hyperhive/hive-c0re/src/forge/mod.rs

//! Optional Forgejo wiring — the `core/meta` repo and meta read-access
//! grants. Those writes, as `core`, run only beside a local `hive-forge`
//! container; reads of the forge go through [`reader_token`] on every hive.
//! The swarm-wide orgs, teams and repos, and each agent's read grant on
//! `internal/docs`, are swarm-controller's. Full design:
//! `docs/integrations/forge.md`.

mod pr_comment;
mod reader;
mod reconcile;
mod repos;
mod users;

pub use pr_comment::{config_repo, merged_pr_for_commit, post_pr_comment};
pub use reader::reader_token;
pub use reconcile::{fetch_forge_main, reconcile_config_apply, reconcile_config_status};
pub use repos::{
    clone_config_into_proposed, ensure_meta_remote, ensure_repo, fast_forward_applied_main,
    fetch_config_main_into_applied, meta_read_access, push_meta,
};
pub use users::core_token;

use std::sync::OnceLock;
use std::time::{Duration, Instant};

use anyhow::{Context, Result};
use forgejo_api::{Auth, Forgejo};
use url::Url;

use users::{ensure_core_avatar, ensure_core_user_and_token};

const FORGE_CONTAINER: &str = "hive-forge";

/// Base HTTP URL for the local Forgejo instance, from `HIVE_FORGE_URL`
/// (set unconditionally by the hyperhive NixOS module on the `hive-c0re`
/// unit, to `http://<forge.domain>`).
///
/// # Panics
///
/// When `HIVE_FORGE_URL` is unset. That is deliberate: this daemon only
/// runs under the NixOS module, which always sets it, so an unset var
/// means the deployment is broken. There is no loopback fallback,
/// because a guess is wrong in exactly the cases that matter — the
/// forge may live on a different host from the daemon, and a fallback
/// turns "misconfigured" into "silently talking to the wrong machine"
/// or, worse, "connection refused" surfacing far from its cause.
pub(crate) fn forge_http_base() -> &'static str {
    static BASE: OnceLock<String> = OnceLock::new();
    BASE.get_or_init(|| {
        std::env::var("HIVE_FORGE_URL").expect(
            "HIVE_FORGE_URL is unset — the hyperhive NixOS module sets it \
             unconditionally on the hive-c0re unit, so this process was \
             started outside that unit",
        )
    })
}

/// Git remote for `repo` (e.g. `"core/meta"`) — **credential-free**.
///
/// The token does not go here. A URL is a process argument, and `argv` is
/// world-readable through `/proc/<pid>/cmdline` for as long as the git child
/// lives, so a credentialed remote publishes the core admin token to every
/// local user on the host. Credentials travel in the environment instead, via
/// [`core_auth_header`] and [`crate::lifecycle::git_command_authed`] —
/// `/proc/<pid>/environ` is owner-only.
pub(crate) fn forge_git_url(repo: &str) -> String {
    git_url_with_base(forge_http_base(), repo)
}

/// The pure half of [`forge_git_url`], split out so it can be tested without a
/// process-wide env var (which would race every other test in this binary).
fn git_url_with_base(base: &str, repo: &str) -> String {
    format!("{base}/{repo}.git")
}

/// The `http.extraHeader` value authenticating as the forge core user.
pub(crate) fn core_auth_header(token: &str) -> String {
    basic_auth_header("core", token)
}

/// The `http.extraHeader` value carrying `token`. Forgejo takes the account
/// from the token, so `login` only labels the request.
///
/// Basic auth over a header rather than userinfo in the URL, so the secret
/// reaches git through the environment (see [`forge_git_url`]). Pair with
/// [`crate::lifecycle::git_command_authed`], which is the only thing that
/// should ever hold the result.
fn basic_auth_header(login: &str, token: &str) -> String {
    use base64::Engine as _;
    let basic = base64::engine::general_purpose::STANDARD.encode(format!("{login}:{token}"));
    format!("Authorization: Basic {basic}")
}

/// Forgejo org grouping every agent's config repo. Core is a site admin
/// and reads + writes every repo here. Each agent is a **write collaborator
/// on its own** `agent-configs/<name>` repo — the editable PR surface it
/// pushes config-change branches to. `main`'s branch protection is
/// swarm-controller's: merge and approval allowlisted to the `operators` team,
/// so the agent can't push `main` or self-merge, and an operator's merge
/// deploys through swarm-controller. The repos remain private, so an agent
/// still can't reach *another* agent's config. hive-c0re only reads from it.
pub(crate) const CONFIG_ORG: &str = "agent-configs";

/// Leak `s` to get a `&'static str` warning `kind` for the small, bounded
/// set of boot warnings in [`ensure_all`] keyed by a runtime name (at
/// most a handful per process). [`crate::warnings::set_boot_warning`]
/// requires a `'static` kind so distinct orgs/repos don't clobber each
/// other's banner entry; leaking a few short strings once per boot is
/// cheap and bounded, unlike a per-request or per-loop-iteration leak.
fn static_kind(s: String) -> &'static str {
    Box::leak(s.into_boxed_str())
}

/// Probe whether `hive-forge` exists as a nixos-container. Cheap —
/// `nixos-container list` is just a directory scan in /etc. Routed
/// through hive-priv: `nixos-container` needs root, and hive-c0re runs
/// unprivileged (privsep).
pub async fn is_present() -> bool {
    let Ok(stdout) = crate::priv_client::list_containers().await else {
        return false;
    };
    stdout.lines().any(|l| l.trim() == FORGE_CONTAINER)
}

/// Name a `forgejo admin` invocation for an error message without
/// reproducing its arguments: keep the leading verb path, stop at the
/// first flag. `["user", "create", "--username", "iris", "--password",
/// "…"]` becomes `forgejo admin user create`.
///
/// The verbs are an **allowlist**, and that is the whole point. Some
/// callers pass a live secret as an argument value (`--password`), so a
/// message built from the raw vector puts it in the log. Listing the
/// flags to *hide* instead would repeat the bug this guards against: a
/// newly added secret-bearing flag would leak until someone remembered
/// to extend the list. Verbs are a closed set this crate chooses
/// itself; argument values never are.
fn describe_forge_admin(args: &[&str]) -> String {
    let verbs: Vec<&str> = args
        .iter()
        .take_while(|a| !a.starts_with('-'))
        .copied()
        .collect();
    if verbs.is_empty() {
        "forgejo admin".to_owned()
    } else {
        format!("forgejo admin {}", verbs.join(" "))
    }
}

/// Run `forgejo admin <args>` inside the hive-forge container as the
/// forgejo user (the only uid with write access to the state dir).
/// Returns stdout on success; bails with stderr context on failure.
async fn forge_admin(args: &[&str]) -> Result<String> {
    // Route through hive-priv (root helper) because `nixos-container run`
    // uses nsenter to enter the container's namespaces, which requires root.
    // hive-c0re runs as the unprivileged `hive-core` user and cannot call
    // nsenter directly — doing so produces:
    //   nsenter: stat of /proc/<pid>/ns/user failed: Permission denied
    let (stdout, _stderr) = crate::priv_client::run_forge_admin(args)
        .await
        .with_context(|| format!("{} (via hive-priv)", describe_forge_admin(args)))?;
    Ok(stdout)
}

/// Typed Forgejo API client for the local forge ([`forge_http_base()`]),
/// authenticated as `token`. All Forgejo API calls that don't shell
/// out to `forgejo admin` go through clients built here — one place
/// for the base URL and auth. Tokens differ per call site (core admin
/// token vs per-agent tokens), so the token is passed per call; the
/// base URL is parsed once. Failures surface as
/// `forgejo_api::ForgejoError`, whose Display carries the HTTP status
/// and the API's error message (e.g. the validation reason on a 422).
pub(crate) fn api(token: &str) -> Result<Forgejo> {
    static URL: OnceLock<Url> = OnceLock::new();
    let url = URL
        .get_or_init(|| Url::parse(forge_http_base()).expect("forge_http_base() is a valid URL"))
        .clone();
    Forgejo::new(Auth::Token(token), url).context("build forgejo api client")
}

/// Per-agent forge sync: grant read access to `core/meta`, and wire the
/// `meta` remote in its proposed repo. All operations are idempotent;
/// failures are logged as warnings but don't abort the caller.
///
/// `core_token` is `core_token()` — passed in so callers that already
/// fetched it don't re-read the file. Pass `None` to skip the
/// `meta_read_access` step (safe: the access grant is best-effort).
///
/// Called by both `ensure_all()` (startup sweep) and `rebuild_agent`
/// (per-rebuild) so the two paths stay equivalent.
/// Returns `true` if all steps succeeded, `false` if any step failed. The
/// caller can use the return value to aggregate per-agent failures into a
/// dashboard warning (see [`ensure_all`]); the rebuild path ignores it and
/// relies on the journal `warn!` lines alone (a rebuild is its own retry).
pub async fn sync_agent(name: &str, core_token: Option<&str>) -> bool {
    // The agent's forge account, token and `agent-configs/<name>` repo are
    // swarm-controller's; this hive creates none of them and pushes nothing
    // to the repo.
    let mut ok = true;
    // Grant read-only access to core/meta and wire the `meta` remote
    // into the proposed repo so agents can fetch their deployment context.
    if let Some(token) = core_token
        && let Err(e) = meta_read_access(name, token).await
    {
        tracing::warn!(%name, error = ?e, "forge: ensure_meta_read_access failed");
        ok = false;
    }
    if let Err(e) = ensure_meta_remote(name).await {
        tracing::warn!(%name, error = ?e, "forge: ensure_meta_remote failed");
        ok = false;
    }
    ok
}

/// The `core_token.is_some()` half of [`ensure_all`]: the meta repo, the
/// core avatar, and removing this hive's own config-PR hook —
/// every step that needs an authenticated forge client. The swarm-wide
/// objects (orgs, the `operators` team, mirrors, `internal/docs`,
/// `internal/knowledge`, the `agent-configs` avatar) are the
/// swarm-controller's, not this hive's. Split out purely to keep
/// `ensure_all` under clippy's function-length limit; not meant to be called
/// from anywhere else.
async fn ensure_all_orgs_and_repos(token: &str) {
    // Meta repo lives at core/meta — pushed from git_commit in
    // meta.rs on every deploy/lock-update. Make sure it exists
    // before the first push hits a 404.
    if let Err(e) = ensure_repo("meta", token).await {
        tracing::warn!(error = ?e, "forge: ensure_repo core/meta failed");
        crate::warnings::set_boot_warning(
            "forge_ensure_meta_repo",
            "crit",
            format!("forge: core/meta repo provisioning failed: {e}"),
        );
    }
    if let Err(e) = ensure_core_avatar(token).await {
        tracing::warn!(error = ?e, "forge: ensure_core_avatar failed");
        crate::warnings::set_boot_warning(
            "forge_ensure_core_avatar",
            "warn",
            format!("forge: core avatar upload failed: {e}"),
        );
    }
    if let Err(e) = remove_config_pr_webhook(token).await {
        tracing::warn!(error = ?e, "forge: remove_config_pr_webhook failed");
    }
}

/// Delete this hive's own `/webhook/config-pr` hook from the
/// `agent-configs` org. No hive serves that route, so such a hook fails on
/// every config-repo event; swarm-controller's hook is the one that acts on
/// config PRs.
///
/// Only a hook whose URL equals this hive's exactly is removed, never one
/// matching by path: the same path on another base is another hive's hook.
/// Idempotent, and a no-op when `HYPERHIVE_HIVE_DOMAIN` is unset.
async fn remove_config_pr_webhook(core_token: &str) -> Result<()> {
    const HTTP_TIMEOUT: Duration = Duration::from_secs(10);

    let Some(domain) = std::env::var("HYPERHIVE_HIVE_DOMAIN")
        .ok()
        .filter(|v| !v.is_empty())
    else {
        return Ok(());
    };
    let own_url = config_pr_hook_url(&domain);
    let client = api(core_token)?;
    let hooks = tokio::time::timeout(HTTP_TIMEOUT, client.org_list_hooks(CONFIG_ORG).send())
        .await
        .map_err(anyhow::Error::from)
        .and_then(|r| r.map_err(anyhow::Error::from))
        .with_context(|| format!("list webhooks for org {CONFIG_ORG}"))?;
    for id in hook_ids_at(&hooks, &own_url) {
        tokio::time::timeout(HTTP_TIMEOUT, client.org_delete_hook(CONFIG_ORG, id).send())
            .await
            .map_err(anyhow::Error::from)
            .and_then(|r| r.map_err(anyhow::Error::from))
            .with_context(|| format!("delete webhook {id} on org {CONFIG_ORG}"))?;
        tracing::info!(%own_url, id, "forge: removed this hive's config-pr webhook");
    }
    Ok(())
}

/// The URL this hive's config-PR hook was registered under.
fn config_pr_hook_url(hive_domain: &str) -> String {
    format!("https://{hive_domain}/webhook/config-pr")
}

/// Ids of the hooks whose URL is exactly `url`.
fn hook_ids_at(hooks: &[forgejo_api::structs::Hook], url: &str) -> Vec<i64> {
    hooks
        .iter()
        .filter(|h| {
            h.config
                .as_ref()
                .and_then(|c| c.get("url"))
                .is_some_and(|u| u == url)
        })
        .filter_map(|h| h.id)
        .collect()
}

/// Poll the local Forgejo API until it answers, with a timeout of 1 minute.
/// The whole boot provisioning below hits the API, and [`is_present`] only
/// confirms the container exists — not that Forgejo is *listening*. A
/// `nixos-rebuild` that restarts hive-forge and hive-c0re together races:
/// without this gate every `ensure_*` fires at a refused socket and leaves a
/// stale "provisioning failed" banner that never clears (the pass is one-shot).
/// Returns whether the endpoint became ready before the deadline; on timeout
/// the caller proceeds anyway so a genuinely-down forge still surfaces its real
/// errors. Uses the unauthenticated `get_version` endpoint (no token yet).
async fn wait_until_ready() -> bool {
    const READY_TIMEOUT: Duration = Duration::from_mins(1);
    const POLL_INTERVAL: Duration = Duration::from_millis(500);
    let Ok(url) = Url::parse(forge_http_base()) else {
        tracing::warn!("forge: HIVE_FORGE_URL is not a valid URL; skipping readiness wait");
        return false;
    };
    let Ok(client) = Forgejo::new(Auth::None, url) else {
        tracing::warn!("forge: could not build readiness client; skipping readiness wait");
        return false;
    };
    let deadline = Instant::now() + READY_TIMEOUT;
    let mut waited = false;
    loop {
        if client.get_version().await.is_ok() {
            if waited {
                tracing::info!("forge: endpoint ready, proceeding with provisioning");
            }
            return true;
        }
        if Instant::now() >= deadline {
            tracing::warn!(
                "forge: endpoint not ready after {READY_TIMEOUT:?}; provisioning anyway"
            );
            return false;
        }
        waited = true;
        tokio::time::sleep(POLL_INTERVAL).await;
    }
}

/// Sweep the forge at startup: seed the `core` admin user (hive-c0re's own
/// identity for pushing the meta repo + driving the API) and its token, the
/// `core/meta` repo and the local knowledge clone, then run [`sync_agent`]
/// over every existing container (manager + sub-agents). Agent accounts,
/// tokens and `agent-configs/<name>` repos are the swarm-controller's, as is
/// the `agent-configs` org; this sweep pushes nothing to them.
/// Called once at hive-c0re startup. Per-step failures are logged
/// but don't abort the sweep.
pub async fn ensure_all() {
    if !is_present().await {
        tracing::debug!("forge: hive-forge container absent, skipping user sweep");
        return;
    }
    // The container exists, but its HTTP may not be up yet (a rebuild restarts
    // hive-forge + hive-c0re together). Wait for the API to answer before the
    // provisioning pass so a boot race doesn't leave stale failure banners.
    wait_until_ready().await;
    let core_token = match ensure_core_user_and_token().await {
        Ok(t) => Some(t),
        Err(e) => {
            tracing::warn!(error = ?e, "forge: ensure_core_user_and_token failed");
            crate::warnings::set_boot_warning(
                "forge_ensure_core_user",
                "crit",
                format!("forge: core user/token provisioning failed: {e}"),
            );
            None
        }
    };
    if let Some(token) = core_token.as_deref() {
        ensure_all_orgs_and_repos(token).await;
    }
    let Ok(containers) = crate::lifecycle::list().await else {
        tracing::warn!("forge: nixos-container list failed; skipping user sweep");
        crate::warnings::set_boot_warning(
            "forge_container_list",
            "crit",
            "forge: nixos-container list failed; per-agent forge sync skipped this boot",
        );
        return;
    };
    let mut sync_failed: Vec<String> = Vec::new();
    for c in containers {
        let Some(name) = c.strip_prefix(crate::lifecycle::AGENT_PREFIX) else {
            continue;
        };
        if !sync_agent(name, core_token.as_deref()).await {
            sync_failed.push(name.to_owned());
        }
    }
    if !sync_failed.is_empty() {
        // Use static_kind to mint a `&'static str` key from the failed-agent
        // list (bounded leak: one per hive-c0re boot, not per request).
        let key = static_kind(format!("forge_sync_agent_{}", sync_failed.join("_")));
        crate::warnings::set_boot_warning(
            key,
            "warn",
            format!(
                "forge: per-agent sync failed for: {} (see journal for per-step detail)",
                sync_failed.join(", ")
            ),
        );
    }
}

#[cfg(test)]
mod tests {
    use super::{config_pr_hook_url, describe_forge_admin, git_url_with_base, hook_ids_at};

    fn hook(id: i64, url: &str) -> forgejo_api::structs::Hook {
        serde_json::from_value(serde_json::json!({ "id": id, "config": { "url": url } }))
            .expect("hook json")
    }

    /// The same path on another base is another hive's hook, and removing it
    /// would cut that hive off. Only an exact URL match is this hive's.
    #[test]
    fn only_this_hives_own_config_pr_hook_is_removed() {
        let own = config_pr_hook_url("hive.example");
        let hooks = [
            hook(1, &own),
            hook(2, "https://other-hive.example/webhook/config-pr"),
            hook(3, "http://127.0.0.1:7000/webhook/config-pr"),
            hook(4, "https://swarm.example/webhook/forge/config-pr"),
        ];
        assert_eq!(hook_ids_at(&hooks, &own), vec![1]);
        assert!(hook_ids_at(&hooks[1..], &own).is_empty());
    }

    /// The remote carries **no credential**. `argv` is world-readable through
    /// `/proc/<pid>/cmdline`, so a token spliced in here would be published to
    /// every local user for the life of the git child.
    ///
    /// Deliberately not via `forge_git_url`, which reads `HIVE_FORGE_URL` —
    /// setting that here would race every other test in this binary.
    #[test]
    fn forge_git_url_carries_no_credential() {
        let url = git_url_with_base("http://forge.example.test", "a/iris");
        assert_eq!(url, "http://forge.example.test/a/iris.git");
        assert!(!url.contains('@'), "no userinfo: {url}");
    }

    #[test]
    fn forge_git_url_preserves_https() {
        // The scheme is carried through rather than assumed: a swarm
        // whose forge is behind TLS must not be downgraded to http.
        let url = git_url_with_base("https://forge.example.test", "a/iris");
        assert!(url.starts_with("https://"), "https must survive: {url}");
    }

    /// The credential goes in an `Authorization` header instead — decodable
    /// back to `core:<token>`, so the swap is genuinely equivalent auth and
    /// not a silent downgrade to anonymous.
    #[test]
    fn core_auth_header_is_basic_core_token() {
        use base64::Engine as _;
        let header = super::core_auth_header("s3cret");
        let b64 = header
            .strip_prefix("Authorization: Basic ")
            .expect("basic auth header");
        let decoded = base64::engine::general_purpose::STANDARD
            .decode(b64)
            .expect("valid base64");
        assert_eq!(String::from_utf8_lossy(&decoded), "core:s3cret");
        assert!(
            !header.contains("s3cret"),
            "token not in the clear: {header}"
        );
    }

    #[test]
    fn describe_keeps_the_verb_path_and_drops_every_value() {
        assert_eq!(
            describe_forge_admin(&[
                "user",
                "create",
                "--username",
                "iris",
                "--email",
                "iris@hyperhive.local",
                "--random-password",
            ]),
            "forgejo admin user create"
        );
    }

    #[test]
    fn describe_does_not_reproduce_a_password_argument() {
        let described = describe_forge_admin(&[
            "user",
            "change-password",
            "--username",
            "iris",
            "--password",
            "correct-horse-battery-staple",
        ]);
        assert_eq!(described, "forgejo admin user change-password");
        assert!(!described.contains("correct-horse-battery-staple"));
    }

    #[test]
    fn describe_survives_a_leading_flag_and_an_empty_vector() {
        assert_eq!(describe_forge_admin(&["--help"]), "forgejo admin");
        assert_eq!(describe_forge_admin(&[]), "forgejo admin");
    }
}