//! Per-container HTTP UI. SPA shape: `GET /` returns a static shell; //! `GET /static/*` serves CSS + JS; `GET /api/state` returns the page //! state as JSON; the JS app renders. Live events stream on //! `/events/stream`. Action POSTs (`/send`, `/login/*`) return either a //! 303 Redirect (for browsers that submit the form normally) or just //! 200 OK — the JS app re-fetches `/api/state` afterwards. //! //! Handlers are split by concern into the submodules below; this file owns the //! shared [`AppState`], the listener + router wiring in [`serve`], and a couple //! of small shared helpers ([`error_response`], [`SOCKET_FETCH_TIMEOUT`]). mod actions; mod auth; mod proxy; mod screen; mod state; mod stats; mod stream; use std::net::SocketAddr; use std::path::{Path, PathBuf}; use std::sync::atomic::AtomicBool; use std::sync::{Arc, Mutex}; use anyhow::{Context, Result}; use axum::{ Router, http::StatusCode, response::{IntoResponse, Response}, routing::{get, post}, }; use tower_http::services::ServeDir; use crate::events::Bus; use crate::login::LoginState; use crate::login_session::LoginSession; /// Deadline for broker-backed fetches on web-UI request paths. The /// page's critical fields (status, turn state, usage) are all /// in-memory; a busy or stalled hive-c0re must degrade the /// socket-backed extras (inbox rows, loose ends, reminder stats) /// instead of hanging the whole response — an unbounded await here is /// what let `/api/state` stall long enough to bork the terminal. const SOCKET_FETCH_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(3); /// Live login state for the web UI. The harness updates this in place as it /// transitions between `NeedsLogin` and `Online`; the UI reads on each /// render. pub type LoginStateCell = Arc>; #[derive(Clone)] struct AppState { label: String, login: LoginStateCell, session: Arc>>>, bus: Bus, socket: PathBuf, /// VNC port from the `HIVE_GUI_VNC_PORT` env var at startup. /// `None` when unset (gui not enabled for this agent). gui_vnc_port: Option, /// Set by `post_cancel_turn` on a successful SIGINT; read-and-cleared /// by the serve loop's next `handle_turn` to prepend /// `hive_sh4re::INTERRUPTED_HINT` to that turn's wake prompt. Shared /// with the serve loop via the same `Arc` (see `serve_main`) — an /// in-memory flag, not a marker file, since a `/cancel` from a prior /// process lifetime isn't meaningful once the harness restarts. interrupted: Arc, } /// Bind the per-container web listener and serve the SPA. /// /// `HIVE_WEB_SOCKET` opt-in selects unix-socket vs TCP binding; the /// dual-mode transition + gateway-side consumer live in /// [`docs/web-ui/shape.md::Listener bind`](../../../docs/web-ui/shape.md) and /// [`docs/gateway.md::Per-agent unix-socket upstream`](../../../docs/gateway.md). /// /// # Errors /// /// Returns an error if neither the TCP listener (default) nor the /// unix-socket bind (`HIVE_WEB_SOCKET`, if set) can be acquired, or /// if `HIVE_STATIC_DIR` is missing. pub async fn serve( label: String, port: u16, login: LoginStateCell, bus: Bus, socket: PathBuf, interrupted: Arc, ) -> Result<()> { let gui_vnc_port = read_gui_vnc_port(); let static_dir: PathBuf = std::env::var_os("HIVE_STATIC_DIR") .map(PathBuf::from) .context( "HIVE_STATIC_DIR env var not set — point it at the merged \ per-agent dist (see hyperhive.frontend.mergedDist in nix)", )?; if !static_dir.is_dir() { anyhow::bail!( "HIVE_STATIC_DIR ({}) is not a directory", static_dir.display() ); } tracing::info!(static_dir = %static_dir.display(), "web UI static dir resolved"); let state = AppState { label, login, session: Arc::new(Mutex::new(None)), bus, socket, gui_vnc_port, interrupted, }; let app: Router = Router::new() .route("/api/state", get(state::api_state)) .route("/api/dashboard-state", get(state::api_dashboard_state)) .route("/events/stream", get(stream::events_stream)) .route("/events/history", get(stream::events_history)) .route("/send", post(actions::post_send)) .route("/login/start", post(auth::post_login_start)) .route("/login/code", post(auth::post_login_code)) .route("/login/cancel", post(auth::post_login_cancel)) .route("/api/cancel", post(actions::post_cancel_turn)) .route("/api/compact", post(actions::post_compact)) .route("/api/model", post(actions::post_set_model)) .route("/api/effort", post(actions::post_set_effort)) .route("/api/new-session", post(actions::post_new_session)) .route("/api/logout", post(auth::post_logout)) .route("/api/todos", get(stats::api_todos)) .route("/api/todos/mark-done", post(actions::post_mark_todos_done)) .route("/api/stats", get(stats::api_stats)) .route("/screen/ws", get(screen::screen_ws)) .route("/icon", get(screen::serve_icon)); // Mount any `hyperhive.extraWebProxies` under `/extra//` before the // static fallback so declared proxies win over `ServeDir`. let app = proxy::mount_extra_proxies(app) // Anything else (`/`, `/stats`, `/screen`, `/static/*`) // falls through to the merged dist. ServeDir auto-appends // `.html` when the URL is a bare path that matches a file // (so `/stats` → `dist/stats.html`, `/screen` → `dist/ // screen.html`). Per-agent `extraFiles` additions are // already layered into this same directory (see // hyperhive.frontend.mergedDist in nix). .fallback_service(ServeDir::new(&static_dir)) .with_state(state); // `HIVE_WEB_SOCKET` opt-in: when set + non-empty, bind a // `UnixListener` at the given path. Empty string treated as // unset so a stray `HIVE_WEB_SOCKET=` doesn't trap us into an // un-bindable empty path. Falls through to the TCP path below // otherwise. See docs/gateway.md::Per-agent unix-socket upstream // for the gateway-side consumer. if let Some(socket_path) = std::env::var_os("HIVE_WEB_SOCKET") && !socket_path.is_empty() { let path = PathBuf::from(socket_path); let listener = bind_unix(&path)?; tracing::info!(socket = %path.display(), "web UI listening on unix socket"); axum::serve(listener, app).await?; return Ok(()); } let addr = SocketAddr::from(([0, 0, 0, 0], port)); let listener = bind_with_retry(addr, "web UI").await?; tracing::info!(%port, "web UI listening on tcp"); axum::serve(listener, app).await?; Ok(()) } /// Bind a `UnixListener` at `path` and drop a `.bound` marker next /// to it so c0re's gateway-map writer knows the socket is live. /// Best-effort unlinks any stale socket left from a crashed previous /// harness (clean exit removes it, but `bind(2)` refuses to overwrite /// an existing file) and `mkdir -p`s the parent for first-boot. Mode /// `0o666` — world-accessible so the gateway container's nginx process /// can `connect(2)` without sharing a group with the agent user. /// The per-agent subdir (`/run/hive-agent//`) is only accessible /// to containers that have it bind-mounted, so world-accessible sockets /// are not a material risk. /// /// Marker-gating + the gateway-side consumer: see /// [`docs/gateway.md::Per-agent unix-socket upstream`](../../../docs/gateway.md). fn bind_unix(path: &Path) -> Result { use std::os::unix::fs::PermissionsExt; if let Some(parent) = path.parent() { std::fs::create_dir_all(parent) .with_context(|| format!("create socket parent dir {}", parent.display()))?; } // Best-effort: ENOENT is fine (no stale file); any other error // surfaces via the bind below with a clearer "AddrInUse" / perms // message than a partial cleanup would. let _ = std::fs::remove_file(path); let listener = tokio::net::UnixListener::bind(path) .with_context(|| format!("bind unix socket at {}", path.display()))?; std::fs::set_permissions(path, std::fs::Permissions::from_mode(0o666)) .with_context(|| format!("set perms on {}", path.display()))?; // Best-effort ready marker: failed write isn't fatal (the harness // still binds + serves), it just means the gateway side keeps the // TCP upstream for one more sync tick. if let Some(parent) = path.parent() { let marker = parent.join("hyperhive-socket-bound"); if let Err(e) = std::fs::write(&marker, b"") { tracing::warn!( marker = %marker.display(), error = %e, "failed to write hyperhive-socket-bound marker — gateway may keep TCP upstream" ); } } Ok(listener) } /// Maximum bind attempts before `bind_with_retry` gives up on `AddrInUse`. const MAX_BIND_ATTEMPTS: u32 = 12; /// Bind a TCP listener with `SO_REUSEADDR` set, retrying on `AddrInUse` with /// exponential backoff capped at 2s, up to [`MAX_BIND_ATTEMPTS`] attempts. If /// the port is still held after the final attempt, returns the `AddrInUse` /// error rather than looping forever (a genuine collision needs the operator, /// not an unbounded wait). /// /// Retry rationale + dashboard-banner-on-real-collision: /// see [`docs/web-ui/shape.md::Listener bind`](../../../docs/web-ui/shape.md). async fn bind_with_retry(addr: SocketAddr, label: &str) -> Result { let mut delay_ms = 250u64; let mut attempts = 0u32; loop { match try_bind(addr) { Ok(l) => { if attempts > 0 { tracing::info!( %addr, attempts, "{label}: bind succeeded after retry" ); } return Ok(l); } Err(e) if e.kind() == std::io::ErrorKind::AddrInUse => { let attempt = attempts + 1; if attempt >= MAX_BIND_ATTEMPTS { return Err(e).with_context(|| { format!("bind {label} on {addr}: still AddrInUse after {attempt} attempts") }); } tracing::warn!( %addr, attempt, "{label}: AddrInUse, retrying in {delay_ms}ms" ); tokio::time::sleep(std::time::Duration::from_millis(delay_ms)).await; attempts += 1; delay_ms = (delay_ms * 2).min(2000); } Err(e) => { return Err(e).with_context(|| format!("bind {label} on {addr}")); } } } } fn try_bind(addr: SocketAddr) -> std::io::Result { let sock = match addr { SocketAddr::V4(_) => tokio::net::TcpSocket::new_v4()?, SocketAddr::V6(_) => tokio::net::TcpSocket::new_v6()?, }; sock.set_reuseaddr(true)?; sock.bind(addr)?; sock.listen(1024) } /// The fixed VNC port weston bound, from the `HIVE_GUI_VNC_PORT` env var /// the harness service sets when gui is enabled (see weston-vnc.nix). /// `None` when unset (gui not enabled for this agent) or unparseable. /// The port is a fixed, container-local value — no per-agent hashing, no /// marker file — because network isolation is unconditional (each agent /// has its own netns, so the port can't collide across containers). fn read_gui_vnc_port() -> Option { std::env::var("HIVE_GUI_VNC_PORT").ok()?.parse().ok() } /// Outcome of [`sigint_claude`] — shared by `/api/cancel` and `/api/logout` /// so both can render the same three cases. enum SigintOutcome { /// The tracked pid was signalled. Signalled, /// No claude child is currently tracked (turn not in flight, or it /// finished/exited between the check and the signal — same "nothing to /// interrupt" outcome either way). NoProcess, /// The `kill` syscall itself failed for a reason other than "no such /// process" (permission issue, etc). Failed(std::io::Error), } /// Find a `claude` process that is a direct OS child of this harness /// process, if any. `hive-claude`'s driver spawns the turn's claude /// directly (`Command::new(program).spawn()`, no shell in between), so the /// harness is always the immediate parent of any claude turn it started — /// scanning `/proc/*/status` for `PPid: ` plus `/proc/*/cmdline` /// for an argv[0] of `claude` finds *that* specific process without needing /// the driver to surface its pid through any extra plumbing. Distinguishes /// the harness's own tracked turn from an unrelated `claude` someone is /// running interactively in the same container (a manually shelled-in /// "choom" session) — that one's parent is a login shell, not us. /// /// **Matches on `cmdline`, not `status`'s `Name:` field.** The nixpkgs /// `claude-code` package wraps its real binary (`wrapProgram`-style: the /// executable on `PATH` is a thin `exec -a claude .../.claude-wrapped ...` /// shim) — `exec -a` only overrides argv[0] as the process itself/`cmdline` /// see it, not the kernel's own `comm` (what `status`'s `Name:` line /// reports, set from the executed binary's own basename at `execve` time). /// So `Name:` shows `.claude-wrapped`, not `claude`, on a wrapped package — /// `cmdline`'s first argument still carries the bare name /// `Command::new("claude")` resolved on `PATH`, which is what actually /// matters here. Best-effort: a process that exits mid-scan (its /// `/proc//{status,cmdline}` read fails, ESRCH) is just skipped. fn find_claude_child() -> Option { let own_pid = std::process::id(); for entry in std::fs::read_dir("/proc").ok()?.flatten() { let Ok(pid) = entry.file_name().to_string_lossy().parse::() else { continue; // not a pid dir (self, cwd, net, ...) }; let Ok(status) = std::fs::read_to_string(entry.path().join("status")) else { continue; }; let parent_pid = status .lines() .find_map(|line| line.strip_prefix("PPid:")) .and_then(|v| v.trim().parse::().ok()); if parent_pid != Some(own_pid) { continue; } let Ok(cmdline) = std::fs::read(entry.path().join("cmdline")) else { continue; }; let argv0 = cmdline.split(|&b| b == 0).next().unwrap_or_default(); if argv0 == b"claude" { return Some(pid); } } None } /// SIGINT this container's harness-spawned claude child, if any /// (best-effort). See [`find_claude_child`] for how it's identified — /// **not** a name-based `pkill claude`, which would also hit an unrelated /// `claude` process someone is running interactively in the container. async fn sigint_claude() -> SigintOutcome { let Some(pid) = find_claude_child() else { return SigintOutcome::NoProcess; }; match tokio::process::Command::new("kill") .args(["-INT", &pid.to_string()]) .status() .await { Ok(status) if status.success() => SigintOutcome::Signalled, // Non-zero from `kill` means "no such process" (ESRCH) — it already // exited between the check above and the signal. Same as never // having found it. Ok(_) => SigintOutcome::NoProcess, Err(e) => SigintOutcome::Failed(e), } } fn error_response(status: StatusCode, message: &str) -> Response { // Plain text — JS app surfaces in `alert()`, HTML wrapping would just // be noise. Status is per-caller: 400 for bad input, 409 for a // retryable state conflict (turn in flight / hive-c0re busy), 500 only // for a genuine server/transport failure — the frontend shows the code // in its alert, so a benign "busy, retry" must not read as a 500. (status, message.to_owned()).into_response() } /// Why a deadline-bounded broker request via the per-agent socket didn't /// yield a response. Kept distinct so action handlers pick the right status /// code (see [`broker_error_response`]) while decorative fetches `.ok()` both. enum BrokerError { /// Outran [`SOCKET_FETCH_TIMEOUT`] — hive-c0re is busy or stalled. A /// retryable state conflict (→ 409), not a server fault. Timeout, /// The socket transport itself failed (connect / encode / decode). Transport(anyhow::Error), } /// Issue a broker request over the per-agent socket, bounded by /// [`SOCKET_FETCH_TIMEOUT`] so a busy or stalled hive-c0re degrades the /// response instead of hanging it. Callers match the returned [`Response`] /// variant themselves; the error side distinguishes a retryable timeout from /// a transport failure. This is the one shared broker-call scaffold — every /// web-UI handler that talks to the broker goes through it. async fn broker_request( socket: &Path, req: &hive_core_agent_sock::Request, ) -> std::result::Result { match tokio::time::timeout( SOCKET_FETCH_TIMEOUT, hive_sock_client::request::<_, hive_core_agent_sock::Response>( socket, req, crate::CONTROL_SOCKET_RETRY, ), ) .await { Ok(Ok(resp)) => Ok(resp), Ok(Err(e)) => Err(BrokerError::Transport(e)), Err(_) => Err(BrokerError::Timeout), } } /// Map a [`BrokerError`] to an operator-facing error response: a timeout is a /// retryable "busy" conflict (409), a transport failure is a 500. `action` /// prefixes the message (e.g. `"send"`, `"get_loose_ends"`). fn broker_error_response(err: &BrokerError, action: &str) -> Response { match err { BrokerError::Timeout => error_response( StatusCode::CONFLICT, &format!("{action}: timed out — hive-c0re busy, retry"), ), BrokerError::Transport(e) => error_response( StatusCode::INTERNAL_SERVER_ERROR, &format!("{action}: transport: {e:#}"), ), } }