//! Unified hyperhive harness binary (#598). //! //! Replaces the pre-#598 `hive-ag3nt` + `hive-m1nd` split. One binary, //! picks its role at startup from `HIVE_ROLE` (set by post-#676 //! `harness-base.nix` from `hyperhive.role` — `"agent"` or //! `"manager"`). Both agent + manager wire surfaces live in the same //! binary because the privilege boundary is enforced server-side at //! the socket (`/run/hive/mcp.sock`): an agent socket refuses //! `ManagerRequest` calls regardless of who sends them, so there's no //! escalation risk in shipping the same code to both. //! //! `HIVE_ROLE` defaults to `"agent"` if unset to keep the standalone //! `nix run .#hive-ag3nt` shape working without env plumbing. use std::path::{Path, PathBuf}; use std::sync::{Arc, Mutex}; use std::time::Duration; use hive_ag3nt::web_ui::TurnLock; use anyhow::{Result, bail}; use clap::{Parser, Subcommand}; use hive_ag3nt::events::{Bus, LiveEvent, TurnState}; use hive_ag3nt::login::{self, LoginState}; use hive_ag3nt::turn_stats::TurnStats; use hive_ag3nt::{DEFAULT_SOCKET, DEFAULT_WEB_PORT, client, mcp, plugins, serve_common, turn, web_ui}; use hive_sh4re::{ AgentRequest, AgentResponse, HelperEvent, ManagerRequest, ManagerResponse, SYSTEM_SENDER, }; #[derive(Parser)] #[command( name = "hive", about = "hyperhive harness — role from $HIVE_ROLE (agent|manager)" )] struct Cli { /// Path to the per-agent MCP socket (bind-mounted from the host). #[arg(long, global = true, default_value = DEFAULT_SOCKET)] socket: PathBuf, #[command(subcommand)] cmd: Cmd, } #[derive(Subcommand)] enum Cmd { /// Run the long-lived harness loop. Polls inbox; replies via /// `claude --print` when available. Serve { /// Inbox poll interval in milliseconds. #[arg(long, default_value_t = 1000)] poll_ms: u64, }, /// Run this role's MCP server on stdio. Spawned by `claude` via /// `--mcp-config`; tools dispatch through `/run/hive/mcp.sock` back /// into the hyperhive broker. Mcp, /// Agent-only: inject a wake-up event into this agent's inbox so /// the next turn fires with the given body. Intended for extra MCP /// servers / helpers (matrix bridge, scraper, webhook listener) /// that need to nudge claude on external events. Refused when /// `HIVE_ROLE=manager` — the manager surface has no `Wake` /// equivalent. Wake { #[arg(long)] from: String, /// Body of the wake message. Pass `-` to read from stdin. #[arg(long)] body: String, }, } #[derive(Copy, Clone)] enum Role { Agent, Manager, } fn resolve_role() -> Result { match std::env::var("HIVE_ROLE").as_deref() { Ok("agent") | Err(_) => Ok(Role::Agent), Ok("manager") => Ok(Role::Manager), Ok(other) => bail!("unknown HIVE_ROLE={other:?}; expected 'agent' or 'manager'"), } } #[tokio::main] async fn main() -> Result<()> { tracing_subscriber::fmt() .with_env_filter( tracing_subscriber::EnvFilter::try_from_default_env() .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info")), ) .init(); let cli = Cli::parse(); let role = resolve_role()?; match (role, cli.cmd) { (Role::Agent, Cmd::Serve { poll_ms }) => agent_serve_main(&cli.socket, poll_ms).await, (Role::Manager, Cmd::Serve { poll_ms }) => manager_serve_main(&cli.socket, poll_ms).await, (Role::Agent, Cmd::Mcp) => mcp::serve_agent_stdio(cli.socket).await, (Role::Manager, Cmd::Mcp) => mcp::serve_manager_stdio(cli.socket).await, (Role::Agent, Cmd::Wake { from, body }) => agent_wake(&cli.socket, from, body).await, (Role::Manager, Cmd::Wake { .. }) => { bail!("wake is agent-only — manager has no equivalent surface") } } } // ---------- agent role ---------- async fn agent_serve_main(socket: &Path, poll_ms: u64) -> Result<()> { let port = std::env::var("HIVE_PORT") .ok() .and_then(|s| s.parse::().ok()) .unwrap_or(DEFAULT_WEB_PORT); let label = std::env::var("HIVE_LABEL").unwrap_or_else(|_| "hive-ag3nt".into()); let claude_dir = login::default_dir(); let initial = LoginState::from_dir(&claude_dir); tracing::info!(state = ?initial, claude_dir = %claude_dir.display(), "harness boot"); let login_state = Arc::new(Mutex::new(initial)); let bus = Bus::new(); let stats = TurnStats::open_default(); if let Some(s) = &stats { let (ctx, cost) = s.last_usage(); if ctx.is_some() || cost.is_some() { bus.seed_usage(ctx, cost); } } let files = turn::TurnFiles::prepare(socket, &label, mcp::Flavor::Agent).await?; let turn_lock: TurnLock = Arc::new(tokio::sync::Mutex::new(())); plugins::install_configured(socket, Some("manager")).await; tokio::spawn(hive_ag3nt::forge_notify::run(socket.to_path_buf(), false)); tokio::spawn(web_ui::serve( label.clone(), port, login_state.clone(), bus.clone(), socket.to_path_buf(), files.clone(), turn_lock.clone(), )); match initial { LoginState::Online => { agent_serve_loop( socket, Duration::from_millis(poll_ms), login_state, claude_dir, bus, stats, &files, turn_lock, &label, ) .await } LoginState::NeedsLogin => { turn::wait_for_login(&claude_dir, login_state.clone(), &bus, poll_ms).await; agent_serve_loop( socket, Duration::from_millis(poll_ms), login_state, claude_dir, bus, stats, &files, turn_lock, &label, ) .await } } } #[allow(clippy::too_many_arguments)] async fn agent_serve_loop( socket: &Path, interval: Duration, login_state: Arc>, claude_dir: std::path::PathBuf, bus: Bus, stats: Option, files: &turn::TurnFiles, turn_lock: TurnLock, label: &str, ) -> Result<()> { tracing::info!(socket = %socket.display(), "hive-ag3nt serve"); agent_requeue_inflight(socket).await; loop { let recv: Result = client::request( socket, &AgentRequest::Recv { wait_seconds: Some(180), max: None, }, ) .await; match recv { Ok(AgentResponse::Messages { messages }) if !messages.is_empty() => { let first = messages.into_iter().next().expect("checked non-empty"); let auth_failed = handle_agent_turn(socket, &bus, stats.as_ref(), files, &turn_lock, label, first) .await; if auth_failed { *login_state.lock().unwrap() = LoginState::NeedsLogin; turn::wait_for_login( &claude_dir, login_state.clone(), &bus, u64::try_from(interval.as_millis()).unwrap_or(2000), ) .await; } } Ok(AgentResponse::Messages { .. }) => { tokio::time::sleep(interval).await; } Ok( AgentResponse::Ok | AgentResponse::Status { .. } | AgentResponse::Recent { .. } | AgentResponse::QuestionQueued { .. } | AgentResponse::LooseEnds { .. } | AgentResponse::PendingRemindersCount { .. } | AgentResponse::ReminderRollup { .. } | AgentResponse::AgentMeta { .. }, ) => { tracing::warn!("recv produced unexpected response kind"); } Ok(AgentResponse::Err { message }) => { tracing::warn!(%message, "recv error"); } Err(e) => { tracing::warn!(error = ?e, "recv failed; retrying"); } } } } async fn handle_agent_turn( socket: &Path, bus: &Bus, stats: Option<&TurnStats>, files: &turn::TurnFiles, turn_lock: &TurnLock, label: &str, first: hive_sh4re::DeliveredMessage, ) -> bool { let from = first.from; let body = first.body; let redelivered = first.redelivered; tracing::info!(%from, %body, %redelivered, "inbox"); let unread = agent_inbox_unread(socket).await; bus.emit(LiveEvent::TurnStart { from: from.clone(), body: body.clone(), unread }); bus.set_state(TurnState::Thinking); let started_at = serve_common::now_unix(); let started_instant = std::time::Instant::now(); let model_at_start = bus.model(); let prompt = serve_common::format_wake_prompt(&from, &body, unread, redelivered); let outcome = { let _guard = turn_lock.lock().await; turn::drive_turn(&prompt, files, bus).await }; turn::emit_turn_end(bus, &outcome); bus.set_state(TurnState::Idle); if matches!(outcome, turn::TurnOutcome::Ok | turn::TurnOutcome::Compacted) { agent_ack_turn(socket).await; } if matches!(outcome, turn::TurnOutcome::RateLimited) { let secs = turn::rate_limit_sleep_secs(); bus.emit_status("rate_limited"); bus.emit(LiveEvent::Note { text: format!("API rate-limited — sleeping {secs}s before retry"), }); tracing::warn!(sleep_secs = secs, "rate-limited; parking"); tokio::time::sleep(Duration::from_secs(secs)).await; agent_requeue_inflight(socket).await; bus.emit_status("online"); } if matches!(outcome, turn::TurnOutcome::AuthFailed) { bus.emit_status("needs_login_idle"); bus.emit(LiveEvent::Note { text: "API 401 — waiting for re-login via web UI".into(), }); tracing::warn!("auth-failed; parking until re-login"); agent_requeue_inflight(socket).await; } if let turn::TurnOutcome::Failed(e) = &outcome { agent_notify_manager_of_failure(socket, label, e).await; } if let Some(stats) = stats { let ended_at = serve_common::now_unix(); let duration_ms = i64::try_from(started_instant.elapsed().as_millis()).unwrap_or(i64::MAX); let (open_threads, open_reminders) = agent_post_turn_counts(socket).await; let row = serve_common::build_row( started_at, ended_at, duration_ms, model_at_start, from.clone(), &outcome, bus, open_threads, open_reminders, ); stats.record(&row); } let pending = agent_inbox_unread(socket).await; if pending > 0 { tracing::info!(%pending, "pending messages after turn; fetching next"); } agent_check_and_inject_continue(socket, label).await; matches!(outcome, turn::TurnOutcome::AuthFailed) } async fn agent_ack_turn(socket: &Path) { match client::request::<_, AgentResponse>(socket, &AgentRequest::AckTurn).await { Ok(AgentResponse::Ok) => {} Ok(AgentResponse::Err { message }) => { tracing::warn!(%message, "ack_turn rejected by broker"); } Ok(other) => { tracing::warn!(?other, "ack_turn unexpected response"); } Err(e) => tracing::warn!(error = ?e, "ack_turn transport error"), } } async fn agent_requeue_inflight(socket: &Path) { match client::request::<_, AgentResponse>(socket, &AgentRequest::RequeueInflight).await { Ok(AgentResponse::Ok) => {} Ok(AgentResponse::Err { message }) => { tracing::warn!(%message, "requeue_inflight rejected by broker"); } Ok(other) => { tracing::warn!(?other, "requeue_inflight unexpected response"); } Err(e) => tracing::warn!(error = ?e, "requeue_inflight transport error"), } } async fn agent_notify_manager_of_failure(socket: &Path, label: &str, err: &anyhow::Error) { let body = format!("[system] agent `{label}` claude turn failed:\n{err:#}"); let res = client::request::<_, AgentResponse>( socket, &AgentRequest::Send { to: "manager".into(), body, in_reply_to: None, }, ) .await; if let Err(e) = res { tracing::warn!(error = ?e, "failed to notify manager of turn failure"); } } async fn agent_inbox_unread(socket: &Path) -> u64 { match client::request::<_, AgentResponse>(socket, &AgentRequest::Status).await { Ok(AgentResponse::Status { unread }) => unread, _ => 0, } } async fn agent_post_turn_counts(socket: &Path) -> (Option, Option) { let threads = match client::request::<_, AgentResponse>(socket, &AgentRequest::GetLooseEnds).await { Ok(AgentResponse::LooseEnds { loose_ends }) => u64::try_from(loose_ends.len()).ok(), _ => None, }; let reminders = match client::request::<_, AgentResponse>( socket, &AgentRequest::CountPendingReminders, ) .await { Ok(AgentResponse::PendingRemindersCount { count }) => Some(count), _ => None, }; (threads, reminders) } async fn agent_check_and_inject_continue(socket: &Path, label: &str) { let sentinel = hive_ag3nt::paths::state_dir().join("hyperhive-continue"); if !sentinel.exists() { return; } if let Err(e) = std::fs::remove_file(&sentinel) { tracing::warn!(error = %e, "check_and_inject_continue: remove sentinel failed"); return; } let res = client::request::<_, AgentResponse>( socket, &AgentRequest::Wake { from: "self".into(), body: "continue".into(), }, ) .await; match res { Ok(AgentResponse::Ok) => { tracing::info!(%label, "request_next_turn: injected self-continue wake"); } Ok(AgentResponse::Err { message }) => { tracing::warn!(%message, "check_and_inject_continue: wake rejected"); } Err(e) => { tracing::warn!(error = ?e, "check_and_inject_continue: wake transport error"); } _ => {} } } async fn agent_wake(socket: &Path, from: String, body: String) -> Result<()> { let body = if body == "-" { let mut buf = String::new(); std::io::Read::read_to_string(&mut std::io::stdin(), &mut buf)?; buf } else { body }; let resp: AgentResponse = client::request(socket, &AgentRequest::Wake { from, body }).await?; match resp { AgentResponse::Ok => Ok(()), AgentResponse::Err { message } => anyhow::bail!("wake: {message}"), other => anyhow::bail!("wake: unexpected response {other:?}"), } } // ---------- manager role ---------- async fn manager_serve_main(socket: &Path, poll_ms: u64) -> Result<()> { let port = std::env::var("HIVE_PORT") .ok() .and_then(|s| s.parse::().ok()) .unwrap_or(DEFAULT_WEB_PORT); let label = std::env::var("HIVE_LABEL").unwrap_or_else(|_| "hm1nd".into()); let claude_dir = login::default_dir(); let initial = LoginState::from_dir(&claude_dir); tracing::info!(state = ?initial, claude_dir = %claude_dir.display(), "hm1nd boot"); let login_state = Arc::new(Mutex::new(initial)); let bus = Bus::new(); let stats = TurnStats::open_default(); if let Some(s) = &stats { let (ctx, cost) = s.last_usage(); if ctx.is_some() || cost.is_some() { bus.seed_usage(ctx, cost); } } let files = turn::TurnFiles::prepare(socket, &label, mcp::Flavor::Manager).await?; let turn_lock: TurnLock = Arc::new(tokio::sync::Mutex::new(())); plugins::install_configured(socket, None).await; tokio::spawn(web_ui::serve( label, port, login_state.clone(), bus.clone(), socket.to_path_buf(), files.clone(), turn_lock.clone(), )); tokio::spawn(hive_ag3nt::forge_notify::run(socket.to_path_buf(), true)); match initial { LoginState::Online => { manager_serve_loop( socket, Duration::from_millis(poll_ms), login_state, claude_dir, bus, stats, &files, turn_lock, ) .await } LoginState::NeedsLogin => { turn::wait_for_login(&claude_dir, login_state.clone(), &bus, poll_ms).await; manager_serve_loop( socket, Duration::from_millis(poll_ms), login_state, claude_dir, bus, stats, &files, turn_lock, ) .await } } } #[allow(clippy::too_many_arguments)] async fn manager_serve_loop( socket: &Path, interval: Duration, login_state: Arc>, claude_dir: std::path::PathBuf, bus: Bus, stats: Option, files: &turn::TurnFiles, turn_lock: TurnLock, ) -> Result<()> { tracing::info!(socket = %socket.display(), "hive-m1nd serve"); manager_requeue_inflight(socket).await; loop { let recv: Result = client::request( socket, &ManagerRequest::Recv { wait_seconds: Some(180), max: None, }, ) .await; match recv { Ok(ManagerResponse::Messages { messages }) if !messages.is_empty() => { let first = messages.into_iter().next().expect("checked non-empty"); let auth_failed = handle_manager_turn(socket, &bus, stats.as_ref(), files, &turn_lock, first) .await; if auth_failed { *login_state.lock().unwrap() = LoginState::NeedsLogin; turn::wait_for_login( &claude_dir, login_state.clone(), &bus, u64::try_from(interval.as_millis()).unwrap_or(2000), ) .await; } } Ok(ManagerResponse::Messages { .. }) => { tokio::time::sleep(interval).await; } Ok( ManagerResponse::Ok | ManagerResponse::Status { .. } | ManagerResponse::QuestionQueued { .. } | ManagerResponse::Recent { .. } | ManagerResponse::Logs { .. } | ManagerResponse::LooseEnds { .. } | ManagerResponse::PendingRemindersCount { .. } | ManagerResponse::ReminderRollup { .. } | ManagerResponse::AgentMeta { .. } | ManagerResponse::Schedules { .. }, ) => { tracing::warn!("recv produced unexpected response kind"); } Ok(ManagerResponse::Err { message }) => { tracing::warn!(%message, "recv error"); } Err(e) => { tracing::warn!(error = ?e, "recv failed; retrying"); } } } } async fn handle_manager_turn( socket: &Path, bus: &Bus, stats: Option<&TurnStats>, files: &turn::TurnFiles, turn_lock: &TurnLock, first: hive_sh4re::DeliveredMessage, ) -> bool { let from = first.from; let body = first.body; let redelivered = first.redelivered; if from == SYSTEM_SENDER { let parsed = serde_json::from_str::(&body).ok(); if let Some(event) = parsed { tracing::info!(?event, "helper event"); } else { tracing::info!(%from, %body, "system message"); } bus.emit(LiveEvent::Note { text: format!("[system] {body}") }); } tracing::info!(%from, %body, %redelivered, "manager inbox"); let unread = manager_inbox_unread(socket).await; bus.emit(LiveEvent::TurnStart { from: from.clone(), body: body.clone(), unread }); let prompt = serve_common::format_wake_prompt(&from, &body, unread, redelivered); bus.set_state(TurnState::Thinking); let started_at = serve_common::now_unix(); let started_instant = std::time::Instant::now(); let model_at_start = bus.model(); let outcome = { let _guard = turn_lock.lock().await; turn::drive_turn(&prompt, files, bus).await }; turn::emit_turn_end(bus, &outcome); bus.set_state(TurnState::Idle); if matches!(outcome, turn::TurnOutcome::Ok | turn::TurnOutcome::Compacted) { manager_ack_turn(socket).await; } if matches!(outcome, turn::TurnOutcome::RateLimited) { let secs = turn::rate_limit_sleep_secs(); bus.emit_status("rate_limited"); bus.emit(LiveEvent::Note { text: format!("API rate-limited — sleeping {secs}s before retry"), }); tracing::warn!(sleep_secs = secs, "rate-limited; parking"); tokio::time::sleep(Duration::from_secs(secs)).await; manager_requeue_inflight(socket).await; bus.emit_status("online"); } if matches!(outcome, turn::TurnOutcome::AuthFailed) { bus.emit_status("needs_login_idle"); bus.emit(LiveEvent::Note { text: "API 401 — waiting for re-login via web UI".into(), }); tracing::warn!("auth-failed; parking until re-login"); manager_requeue_inflight(socket).await; } if let Some(stats) = stats { let ended_at = serve_common::now_unix(); let duration_ms = i64::try_from(started_instant.elapsed().as_millis()).unwrap_or(i64::MAX); let (open_threads, open_reminders) = manager_post_turn_counts(socket).await; let row = serve_common::build_row( started_at, ended_at, duration_ms, model_at_start, from.clone(), &outcome, bus, open_threads, open_reminders, ); stats.record(&row); } let pending = manager_inbox_unread(socket).await; if pending > 0 { tracing::info!(%pending, "pending messages after turn; fetching next"); } matches!(outcome, turn::TurnOutcome::AuthFailed) } async fn manager_ack_turn(socket: &Path) { match client::request::<_, ManagerResponse>(socket, &ManagerRequest::AckTurn).await { Ok(ManagerResponse::Ok) => {} Ok(ManagerResponse::Err { message }) => { tracing::warn!(%message, "ack_turn rejected by broker"); } Ok(other) => { tracing::warn!(?other, "ack_turn unexpected response"); } Err(e) => tracing::warn!(error = ?e, "ack_turn transport error"), } } async fn manager_requeue_inflight(socket: &Path) { match client::request::<_, ManagerResponse>(socket, &ManagerRequest::RequeueInflight).await { Ok(ManagerResponse::Ok) => {} Ok(ManagerResponse::Err { message }) => { tracing::warn!(%message, "requeue_inflight rejected by broker"); } Ok(other) => { tracing::warn!(?other, "requeue_inflight unexpected response"); } Err(e) => tracing::warn!(error = ?e, "requeue_inflight transport error"), } } async fn manager_inbox_unread(socket: &Path) -> u64 { match client::request::<_, ManagerResponse>(socket, &ManagerRequest::Status).await { Ok(ManagerResponse::Status { unread }) => unread, _ => 0, } } async fn manager_post_turn_counts(socket: &Path) -> (Option, Option) { let threads = match client::request::<_, ManagerResponse>( socket, &ManagerRequest::GetLooseEnds { agent: None }, ) .await { Ok(ManagerResponse::LooseEnds { loose_ends }) => u64::try_from(loose_ends.len()).ok(), _ => None, }; let reminders = match client::request::<_, ManagerResponse>( socket, &ManagerRequest::CountPendingReminders { agent: None }, ) .await { Ok(ManagerResponse::PendingRemindersCount { count }) => Some(count), _ => None, }; (threads, reminders) }