempfile::tempdir().expect("tempdir"); seed_echo_only(&dir.path().join("config.ron")); let manager = SessionManager::new( dir.path().join("config.ron"), dir.path().join("sessions"), dir.path().join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); session.run_command(SessionCommand::Raw("/tool now".to_string())); let seen = collect_until(&mut rx, |event| matches!(event, Event::ToolStart { .. })).await; // Sent, and never queued: a session between turns has nothing to // wait for, and a phone should not draw a bubble that resolves in // the same frame. assert!( seen.iter() .any(|entry| matches!(entry.event, Event::CommandSent { .. })) ); assert!( !seen .iter() .any(|entry| matches!(entry.event, Event::CommandQueued { .. })) ); } #[tokio::test] async fn questions_round_trip_through_answer() { let dir = tempfile::tempdir().expect("tempdir"); seed_echo_only(&dir.path().join("config.ron")); let manager = SessionManager::new( dir.path().join("config.ron"), dir.path().join("sessions"), dir.path().join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); session.send_message("/question deploy?".to_string(), Vec::new()); let seen = collect_until(&mut rx, |event| { matches!( event, Event::Status { state: SessionStatus::AwaitingInput } ) }) .await; let question_id = seen .iter() .find_map(|entry| match &entry.event { Event::Question { id, .. } => Some(id.clone()), _ => None, }) .expect("question event"); session.answer_question(&question_id, &["Yes".to_string()]); let seen = collect_until(&mut rx, is_idle).await; assert!(seen.iter().any(|entry| matches!( &entry.event, Event::Answered { id, answers } if *id == question_id && answers == &["Yes".to_string()] ))); } #[tokio::test] async fn a_restart_reports_when_a_session_last_did_something() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), data_dir.clone(), data_dir.join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); session.send_message("something".to_string(), Vec::new()); collect_turn(&mut rx).await; let before_restart = manager.sessions()[0].last_activity; drop(rx); drop(session); drop(manager); // Far enough back that a restart taking the clock cannot pass by // being fast: the assertion is about which source was used, not // about how long the test took. let long_ago = before_restart - 86_400.0; rewrite_transcript_times(&data_dir.join(&info.id).join("transcript.jsonl"), long_ago); let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager restart"); let listed = manager.sessions(); assert_eq!(listed.len(), 1); assert!( (listed[0].last_activity - long_ago).abs() < 1.0, "a relaunched session reported {} instead of the {long_ago} its transcript records \ -- every row would read \"just now\" and the list would sort by nothing", listed[0].last_activity, ); } /// The context figure follows the conversation down as well as up. /// /// It used to be a running total of what the session had spent, which /// only ever climbs -- so a session that had just been compacted from /// 128k to 10k, or cleared outright, went on reporting the larger /// figure, and the number on the status row disagreed with the divider /// directly above it. Turns raise it, a compaction replaces it with /// what the compaction says it recovered, and a clear leaves it /// unmeasured rather than guessing a small number. /// /// The compaction leg is in `driver::tests` rather than here: echo /// spends thirteen seconds on one so a person can watch the state, and /// the rule both paths use is the same function. #[tokio::test] async fn the_context_figure_follows_compactions_and_clears() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), data_dir.clone(), data_dir.join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live"); // Nothing measured yet, which is not the same as an empty context // and is not reported as one. assert_eq!(manager.sessions()[0].context_tokens, None); // Echo's pretend context is a hundred a turn plus the words, so the // arithmetic is checkable. let mut rx = session.subscribe(); session.send_message("one two three".to_string(), Vec::new()); collect_turn(&mut rx).await; session.send_message("four five".to_string(), Vec::new()); collect_turn(&mut rx).await; assert_eq!( manager.sessions()[0].context_tokens, Some(205), "two turns of three and two words" ); // The event carries it too, so a phone never has to fold the part of // the transcript it happens to hold. let last_context = transcript::read_after(session.transcript_path(), 0) .expect("transcript") .iter() .rev() .find_map(|entry| match entry.event { Event::UsageDelta { context, .. } => context, _ => None, }) .expect("a usage event"); assert_eq!(last_context, 205); // A clear leaves it unmeasured: the conversation is gone, and how // much is left is a thing nobody has counted. session.run_command(SessionCommand::Clear); collect_until(&mut rx, |event| matches!(event, Event::Cleared)).await; assert_eq!(manager.sessions()[0].context_tokens, None); // And a restart folds it back out of the file rather than starting // over -- including the clear, which is why it is not the last // usage event that decides. drop(rx); drop(session); drop(manager); let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager restart"); assert_eq!(manager.sessions()[0].context_tokens, None); } /// Backdates every line in a transcript, so a restart has something to /// report that the clock could not have produced. fn rewrite_transcript_times(path: &Path, ts: f64) { let text = std::fs::read_to_string(path).expect("read transcript"); let rewritten: String = text .lines() .map(|line| { let mut entry: serde_json::Value = serde_json::from_str(line).expect("line"); entry["ts"] = serde_json::json!(ts); format!("{entry}\n") }) .collect(); std::fs::write(path, rewritten).expect("write transcript"); } /// Stopping and starting a session is about its *process*, and the two /// refusals are the whole of what keeps starting one from becoming a /// second one on the same conversation. /// /// Echo has no process, which makes it the right session to ask the /// first question of: "there is nothing to stop" is an answer, and /// reporting success would leave a phone showing a session it believes /// it stopped. The second question is asked of a session that has been /// told it exited, since the guard is on the *status* rather than on /// which driver it is. #[tokio::test] async fn a_session_is_started_again_only_once_it_is_known_to_have_exited() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); let refused = manager.stop_session(&info.id).expect_err("nothing to stop"); assert!( refused.to_string().contains("no process running"), "said: {refused:#}" ); let refused = manager .start_session(&info.id) .expect_err("already running"); assert!( refused.to_string().contains("already running"), "said: {refused:#}" ); // What a driver reports when its process goes, without a process // to go: the guard reads the recorded status, so this is the same // state a stopped claude session reaches. let _ = session.sink.send(Event::Status { state: SessionStatus::Exited, }); collect_until(&mut rx, |event| { matches!( event, Event::Status { state: SessionStatus::Exited } ) }) .await; manager.start_session(&info.id).expect("start again"); collect_until(&mut rx, is_idle).await; // Idle rather than exited, and said by the start rather than left // for a driver that has been given no work to say for itself. assert_eq!(manager.sessions()[0].status, SessionStatus::Idle); // The same live session throughout: only the driver was replaced, // so nothing a phone is reading was interrupted. assert!(Arc::ptr_eq( &session, &manager.session(&info.id).expect("still live") )); } #[tokio::test] async fn a_restart_relaunches_sessions_and_continues_the_numbering() { let dir = tempfile::tempdir().expect("tempdir"); let config_path = dir.path().join("config.ron"); let data_dir = dir.path().join("sessions"); seed_echo_only(&config_path); let manager = SessionManager::new( config_path.clone(), data_dir.clone(), data_dir.join("models"), ) .expect("manager"); let info = manager.spawn_session(echo_spec()).expect("spawn"); let session = manager.session(&info.id).expect("live session"); let mut rx = session.subscribe(); session.send_message("first".to_string(), Vec::new()); let seen = collect_turn(&mut rx).await; let last_seq = seen.last().expect("events").seq; drop(rx); drop(session); drop(manager); // A new manager over the same state: the session is back, and new // events continue the sequence rather than restarting it -- which // is what makes a phone's cursor survive a backend restart. let manager = SessionManager::new(config_path, data_dir.clone(), data_dir.join("models")) .expect("manager restart"); let listed = manager.sessions(); assert_eq!(listed.len(), 1); assert_eq!(listed[0].id, info.id); let session = manager.session(&info.id).expect("relaunched session"); let mut rx = session.subscribe(); session.send_message("second".to_string(), Vec::new()); let seen = collect_turn(&mut rx).await; assert!(seen.first().expect("events").seq > last_seq); } }