196 lines
9.2 KiB
Rust
196 lines
9.2 KiB
Rust
//! First-spawn provisioning: seed the hive-c0re-owned applied repo, and
|
|
//! ensure the per-agent state / claude-credentials dirs (btrfs subvolume when
|
|
//! available) exist.
|
|
//!
|
|
//! Seeding is the only write the repo gets from here. Later config changes
|
|
//! arrive as forge PRs authored in a clone - nothing edits a working tree in
|
|
//! place.
|
|
|
|
use std::path::Path;
|
|
|
|
use anyhow::{Context, Result, bail};
|
|
|
|
use super::git::{git, git_commit, git_rev_parse, git_tag};
|
|
|
|
/// Seed an agent's applied repo on first spawn, preferring the config the
|
|
/// forge already has. `agent-configs/<name>` is authored by whoever created
|
|
/// the agent (at swarm level the controller, which writes the config before
|
|
/// any hive is told to deploy it), so this takes the forge's `main` when
|
|
/// there is one and writes a template only when there is not. Two authors for
|
|
/// one file is the failure mode being avoided: whichever wrote second would
|
|
/// win, and neither knows about the other.
|
|
///
|
|
/// The template ([`seed_template`]) is the fallback when there is genuinely
|
|
/// nothing to take yet: `swarm-controller` creates `agent-configs/<name>`
|
|
/// before telling a hive to deploy, but hasn't necessarily pushed `main` to
|
|
/// it, or the forge is unreachable, or this hive has no forge read token.
|
|
///
|
|
/// Seeding is the only write hive-c0re makes here. Later config changes
|
|
/// arrive as forge PRs and are fetched from the forge's `main` (see
|
|
/// `actions::advance_applied_to_rev`). `flake.nix` is tracked in the seed
|
|
/// and rides along on every fetch.
|
|
///
|
|
/// A repo that is already there is only checked for its shape (a rebuild
|
|
/// finds it already seeded): a missing `deployed/0` tag means it predates the
|
|
/// meta-flake layout and is an error.
|
|
pub async fn setup_applied(applied_dir: &Path, name: &str) -> Result<()> {
|
|
std::fs::create_dir_all(applied_dir)
|
|
.with_context(|| format!("create {}", applied_dir.display()))?;
|
|
|
|
if !applied_dir.join(".git").exists() {
|
|
if crate::forge::fetch_config_main_into_applied(name).await {
|
|
return Ok(());
|
|
}
|
|
seed_template(applied_dir, name).await?;
|
|
git_tag(applied_dir, "deployed/0", "refs/heads/main").await?;
|
|
} else if git_rev_parse(applied_dir, "refs/tags/deployed/0")
|
|
.await
|
|
.is_err()
|
|
{
|
|
// Pre-overhaul applied repo - no deployed/* tag scheme,
|
|
// flake.nix may be untracked, agent.nix possibly authored by
|
|
// hive-c0re directly. The startup auto-migration fixes this
|
|
// in place; if it didn't run (or got skipped), surface a
|
|
// clear error.
|
|
bail!(
|
|
"applied repo at {} predates the meta-flake layout. \
|
|
Restart hive-c0re to let the auto-migration run, or \
|
|
destroy --purge {name} and re-spawn.",
|
|
applied_dir.display()
|
|
);
|
|
}
|
|
Ok(())
|
|
}
|
|
|
|
/// Author the initial config in place: `agent.nix` (the agent's own module)
|
|
/// and `flake.nix` (the boilerplate that lets the meta flake import this repo
|
|
/// as an input: meta locks at a specific sha and reads
|
|
/// `nixosModules.default`, so `flake.nix` must be in the commit). `flake.nix`
|
|
/// isn't meant to be edited, but it's tracked so it can be read.
|
|
///
|
|
/// The fallback half of [`setup_applied`]: reached only when the forge has
|
|
/// no config for this agent to take.
|
|
async fn seed_template(dir: &Path, name: &str) -> Result<()> {
|
|
let agent_path = dir.join("agent.nix");
|
|
if !agent_path.exists() {
|
|
std::fs::write(&agent_path, initial_agent_nix(name))
|
|
.with_context(|| format!("write {}", agent_path.display()))?;
|
|
}
|
|
let flake_path = dir.join("flake.nix");
|
|
if !flake_path.exists() {
|
|
std::fs::write(&flake_path, initial_flake_nix())
|
|
.with_context(|| format!("write {}", flake_path.display()))?;
|
|
}
|
|
git(dir, &["init", "--initial-branch=main"]).await?;
|
|
git(dir, &["add", "agent.nix", "flake.nix"]).await?;
|
|
git_commit(dir, "hive-c0re init").await
|
|
}
|
|
|
|
/// Create the per-agent Claude credentials dir if missing. Mode 0755 — hive-core
|
|
/// needs read+execute to list the directory so `claude_has_session` can detect a
|
|
/// valid session; credential files inside (`.credentials.json` etc.) are 0600 so
|
|
/// secrets stay private regardless of the directory mode. Idempotent: existing
|
|
/// dirs are left untouched (an agent's OAuth tokens survive `destroy`/recreate).
|
|
pub fn ensure_claude_dir(claude_dir: &Path) -> Result<()> {
|
|
use std::io;
|
|
if !claude_dir.exists() {
|
|
std::fs::create_dir_all(claude_dir)
|
|
.with_context(|| format!("create {}", claude_dir.display()))?;
|
|
}
|
|
// 0755: hive-core (different user from the agent) needs read+execute to
|
|
// list the directory so `claude_has_session` can detect a valid session.
|
|
// The credential files inside (`.credentials.json` etc.) are 0600 so the
|
|
// secrets themselves stay private regardless of the directory mode.
|
|
//
|
|
// Best-effort: on the first container boot, `hive-agent-user-migrate`
|
|
// chowns this dir to the agent user. After that, hive-core (a different
|
|
// user) cannot chmod it (EPERM) — that's fine because the mode set during
|
|
// initial creation (0755) is preserved through the chown. Any other error
|
|
// (ENOENT, I/O error) is unexpected and propagated.
|
|
#[cfg(unix)]
|
|
{
|
|
use std::os::unix::fs::PermissionsExt;
|
|
match std::fs::set_permissions(claude_dir, std::fs::Permissions::from_mode(0o755)) {
|
|
Ok(()) => {}
|
|
Err(e) if e.kind() == io::ErrorKind::PermissionDenied => {
|
|
tracing::debug!(
|
|
path = %claude_dir.display(),
|
|
"ensure_claude_dir: chmod 755 skipped (dir likely owned by agent user after migration)"
|
|
);
|
|
}
|
|
Err(e) => {
|
|
return Err(e).with_context(|| format!("chmod 755 {}", claude_dir.display()));
|
|
}
|
|
}
|
|
}
|
|
Ok(())
|
|
}
|
|
|
|
/// Create the per-agent state dir if missing. Also creates the sibling
|
|
/// `harness/` dir so the first harness startup can write its sqlite files
|
|
/// immediately, and the sibling `work/` dir.
|
|
pub fn ensure_state_dir(notes_dir: &Path) -> Result<()> {
|
|
if !notes_dir.exists() {
|
|
std::fs::create_dir_all(notes_dir)
|
|
.with_context(|| format!("create {}", notes_dir.display()))?;
|
|
}
|
|
// Harness and work dirs are siblings of the agent-visible state dir.
|
|
if let Some(parent) = notes_dir.parent() {
|
|
for sibling in ["harness", crate::paths::WORK_SUBDIR] {
|
|
let dir = parent.join(sibling);
|
|
if !dir.exists() {
|
|
std::fs::create_dir_all(&dir)
|
|
.with_context(|| format!("create {}", dir.display()))?;
|
|
}
|
|
}
|
|
}
|
|
Ok(())
|
|
}
|
|
|
|
/// Ensure agent `name`'s persistent state root
|
|
/// (`/var/lib/hyperhive/agents/<name>`) is a btrfs subvolume — when the host
|
|
/// filesystem supports it — BEFORE the per-agent subdirs (`state/`, `claude/`,
|
|
/// `harness/`, `work/`) are created by `ensure_state_dir` / `ensure_claude_dir`.
|
|
///
|
|
/// Progressive enhancement: if the root already exists
|
|
/// (any agent provisioned before this landed, plain dir or subvol) it's left
|
|
/// exactly as-is — no auto-migration — and the priv round-trip is skipped. On
|
|
/// a non-btrfs host the priv op no-ops and the root is later created as a
|
|
/// plain dir by `ensure_*_dir`, identical to the old behaviour. Only a
|
|
/// brand-new agent on a btrfs host gets a real subvolume. Subvolume creation
|
|
/// is privileged, so it's delegated to hive-priv.
|
|
pub async fn ensure_agent_state_subvolume(name: &str) -> Result<()> {
|
|
let agent = hive_types::Ident::parse(name)
|
|
.map_err(|e| anyhow::anyhow!("invalid agent name {name:?}: {e}"))?;
|
|
let root = crate::paths::agent_state_dir(&agent);
|
|
if root.exists() {
|
|
return Ok(());
|
|
}
|
|
crate::priv_client::ensure_agent_subvolume(name)
|
|
.await
|
|
.with_context(|| format!("ensure btrfs subvolume for agent {name}"))
|
|
}
|
|
|
|
fn initial_agent_nix(name: &str) -> String {
|
|
format!(
|
|
"{{ config, pkgs, lib, ... }}:\n{{\n # Per-agent overrides for {name}. This is a regular NixOS module\n # — add packages, services, modules, imports as needed.\n #\n # imports = [ ./extra-module.nix ];\n # environment.systemPackages = with pkgs; [ ];\n}}\n",
|
|
)
|
|
}
|
|
|
|
/// Module-only flake exposed by every agent's repo. Consumed by the
|
|
/// swarm's `internal/meta` flake as a flake input. The wrapper is
|
|
/// intentionally permissive:
|
|
///
|
|
/// - Manager edits `inputs.* = …` to add other flakes (e.g. an MCP
|
|
/// server's own flake) — the lock for those lands in the agent's
|
|
/// own `flake.lock` and rolls up into meta's lock transitively.
|
|
/// - The outputs block forwards every input (minus `self`) into
|
|
/// `agent.nix` as the `flakeInputs` module argument, so the
|
|
/// manager just references `flakeInputs.<name>.packages.${pkgs.system}.default`
|
|
/// without further plumbing.
|
|
///
|
|
/// Identity injection (`HIVE_PORT` / `HIVE_LABEL` / dashboard port /
|
|
/// git committer) still lives in the meta flake's wrapper.
|
|
pub fn initial_flake_nix() -> &'static str {
|
|
"{\n description = \"hyperhive agent\";\n inputs = { };\n outputs =\n { self, ... }@inputs:\n {\n nixosModules.default = {\n imports = [ ./agent.nix ];\n _module.args.flakeInputs = builtins.removeAttrs inputs [ \"self\" ];\n };\n };\n}\n"
|
|
}
|