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

//! Per-agent Forgejo user + access-token provisioning, account
//! policy (email alignment, repo-creation lockdown), avatar uploads,
//! and the bootstrap `core` admin user + token lifecycle. The typed
//! API-client constructor + `forgejo admin` helpers live in the
//! module root (`super`).

use std::path::Path;

use anyhow::{Context, Result};
use base64::Engine;
use forgejo_api::structs::{EditUserOption, UpdateUserAvatarOption};
use forgejo_api::{ApiErrorKind, ForgejoError};
use reqwest::StatusCode;

use super::{api, forge_admin};

const TOKEN_NAME_PREFIX: &str = "hyperhive";
// Where the host-side `core` admin token lives. Used by hive-c0re itself
// to push the meta repo + drive admin API calls. Root-only. Literal lives
// in `crate::paths`; aliased here under the long-standing name.
use crate::paths::FORGE_CORE_TOKEN as CORE_TOKEN_PATH;
// Forge provisioning markers (`forge/core-avatar-set`,
// `forge/email-aligned-<name>`) live in `crate::paths` — one-shot guards:
// the upload/align runs once, the marker is written, subsequent startups
// skip. Delete one to force its step to re-run.
// The avatar PNG path is resolved by `core_avatar_png_path` below —
// only-used-here, so it lives in this module rather than the shared
// `hive_sh4re::assets` helpers (which now hold only `prompt_template`, the
// one asset path every crate needs — the agent icon, the last other one, moved off the
// shared-asset model entirely; see `hive-agent::web_ui::screen`).

/// `$HIVE_ASSETS_DIR/branding/hyperhive.png` — the core mark,
/// rasterised. Not independently configurable — override the whole
/// `services.hyperhive.c0re.assets` package to change it.
fn core_avatar_png_path() -> std::path::PathBuf {
    let dir = std::env::var("HIVE_ASSETS_DIR").expect(
        "HIVE_ASSETS_DIR is unset — the hyperhive NixOS module sets it from \
         services.hyperhive.c0re.assets on the hive-c0re unit, so this \
         process was started outside that unit",
    );
    std::path::PathBuf::from(dir).join("branding/hyperhive.png")
}

/// Bootstrap `core` token scopes — adds `read:admin,write:admin` on
/// top of the agent scopes (swarm-controller's `AGENT_TOKEN_SCOPES`)
/// so the host daemon can drive `/api/v1/admin/*`. Site-admin
/// membership alone isn't enough: the token's own scope gate runs
/// before the user-permission check.
/// See `docs/integrations/forge.md::Token scopes`.
const CORE_TOKEN_SCOPES: &str = "read:admin,write:admin,read:user,write:user,read:notification,write:notification,write:repository,write:issue,write:organization,write:misc";

/// Pull the access token out of forgejo's success message. Format
/// has shifted across versions (table form vs. "Access token was
/// successfully created: `<hex>`"), so just hunt the output for the
/// first long hex-looking word.
fn extract_token(output: &str) -> Option<String> {
    output
        .split(|c: char| c.is_whitespace() || c == ',' || c == ':')
        .find(|w| w.len() >= 32 && w.chars().all(|c| c.is_ascii_hexdigit()))
        .map(str::to_owned)
}

/// Canonical email address for a hive agent's Forgejo account.
/// Must match the `user.email` set by `meta::render_flake` so commits
/// by the agent link back to their Forgejo profile page.
fn agent_email(name: &str) -> String {
    format!("{name}@hyperhive.local")
}

/// `EditUserOption` with every field unset except the ones Forgejo's
/// validator effectively requires: `login_name` and `source_id = 0`
/// (local auth, the default for users hive-c0re creates). Omitting
/// `login_name` made Forgejo reset `use_custom_avatar` on every admin
/// edit — the same reason the old raw JSON bodies always carried both
/// fields. Callers set only the field(s) they mean to change on top.
fn sparse_edit_user_option(name: &str) -> EditUserOption {
    EditUserOption {
        active: None,
        admin: None,
        allow_create_organization: None,
        allow_git_hook: None,
        allow_import_local: None,
        description: None,
        email: None,
        full_name: None,
        hide_email: None,
        location: None,
        login_name: Some(name.to_owned()),
        max_repo_creation: None,
        must_change_password: None,
        password: None,
        prohibit_login: None,
        pronouns: None,
        restricted: None,
        source_id: Some(0),
        visibility: None,
        website: None,
    }
}

/// Whether a Forgejo API error is a definitive 403. The typed client
/// maps a 403 response to `ApiErrorKind::Forbidden` when the endpoint
/// spec lists it, or to `UnexpectedStatusCode(403)` otherwise — check
/// both defensively.
fn is_forbidden(e: &ForgejoError) -> bool {
    match e {
        ForgejoError::ApiError(api) => matches!(api.error_kind(), ApiErrorKind::Forbidden),
        ForgejoError::UnexpectedStatusCode(s) => *s == StatusCode::FORBIDDEN,
        _ => false,
    }
}

/// Ensure a forgejo user named `name` exists. Idempotent: forgejo
/// returns a "user already exists" error which we treat as success.
/// `admin` adds `--admin` (site admin) — used for the bootstrap
/// `core` user that drives the API. The password is random and never
/// read: the account authenticates by token.
async fn ensure_user_exists(name: &str, admin: bool) -> Result<()> {
    let email = agent_email(name);
    let mut args = vec![
        "user",
        "create",
        "--username",
        name,
        "--email",
        &email,
        "--random-password",
        "--must-change-password=false",
    ];
    if admin {
        args.push("--admin");
    }
    let result = forge_admin(&args).await;
    match result {
        Ok(_) => {
            tracing::info!(%name, "forge: created user");
            Ok(())
        }
        Err(e) => {
            // Forgejo's "already exists" error wording varies; just
            // try the next step and let token issuance surface a
            // real failure if the user truly isn't there.
            let msg = format!("{e:#}");
            if msg.contains("already exists") || msg.contains("user already") {
                tracing::debug!(%name, "forge: user already exists");
                Ok(())
            } else {
                tracing::warn!(%name, error = %msg, "forge: user create unclear; trying token anyway");
                Ok(())
            }
        }
    }
}

/// Idempotently align the Forgejo account email to `agent_email(name)`.
/// Existing agents were created with `{name}@hive.local`; this corrects
/// that so git commits (which use `{name}@hyperhive`) link to profiles.
/// Best-effort: failures are warned, not propagated.
///
/// Marker-guarded: writes `EMAIL_ALIGNED_MARKER_PREFIX{name}` on first
/// success and skips the PATCH on all subsequent calls. This prevents
/// Forgejo's admin-user-edit endpoint from resetting `use_custom_avatar`
/// on every `sync_agent` tick. Delete the marker to force re-alignment.
///
/// Uses the admin REST API (`admin_edit_user`, i.e. `PATCH
/// /api/v1/admin/users/{name}`) rather than `forgejo admin user edit`
/// because the CLI dropped the `edit` subcommand somewhere between
/// forgejo 8 and current. The edit body carries `login_name` +
/// `source_id = 0` via [`sparse_edit_user_option`].
pub(super) async fn ensure_user_email(name: &str) {
    let marker = crate::paths::forge_email_aligned_marker(name);
    if marker.exists() {
        return;
    }
    let Some(token) = core_token() else {
        tracing::debug!(%name, "forge: skipping ensure_user_email — no core token yet");
        return;
    };
    let email = agent_email(name);
    let mut edit = sparse_edit_user_option(name);
    edit.email = Some(email.clone());
    let client = match api(&token) {
        Ok(c) => c,
        Err(e) => {
            tracing::warn!(%name, error = %e, "forge: PATCH user email: client build failed");
            return;
        }
    };
    match client.admin_edit_user(name, edit).await {
        Ok(_) => {
            if let Some(parent) = marker.parent() {
                std::fs::create_dir_all(parent).ok();
            }
            std::fs::write(&marker, "").ok();
            tracing::info!(%name, %email, "forge: user email aligned");
        }
        Err(e) if is_forbidden(&e) => {
            // Core token missing admin scope — see
            // `docs/integrations/forge.md::Token scopes` migration note.
            tracing::warn!(
                %name, %email, error = %e,
                "forge: PATCH user email forbidden — core token likely missing admin scope. \
                 Delete {CORE_TOKEN_PATH} and restart hive-c0re to re-mint with the new scopes."
            );
        }
        Err(e) => tracing::warn!(%name, %email, error = %e, "forge: PATCH user email failed"),
    }
}

/// Disable direct repo creation for agent `name` by setting
/// `max_repo_creation = 0` on its Forgejo account. Agents must
/// create repos *through hive-c0re* (which owns the perms), never with
/// their own token — a write-scoped token can otherwise create + own
/// repos and self-merge, bypassing the operator-only-merge policy.
///
/// `max_repo_creation = 0` means `CanCreateRepo()` is false for any
/// count (Forgejo: `MaxRepoCreation >= 0 && NumRepos >= MaxRepoCreation`),
/// so creation is refused while push / PR / clone stay intact. **Existing
/// repos are untouched** — this only blocks *new* direct creation.
///
/// Marker-guarded like [`ensure_user_email`]: the edit runs once per
/// agent (delete the marker to re-apply). The edit body carries
/// `login_name` + `source_id` for the same reason `ensure_user_email`
/// does — omitting `login_name` makes Forgejo's `EditUserOption`
/// validator reset `use_custom_avatar`. Best-effort: failures warn,
/// don't propagate.
pub(super) async fn ensure_repo_creation_disabled(name: &str) {
    let marker = crate::paths::forge_repo_creation_disabled_marker(name);
    if marker.exists() {
        return;
    }
    let Some(token) = core_token() else {
        tracing::debug!(%name, "forge: skipping ensure_repo_creation_disabled — no core token yet");
        return;
    };
    let mut edit = sparse_edit_user_option(name);
    edit.max_repo_creation = Some(0);
    let client = match api(&token) {
        Ok(c) => c,
        Err(e) => {
            tracing::warn!(%name, error = %e, "forge: PATCH max_repo_creation: client build failed");
            return;
        }
    };
    match client.admin_edit_user(name, edit).await {
        Ok(_) => {
            if let Some(parent) = marker.parent() {
                std::fs::create_dir_all(parent).ok();
            }
            std::fs::write(&marker, "").ok();
            tracing::info!(%name, "forge: disabled direct repo creation (max_repo_creation=0)");
        }
        Err(e) if is_forbidden(&e) => {
            tracing::warn!(
                %name, error = %e,
                "forge: PATCH max_repo_creation forbidden — core token likely missing admin scope. \
                 Delete {CORE_TOKEN_PATH} and restart hive-c0re to re-mint with the new scopes."
            );
        }
        Err(e) => {
            tracing::warn!(%name, error = %e, "forge: PATCH max_repo_creation failed");
        }
    }
}

/// Mint a fresh access token for `name`. Token name is suffixed with
/// a monotonic clock so re-issuing doesn't collide with an existing
/// token of the same name in the DB. `scopes` is the scope string
/// passed to `forgejo admin user generate-access-token --scopes`;
/// the bootstrap `core` user, its one caller, passes `CORE_TOKEN_SCOPES`.
async fn mint_token(name: &str, scopes: &str) -> Result<String> {
    let token_name = format!(
        "{TOKEN_NAME_PREFIX}-{}",
        std::time::SystemTime::now()
            .duration_since(std::time::UNIX_EPOCH)
            .map_or(0, |d| d.as_secs())
    );
    let stdout = forge_admin(&[
        "user",
        "generate-access-token",
        "--username",
        name,
        "--token-name",
        &token_name,
        "--scopes",
        scopes,
    ])
    .await?;
    // Deliberately does NOT include `stdout`: on this path forgejo has
    // already minted a live token and printed it, and an error string
    // propagates into logs the same way any other message does. The
    // shape of the output is enough to diagnose a version drift.
    let token = extract_token(&stdout).with_context(|| {
        format!(
            "no token-shaped word (>= 32 hex chars) in forgejo output \
             ({} bytes, {} lines); output withheld, it carries the token",
            stdout.len(),
            stdout.lines().count()
        )
    })?;
    tracing::debug!(%name, %token_name, "forge: minted access token");
    Ok(token)
}

/// Mint a fresh Forgejo access token for the `core` admin user and
/// write it directly to `path`. Unlike agent tokens this path is owned
/// by hive-c0re itself (under `/var/lib/hyperhive/`), so a direct
/// write is both correct and necessary (no priv round-trip).
async fn mint_and_persist_core_token(path: &Path) -> Result<()> {
    use std::os::unix::fs::PermissionsExt;
    let token = mint_token("core", CORE_TOKEN_SCOPES).await?;
    if let Some(parent) = path.parent() {
        std::fs::create_dir_all(parent).ok();
    }
    std::fs::write(path, format!("{token}\n"))
        .with_context(|| format!("write core token to {}", path.display()))?;
    let _ = std::fs::set_permissions(path, std::fs::Permissions::from_mode(0o600));
    tracing::info!(path = %path.display(), "forge: persisted core access token");
    Ok(())
}

/// Set `core`'s Forgejo avatar to the hyperhive logo once, then
/// remember it so subsequent startups don't re-upload. Best-effort
/// — any non-2xx is logged at the caller; the project runs fine
/// with the default hash identicon.
pub(super) async fn ensure_core_avatar(token: &str) -> Result<()> {
    let marker = crate::paths::forge_core_avatar_marker();
    if marker.exists() {
        return Ok(());
    }
    let png_path = core_avatar_png_path();
    let png_bytes = tokio::fs::read(&png_path)
        .await
        .with_context(|| format!("read core avatar PNG from {}", png_path.display()))?;
    // The raw-HTTP predecessor POSTed the admin endpoint
    // `/admin/users/core/avatar`, which forgejo-api has no method for.
    // `token` IS the core user's own token though, so updating "the
    // current user's avatar" (`POST /user/avatar`) is behaviorally
    // identical.
    api(token)?
        .user_update_avatar(UpdateUserAvatarOption {
            image: Some(base64::engine::general_purpose::STANDARD.encode(&png_bytes)),
        })
        .await
        .context("set core avatar")?;
    if let Some(parent) = marker.parent() {
        std::fs::create_dir_all(parent).ok();
    }
    std::fs::write(marker, "").ok();
    tracing::info!("forge: set core user avatar to hyperhive logo");
    Ok(())
}

/// Outcome of probing whether the persisted core token still works
/// against the *current* forge. Existence on disk is not validity: a
/// token minted before a forge rebuild / re-provision is unknown to the
/// new forge's DB and 401s on every call — which silently breaks the
/// hive-ci runner-registration prefetch (it reads this same token to
/// fetch a runner registration token).
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
enum CoreTokenCheck {
    /// Token authenticated successfully — keep using it.
    Valid,
    /// Forge explicitly rejected the token (401/403) — re-mint.
    Invalid,
    /// Couldn't determine (forge unreachable / 5xx). Don't re-mint on a
    /// transient: keep the existing token and let a later ensure pass
    /// re-check once the forge is responsive. Re-minting here would both
    /// fail (mint needs the forge too) and churn tokens needlessly.
    Indeterminate,
}

/// Map a failed token-probe call to a [`CoreTokenCheck`]. Only a
/// definitive auth rejection (401/403 — surfaced by the typed client
/// as `Unauthorized`/`Forbidden` API errors, or defensively as bare
/// `UnexpectedStatusCode`s) is `Invalid`; anything else (transport,
/// 5xx, unexpected shapes) is `Indeterminate`. Pure so the decision
/// logic is unit-testable without a live forge.
fn classify_core_token_error(e: &ForgejoError) -> CoreTokenCheck {
    match e {
        ForgejoError::ApiError(api) => match api.error_kind() {
            ApiErrorKind::Unauthorized | ApiErrorKind::Forbidden => CoreTokenCheck::Invalid,
            _ => CoreTokenCheck::Indeterminate,
        },
        ForgejoError::UnexpectedStatusCode(s)
            if *s == StatusCode::UNAUTHORIZED || *s == StatusCode::FORBIDDEN =>
        {
            CoreTokenCheck::Invalid
        }
        _ => CoreTokenCheck::Indeterminate,
    }
}

/// Probe whether `token` is still accepted by the current forge with a
/// cheap authenticated `user_get_current` (`GET /api/v1/user`, covered
/// by the core token's `read:user` scope). See [`CoreTokenCheck`] for
/// how the outcome is interpreted.
async fn check_core_token(token: &str) -> CoreTokenCheck {
    let Ok(client) = api(token) else {
        return CoreTokenCheck::Indeterminate;
    };
    match client.user_get_current().await {
        Ok(_) => CoreTokenCheck::Valid,
        Err(e) => {
            let outcome = classify_core_token_error(&e);
            if outcome == CoreTokenCheck::Indeterminate {
                tracing::debug!(
                    error = %e,
                    "forge: core-token probe inconclusive (unreachable / unexpected response); \
                     treating as indeterminate"
                );
            }
            outcome
        }
    }
}

/// Ensure the bootstrap `core` admin user + a token at
/// `CORE_TOKEN_PATH`. The token is what hive-c0re uses for forgejo
/// API calls (org creation, meta-repo push, and the hive-ci
/// runner-registration prefetch). Returns the token.
///
/// Idempotent, but validity-aware: when a token file is already present
/// it is **probed against the current forge** before being trusted. A
/// token persisted before a forge rebuild / re-provision is stale (the
/// new forge DB doesn't know it) and would 401 every caller — so on a
/// definitive rejection the token is re-minted. A merely-unreachable
/// forge leaves the existing token in place (a later ensure pass
/// re-checks) rather than churning tokens on a transient.
pub(super) async fn ensure_core_user_and_token() -> Result<String> {
    let path = std::path::Path::new(CORE_TOKEN_PATH);
    if let Ok(existing) = std::fs::read_to_string(path) {
        let trimmed = existing.trim().to_owned();
        if !trimmed.is_empty() {
            match check_core_token(&trimmed).await {
                CoreTokenCheck::Valid | CoreTokenCheck::Indeterminate => return Ok(trimmed),
                CoreTokenCheck::Invalid => {
                    tracing::warn!(
                        path = %path.display(),
                        "forge: persisted core token rejected by forge (stale after rebuild?); \
                         re-minting"
                    );
                }
            }
        }
    }
    ensure_user_exists("core", true).await?;
    mint_and_persist_core_token(path).await?;
    let raw = std::fs::read_to_string(path)
        .with_context(|| format!("read {CORE_TOKEN_PATH} after mint"))?;
    Ok(raw.trim().to_owned())
}

/// Read the persisted core token, or None when the forge isn't
/// seeded yet. Cheap — just a file read.
pub fn core_token() -> Option<String> {
    std::fs::read_to_string(CORE_TOKEN_PATH)
        .ok()
        .map(|s| s.trim().to_owned())
        .filter(|s| !s.is_empty())
}

#[cfg(test)]
mod tests {
    use super::{CoreTokenCheck, classify_core_token_error, is_forbidden};
    use forgejo_api::{ApiError, ApiErrorKind, ForgejoError};
    use reqwest::StatusCode;

    fn api_err(kind: ApiErrorKind) -> ForgejoError {
        ForgejoError::ApiError(ApiError {
            message: None,
            kind,
        })
    }

    #[test]
    fn auth_rejection_errors_are_invalid() {
        // The whole point: a stale token (forge rebuilt out from under it)
        // 401s, and 401/403 are the only outcomes that trigger a re-mint.
        assert_eq!(
            classify_core_token_error(&api_err(ApiErrorKind::Unauthorized)),
            CoreTokenCheck::Invalid
        );
        assert_eq!(
            classify_core_token_error(&api_err(ApiErrorKind::Forbidden)),
            CoreTokenCheck::Invalid
        );
        // Defensive: the same statuses arriving as bare status codes
        // (endpoint spec didn't list them) must classify identically.
        for s in [StatusCode::UNAUTHORIZED, StatusCode::FORBIDDEN] {
            assert_eq!(
                classify_core_token_error(&ForgejoError::UnexpectedStatusCode(s)),
                CoreTokenCheck::Invalid,
                "status {s} should be invalid"
            );
        }
    }

    #[test]
    fn transient_and_unexpected_errors_are_indeterminate() {
        // Never re-mint on a transient — minting needs the forge too, and
        // churning tokens on a blip is worse than keeping the existing one.
        for s in [
            StatusCode::INTERNAL_SERVER_ERROR,
            StatusCode::BAD_GATEWAY,
            StatusCode::SERVICE_UNAVAILABLE,
            StatusCode::GATEWAY_TIMEOUT,
            StatusCode::NOT_FOUND,
        ] {
            assert_eq!(
                classify_core_token_error(&ForgejoError::UnexpectedStatusCode(s)),
                CoreTokenCheck::Indeterminate,
                "status {s} should be indeterminate"
            );
        }
        assert_eq!(
            classify_core_token_error(&api_err(ApiErrorKind::NotFound { errors: None })),
            CoreTokenCheck::Indeterminate
        );
        assert_eq!(
            classify_core_token_error(&api_err(ApiErrorKind::Generic)),
            CoreTokenCheck::Indeterminate
        );
    }

    /// The typed client only produces `ApiErrorKind::Forbidden` when the
    /// endpoint's spec lists 403; every other endpoint surfaces the same
    /// response as a bare `UnexpectedStatusCode`. Both shapes must be
    /// recognised, because the arms guarded by this predicate are what tell
    /// the operator that `ensure_repo_creation_disabled` — the lockdown
    /// stopping an agent from creating and self-merging in its own repo —
    /// did not apply, and which credential to re-mint to make it apply.
    /// Drop the second arm as "redundant" and that lockdown fails with a
    /// generic warning that names no remedy.
    #[test]
    fn a_403_is_recognised_in_both_shapes_the_client_can_produce() {
        assert!(is_forbidden(&api_err(ApiErrorKind::Forbidden)));
        assert!(is_forbidden(&ForgejoError::UnexpectedStatusCode(
            StatusCode::FORBIDDEN
        )));
    }

    /// The other direction, and the more expensive one to get wrong: this
    /// predicate gates advice to **delete the core token and restart
    /// hive-c0re**. A widened match would hand that advice out for a 502
    /// from a restarting forge or a client-side error that never reached
    /// the network — destroying a working credential in response to a blip.
    /// 401 is called out separately because it is the near miss: it *is* a
    /// credential problem, but its remedy is [`classify_core_token_error`]'s
    /// automatic re-mint, so classifying it as forbidden buries the cause
    /// under a scope warning that does not apply.
    #[test]
    fn a_non_403_failure_is_not_reported_as_a_missing_admin_scope() {
        for kind in [
            ApiErrorKind::Unauthorized,
            ApiErrorKind::NotFound { errors: None },
            ApiErrorKind::ValidationFailed,
            ApiErrorKind::Generic,
        ] {
            let e = api_err(kind);
            assert!(!is_forbidden(&e), "{e} must not read as forbidden");
        }
        for s in [
            StatusCode::UNAUTHORIZED,
            StatusCode::NOT_FOUND,
            StatusCode::BAD_GATEWAY,
            StatusCode::INTERNAL_SERVER_ERROR,
        ] {
            assert!(
                !is_forbidden(&ForgejoError::UnexpectedStatusCode(s)),
                "status {s} must not read as forbidden"
            );
        }
        // A failure with no HTTP status at all — the request never got an
        // answer, so nothing has been said about the token's scopes.
        assert!(!is_forbidden(&ForgejoError::KeyNotAscii));
        assert!(!is_forbidden(&ForgejoError::HostRequired));
    }
}