diff --git a/docs/tools/hivectl-cli.md b/docs/tools/hivectl-cli.md index 4b466440..49b83751 100644 --- a/docs/tools/hivectl-cli.md +++ b/docs/tools/hivectl-cli.md @@ -24,6 +24,7 @@ This document contains the help content for the `hivectl` command-line program. * [`hivectl wg init`↴](#hivectl-wg-init) * [`hivectl wg peer`↴](#hivectl-wg-peer) * [`hivectl wg status`↴](#hivectl-wg-status) +* [`hivectl peer-config`↴](#hivectl-peer-config) * [`hivectl choom`↴](#hivectl-choom) * [`hivectl stop`↴](#hivectl-stop) * [`hivectl start`↴](#hivectl-start) @@ -49,6 +50,7 @@ Sibling to the `hive-c0re` daemon binary. Covers host-side admin operations that * `gateway` — Gateway htpasswd user management. Add, remove, or list users in an htpasswd file used by the gateway's HTTP Basic auth (`services.hyperhive.gateway.auth`). Credentials are stored as `BCrypt` hashes — no extra service or PAM required * `agents` — Agent container management. Requires the hive-c0re daemon to be running (connects to the host admin socket) * `wg` — WireGuard inter-hive mesh setup helpers (`services.hyperhive.swarm`) +* `peer-config` — Generate the federation peer-config block for THIS hive — the nix a peer operator pastes into their `services.hyperhive.swarm.peers` to trust + reach this hive. Emits `caCert` (+ a `cp` line for the cert) when this hive serves a self-signed CA, the WireGuard public key when the mesh key exists, and the `wireguard{Address,Endpoint}` you pass. The hive's own domain is filled in automatically from the running daemon (`services.hyperhive.domain`). Reads local state (the TLS CA cert, the wg key); never mutates. `wg init` calls this at the end, so a fresh mesh setup prints the hand-over block too * `choom` — Open an interactive Claude session inside an agent container * `stop` — Stop containers hive-wide in one operator action. Bare `hivectl stop` stops **everything** — all sub-agents plus the ci, forge, gateway, and matrix infra containers. Narrow it with scope flags: `--agents` (all sub-agents), `--ci` / `--forge` / `--gateway` / `--matrix` (named infra), and `--agent ` (repeatable) for specific sub-agents. Flags are additive (e.g. `--agents --matrix`). Requires the hive-c0re daemon (connects to the host admin socket). hive-c0re itself is never stopped — it services the request * `start` — Start containers hive-wide — the inverse of `hivectl stop`. Bare `hivectl start` starts everything back up; the same scope flags as `stop` narrow it (`--agents`, `--ci`, `--forge`, `--gateway`, `--matrix`, `--agent `). Requires the hive-c0re daemon @@ -344,6 +346,19 @@ Show the live mesh interface state (`wg show wg-hive`). Requires the mesh to be +## `hivectl peer-config` + +Generate the federation peer-config block for THIS hive — the nix a peer operator pastes into their `services.hyperhive.swarm.peers` to trust + reach this hive. Emits `caCert` (+ a `cp` line for the cert) when this hive serves a self-signed CA, the WireGuard public key when the mesh key exists, and the `wireguard{Address,Endpoint}` you pass. The hive's own domain is filled in automatically from the running daemon (`services.hyperhive.domain`). Reads local state (the TLS CA cert, the wg key); never mutates. `wg init` calls this at the end, so a fresh mesh setup prints the hand-over block too + +**Usage:** `hivectl peer-config [OPTIONS]` + +###### **Options:** + +* `--wg-address ` — This hive's WireGuard mesh address (e.g. `10.42.0.1/32`), emitted as `wireguardAddress`. Omit when not running the mesh +* `--wg-endpoint ` — This hive's public WireGuard endpoint (`host:port`), emitted as `wireguardEndpoint`. Omit when peers dial in / no mesh + + + ## `hivectl choom` Open an interactive Claude session inside an agent container. diff --git a/hive-c0re/src/bin/hivectl.rs b/hive-c0re/src/bin/hivectl.rs index 17d328c7..a7c1c25d 100644 --- a/hive-c0re/src/bin/hivectl.rs +++ b/hive-c0re/src/bin/hivectl.rs @@ -89,6 +89,25 @@ enum Cmd { #[command(subcommand)] cmd: WgCmd, }, + /// Generate the federation peer-config block for THIS hive — the nix + /// a peer operator pastes into their `services.hyperhive.swarm.peers` + /// to trust + reach this hive. Emits `caCert` (+ a `cp` line for the + /// cert) when this hive serves a self-signed CA, the WireGuard public + /// key when the mesh key exists, and the `wireguard{Address,Endpoint}` + /// you pass. The hive's own domain is filled in automatically from the + /// running daemon (`services.hyperhive.domain`). Reads local state (the + /// TLS CA cert, the wg key); never mutates. `wg init` calls this at the + /// end, so a fresh mesh setup prints the hand-over block too. + PeerConfig { + /// This hive's WireGuard mesh address (e.g. `10.42.0.1/32`), + /// emitted as `wireguardAddress`. Omit when not running the mesh. + #[arg(long)] + wg_address: Option, + /// This hive's public WireGuard endpoint (`host:port`), emitted as + /// `wireguardEndpoint`. Omit when peers dial in / no mesh. + #[arg(long)] + wg_endpoint: Option, + }, /// Open an interactive Claude session inside an agent container. /// /// Replaces the current process with `machinectl shell @@ -562,7 +581,7 @@ async fn main() -> Result<()> { AgentsCmd::RestartAll => agents_restart_all(&socket).await, }, Cmd::Wg { cmd } => match cmd { - WgCmd::Init { address } => wg_init(address.as_deref()), + WgCmd::Init { address } => wg_init(&socket, address.as_deref()).await, WgCmd::Peer { domain, pubkey, @@ -574,6 +593,14 @@ async fn main() -> Result<()> { } WgCmd::Status => wg_status(), }, + Cmd::PeerConfig { + wg_address, + wg_endpoint, + } => { + let domain = require_hive_domain(&socket).await?; + peer_config(&domain, wg_address.as_deref(), wg_endpoint.as_deref()); + Ok(()) + } Cmd::Stop { scope, graceful } => stop(&socket, scope.to_scope(), graceful).await, Cmd::Start { scope } => start(&socket, scope.to_scope()).await, Cmd::Restart { scope, graceful } => restart(&socket, scope.to_scope(), graceful).await, @@ -612,9 +639,41 @@ const WG_KEY_PATH: &str = "/etc/wireguard/hive.key"; /// The mesh interface name hive-c0re's nix module brings up. const WG_INTERFACE: &str = "wg-hive"; +/// Host path of this hive's self-signed CA cert (matches the +/// `services.hyperhive.tls.stateDir` default in hive-tls.nix). Its +/// existence means the gateway serves a self-signed, hive-CA-signed leaf, +/// so a federating peer needs this CA via `swarm.peers..caCert`. Absent +/// = ACME / operator cert (trusted by the default CA bundle, no `caCert`). +const HIVE_TLS_CA_PATH: &str = "/var/lib/hive-tls/ca.pem"; + +/// Best-effort query for this hive's domain from the running daemon +/// (`HostRequest::HiveDomain`, which reads `HYPERHIVE_HIVE_DOMAIN` from +/// c0re's service env). `None` when the daemon is unreachable or the +/// domain is unset — callers decide whether that's fatal. +async fn query_hive_domain(socket: &Path) -> Option { + hive_c0re::client::request(socket, hive_sh4re::HostRequest::HiveDomain) + .await + .ok() + .and_then(|r| r.domain) +} + +/// Require this hive's domain from the daemon for snippet generation. +/// Errors with a clear hint when it can't be resolved, so `peer-config` +/// never silently emits a wrong key. +async fn require_hive_domain(socket: &Path) -> Result { + query_hive_domain(socket).await.context( + "could not determine this hive's domain from the daemon — is hive-c0re running \ + and `services.hyperhive.domain` set?", + ) +} + /// `wg init` — generate (if absent) the hive's WireGuard key, print its -/// public key + the nix snippet to enable the mesh. -fn wg_init(address: Option<&str>) -> Result<()> { +/// public key + the nix snippet to enable the mesh, then (best-effort) +/// the `peer-config` block peers paste to federate with this hive, so a +/// fresh setup is one command. The domain comes from the daemon; if it +/// can't be resolved, the peer block is skipped (init still succeeds — +/// its core job is enabling the mesh locally). +async fn wg_init(socket: &Path, address: Option<&str>) -> Result<()> { use std::os::unix::fs::PermissionsExt as _; let key_path = Path::new(WG_KEY_PATH); if key_path.exists() { @@ -657,6 +716,14 @@ fn wg_init(address: Option<&str>) -> Result<()> { println!(" address = \"{addr}\";"); println!(" # listenPort = 51820; # default"); println!(" }};"); + + // Also print the block a peer pastes to federate with us (CA + this + // mesh key) — one-stop setup. Domain comes from the daemon; + // best-effort, so init still succeeds when it can't be resolved. + if let Some(d) = query_hive_domain(socket).await { + println!(); + peer_config(&d, address, None); + } Ok(()) } @@ -702,6 +769,51 @@ fn wg_peer(domain: &str, pubkey: &str, address: &str, endpoint: Option<&str>) { println!(" }};"); } +/// `peer-config` — print the `swarm.peers.""` block a peer +/// operator pastes to federate with THIS hive, plus a `cp` line for the +/// CA when this hive is self-signed. Reads local state only (the TLS CA +/// cert presence + the wg key); prints, never mutates. +fn peer_config(domain: &str, wg_address: Option<&str>, wg_endpoint: Option<&str>) { + let self_signed = Path::new(HIVE_TLS_CA_PATH).exists(); + // CA filename derived from the first DNS label so multiple peers' + // certs don't collide in the operator's config dir. + let ca_file = format!("{}-ca.pem", domain.split('.').next().unwrap_or("peer")); + // WireGuard public key, when this hive has a mesh key. Best-effort: + // a missing key or absent `wg` binary just omits the mesh lines. + let wg_pub = std::fs::read(WG_KEY_PATH) + .ok() + .and_then(|k| wg_pubkey(&k).ok()); + + if self_signed { + println!("# 1. copy this hive's CA cert next to the peer's config:"); + println!("cp {HIVE_TLS_CA_PATH} ./{ca_file}"); + println!(); + println!("# 2. paste into the peer hive's NixOS config:"); + } else { + println!("# paste into the peer hive's NixOS config:"); + } + println!("services.hyperhive.swarm.peers.\"{domain}\" = {{"); + if self_signed { + println!(" caCert = ./{ca_file};"); + } + if let Some(pk) = &wg_pub { + println!(" wireguardPublicKey = \"{pk}\";"); + } + if let Some(addr) = wg_address { + println!(" wireguardAddress = \"{addr}\";"); + } + if let Some(ep) = wg_endpoint { + println!(" wireguardEndpoint = \"{ep}\";"); + } + println!("}};"); + if !self_signed { + println!( + "# (this hive's cert chains to a public CA — no `caCert` needed; \ + it's trusted by the default bundle.)" + ); + } +} + /// `wg status` — show the live mesh interface (`wg show wg-hive`), /// inheriting stdout so the operator sees it directly. fn wg_status() -> Result<()> { diff --git a/hive-c0re/src/server.rs b/hive-c0re/src/server.rs index 8fc56bc5..2248cb90 100644 --- a/hive-c0re/src/server.rs +++ b/hive-c0re/src/server.rs @@ -114,6 +114,16 @@ async fn dispatch(req: &HostRequest, coord: Arc) -> HostResponse { } HostRequest::Rebuild { name } => handle_rebuild(&coord, name).await?, HostRequest::List => HostResponse::list(lifecycle::list().await?), + // The hive domain is injected into c0re's service env by + // hive-c0re.nix (`HYPERHIVE_HIVE_DOMAIN`); surface it so the + // operator CLI can fill in this hive's own identity. + HostRequest::HiveDomain => HostResponse::hive_domain( + // Treat an empty env value as unset — otherwise the CLI + // would emit `swarm.peers."" = …`, invalid nix. + std::env::var("HYPERHIVE_HIVE_DOMAIN") + .ok() + .filter(|d| !d.is_empty()), + ), HostRequest::Pending => HostResponse::pending(coord.approvals.pending()?), HostRequest::Approve { id } => { actions::approve(coord.clone(), *id).await?; @@ -210,6 +220,7 @@ async fn handle_restart_all() -> Result { error: Some(errors.join("; ")), agents: Some(ok_agents), approvals: None, + domain: None, }) } } @@ -368,6 +379,7 @@ fn finish_lifecycle(ok_items: Vec, errors: &[String]) -> HostResponse { error: Some(errors.join("; ")), agents: Some(ok_items), approvals: None, + domain: None, } } } diff --git a/hive-sh4re/src/lib.rs b/hive-sh4re/src/lib.rs index b49f1963..ed121f15 100644 --- a/hive-sh4re/src/lib.rs +++ b/hive-sh4re/src/lib.rs @@ -44,6 +44,11 @@ pub enum HostRequest { Rebuild { name: String }, /// List managed containers. List, + /// Report this hive's canonical DNS domain + /// (`services.hyperhive.domain`), or `None` when unset. Lets the + /// operator CLI fill in the hive's own identity (e.g. the federation + /// peer-config block) without the operator retyping it. + HiveDomain, /// List pending approval requests. Pending, /// Approve a pending request by id; the action runs immediately. @@ -131,6 +136,10 @@ pub struct HostResponse { pub agents: Option>, #[serde(default, skip_serializing_if = "Option::is_none")] pub approvals: Option>, + /// This hive's canonical DNS domain — `HiveDomain` result. `None` + /// when the domain is unset (no `services.hyperhive.domain`). + #[serde(default, skip_serializing_if = "Option::is_none")] + pub domain: Option, } /// One row in the approval queue. `commit_ref` is overloaded per @@ -218,6 +227,7 @@ impl HostResponse { error: None, agents: None, approvals: None, + domain: None, } } @@ -228,6 +238,7 @@ impl HostResponse { error: Some(message.into()), agents: None, approvals: None, + domain: None, } } @@ -238,6 +249,7 @@ impl HostResponse { error: None, agents: Some(agents), approvals: None, + domain: None, } } @@ -248,6 +260,19 @@ impl HostResponse { error: None, agents: None, approvals: Some(approvals), + domain: None, + } + } + + /// `HiveDomain` result — this hive's canonical domain (or `None`). + #[must_use] + pub fn hive_domain(domain: Option) -> Self { + Self { + ok: true, + error: None, + agents: None, + approvals: None, + domain, } } }