hyperhive/hive-c0re/src/actions.rs

//! Operations that are exposed through more than one surface (the host admin
//! socket *and* the dashboard's POST endpoints). Each function takes a
//! `&Coordinator` and the request parameters; callers stitch the response
//! shape they want (HTTP redirect vs JSON).

use std::sync::Arc;

use anyhow::{Context as _, Result, bail};
use hive_sh4re::{ApprovalKind, ApprovalStatus, HelperEvent};

use crate::coordinator::Coordinator;
use crate::lifecycle;

/// Approve a pending request. Marks the approval row durably, then
/// either runs the work inline (`InitConfig`, sub-second git ops) or
/// submits it to the job queue so the dashboard POST returns
/// immediately while the long-running pipeline runs off-thread
/// (operator no longer blocks on a 30-90s spinner for `MergeConfigPr`).
///
/// Dispatch:
/// - `MergeConfigPr` → a `DeployWindow` DAG (`MergeVerify → DeployApply →
///   FinalizeDeploy`, plus an `AfterAny` `DeployTail`, under a
///   resource-holding root; ~30-90s)
/// - `UpdateMetaInputs` → a `MetaUpdate` DAG (fan-out on completion)
/// - `Spawn`       → a `Spawn` DAG (`Create → WriteDropin → Reconcile`)
/// - `InitConfig`  → inline (<1s; queue card would be noise)
///
/// Every queued kind — deploys included — resolves its approval row via
/// [`resolve_approval_dag`] when the DAG settles terminal.
pub async fn approve(coord: Arc<Coordinator>, id: i64) -> Result<()> {
    let approval = coord.approvals.mark_approved(id)?;
    tracing::info!(
        %approval.id,
        %approval.agent,
        kind = ?approval.kind,
        %approval.commit_ref,
        "approval: dispatching",
    );
    match approval.kind {
        ApprovalKind::InitConfig => {
            // Sub-second git seed + forge-remote wire. Routing through
            // the queue would surface a queue card that's gone before
            // the operator's eyes refocus. Run inline.
            let proposed_dir = Coordinator::agent_proposed_dir(&approval.agent);
            let claude_dir = Coordinator::agent_claude_dir(&approval.agent);
            let notes_dir = Coordinator::agent_notes_dir(&approval.agent);
            run_approval_init_config(&coord, approval, proposed_dir, claude_dir, notes_dir).await
        }
        ApprovalKind::UpdateMetaInputs => {
            // Inputs JSON-encoded into commit_ref by the manager's
            // submit path — surface them on the DAG so the dashboard
            // can show *which* inputs are about to bump. The cascade
            // rebuilds fan out when the lock bump lands (so they build
            // against the post-bump lock, and a failed bump fans out
            // nothing).
            let inputs: Vec<String> =
                serde_json::from_str(&approval.commit_ref).unwrap_or_default();
            let submitted = coord.job_queue.submit(
                crate::job_queue::Source::Approval,
                format!("approval #{id} meta input update"),
                |b| crate::job_queue::templates::meta_update(b, inputs, Some(id)),
            );
            if let Err(e) = submitted {
                return Err(e.context("submit meta-update dag"));
            }
            coord.emit_rebuild_queue_snapshot();
            Ok(())
        }
        ApprovalKind::Spawn => {
            // The spawn's tail `Reconcile` starts the container, so the
            // new agent's power intent is `Up` from the outset.
            if let Err(e) = coord
                .power
                .set(approval.agent.as_str(), crate::power::Wanted::Up)
            {
                tracing::warn!(agent = %approval.agent, error = ?e, "agent_power: seed on spawn failed");
            }
            let submitted = coord.job_queue.submit(
                crate::job_queue::Source::Approval,
                format!("approval #{id} spawn"),
                |b| crate::job_queue::templates::spawn(b, approval.agent.as_str(), id),
            );
            if let Err(e) = submitted {
                return Err(e.context("submit spawn dag"));
            }
            coord.emit_rebuild_queue_snapshot();
            Ok(())
        }
        ApprovalKind::SchedulePrompt => {
            // No queue card for SchedulePrompt — the work is a single
            // sqlite insert, the actual "running" lifetime lives on
            // the scheduled-prompts surface itself (worker fires it
            // at the scheduled time). Run inline + fire
            // `ApprovalResolved` so the approval row leaves Pending
            // immediately.
            let result = run_approval_schedule_prompt(&coord, approval).await;
            if result.is_ok() {
                coord.emit_schedules_snapshot();
            }
            result
        }
        ApprovalKind::MergeConfigPr => {
            // The work ends in a container rebuild, so route it through the
            // rebuild queue. The queue worker dispatches the deploy DAG's
            // nodes to `run_deploy_merge_verify` (drift gate + eval),
            // `run_deploy_apply` (ff-merge, then grows the rebuild subgraph),
            // `run_finalize_deploy` (deploy tag + lock commit) and
            // `run_deploy_tail` (compensation + forge mirror).
            enqueue_approval_rebuild(
                &coord,
                approval.agent.as_str(),
                id,
                format!("approval #{id} merge config pr"),
            );
            Ok(())
        }
    }
}

/// Submit the deploy DAG tied to an approval id. Used by the `MergeConfigPr`
/// dispatch arm — the work ends in a container rebuild routed through the
/// queue. See [`crate::job_queue::templates::approval_deploy`] for the node
/// shape; the executor dispatches each node to the `run_deploy_*` bodies below.
fn enqueue_approval_rebuild(
    coord: &Arc<Coordinator>,
    agent: &str,
    approval_id: i64,
    reason: String,
) {
    if let Err(e) = coord
        .job_queue
        .submit(crate::job_queue::Source::Approval, reason, |b| {
            crate::job_queue::templates::approval_deploy(b, agent, approval_id);
        })
    {
        tracing::error!(%agent, approval_id, error = ?e, "submit approval deploy dag failed");
    }
    coord.emit_rebuild_queue_snapshot();
}

/// Ref under which [`run_deploy_apply`] parks the pre-merge `applied/main`
/// sha, for [`run_deploy_tail`] to compensate with.
///
/// Deliberately a *git ref in the applied repo* rather than an in-memory value
/// handed between nodes: hive-c0re can restart between the apply and the tail,
/// and the whole point of splitting the deploy is that the tail still knows
/// what to undo when it does. The ref's existence IS the "a merge landed but
/// hasn't been confirmed good yet" flag — [`run_finalize_deploy`] drops it the
/// moment the rebuild has come up clean.
fn rollback_ref(approval_id: i64) -> String {
    format!("refs/hyperhive/rollback/{approval_id}")
}

/// Everything a deploy node needs, re-derived from sqlite on each node rather
/// than cached across the DAG. Nothing here is *computed* by an earlier node —
/// `pr` and `reviewed` are fields of the approval row the operator signed off
/// on — so re-reading is both cheap and the authoritative source of truth.
struct DeployCtx {
    approval: hive_sh4re::Approval,
    /// PR number, parsed from `approval.commit_ref`.
    pr: u64,
    /// The PR head sha the operator reviewed (`approval.fetched_sha`).
    reviewed: String,
    applied_dir: std::path::PathBuf,
    /// The agent's forge config repo (`<owner>/<name>`).
    repo: String,
}

fn deploy_ctx(coord: &Coordinator, approval_id: i64) -> Result<DeployCtx> {
    let approval = fetch_approval_for_worker(coord, approval_id, ApprovalKind::MergeConfigPr)?;
    let pr: u64 = approval.commit_ref.parse().map_err(|e| {
        anyhow::anyhow!(
            "parse PR number from commit_ref {:?}: {e}",
            approval.commit_ref
        )
    })?;
    let reviewed = approval.fetched_sha.clone().ok_or_else(|| {
        anyhow::anyhow!("merge config pr approval {approval_id} has no reviewed head sha")
    })?;
    Ok(DeployCtx {
        pr,
        reviewed,
        applied_dir: crate::paths::applied_dir(approval.agent.as_str()),
        repo: crate::forge::config_repo(approval.agent.as_str()),
        approval,
    })
}

/// `MergeVerify` node body — everything that can say "no" before anything is
/// mutated. `approval.commit_ref` is the PR number; `approval.fetched_sha` is
/// the PR head the operator reviewed. Steps:
/// 1. drift gate — re-read the live PR head; if it moved since review, abort
///    (the operator must re-review the new head);
/// 2. fetch the reviewed head into the applied repo so later git ops resolve
///    it locally;
/// 3. ancestry gate — the reviewed head must descend from `applied/main`;
/// 4. eval-verify the reviewed commit against the meta flake.
///
/// Steps 1 and 3 ask different questions and both are load-bearing. The drift
/// gate asks whether the *head* is still what was reviewed; the ancestry gate
/// asks whether the *base* is still underneath it. A PR opened from a stale base
/// passes the drift gate untouched and then rewinds `main` when it lands,
/// silently dropping every commit made in between.
///
/// Nothing here needs undoing on failure: the fetch only adds objects, and
/// `main` doesn't move. That's the whole reason this is its own node — a
/// failure at this stage leaves [`run_deploy_tail`] with no ref to compensate.
///
/// # Errors
///
/// Returns an error if the approval can't be loaded, if the live PR head has
/// drifted from the reviewed sha, if fetching that head into the applied repo
/// fails, if the reviewed head does not descend from `applied/main`, or if the
/// eval-verify of the reviewed commit fails. Every one of these leaves the forge
/// and `main` untouched, so the node is safely retryable.
pub async fn run_deploy_merge_verify(coord: &Arc<Coordinator>, approval_id: i64) -> Result<()> {
    let ctx = deploy_ctx(coord, approval_id)?;
    let pr = ctx.pr;
    let reviewed = ctx.reviewed.as_str();

    // 1. Drift gate: the live PR head must still equal what was reviewed.
    let head = crate::forge::pr_head_sha(&ctx.repo, pr)
        .await
        .map_err(|e| anyhow::anyhow!("read PR #{pr} head: {e}"))?;
    if head != reviewed {
        bail!(
            "PR #{pr} head drifted since review (reviewed {reviewed}, now {head}); re-review before merging"
        );
    }

    // 2. Fetch the reviewed head into applied so ff/verify/deploy resolve it.
    crate::forge::fetch_pr_head_into_applied(&ctx.repo, pr)
        .await
        .map_err(|e| anyhow::anyhow!("fetch PR #{pr} head into applied: {e}"))?;

    // 3. Ancestry gate: `main` must be reachable from the reviewed head, or the
    // "fast-forward" in prepare_applied_target is really a rewind that drops
    // every commit between the PR's base and where `main` actually is now.
    let current_main = lifecycle::git_rev_parse(&ctx.applied_dir, "refs/heads/main")
        .await
        .map_err(|e| anyhow::anyhow!("read applied/main: {e:#}"))?;
    if !lifecycle::git_is_ancestor(&ctx.applied_dir, &current_main, reviewed)
        .await
        .map_err(|e| anyhow::anyhow!("ancestry check {current_main}..{reviewed}: {e:#}"))?
    {
        bail!(
            "PR #{pr} does not descend from applied/main (main {current_main}, reviewed {reviewed}); \
             merging it would discard commits — rebase the PR onto main and re-review"
        );
    }

    // 4. Eval-verify BEFORE the irreversible merge (bad nix fails fast here).
    crate::meta::verify_commit(ctx.approval.agent.as_str(), &ctx.applied_dir, reviewed)
        .await
        .map_err(|e| anyhow::anyhow!("verify merge head {reviewed}: {e:#}"))?;
    Ok(())
}

/// `DeployApply` node body — the irreversible half. Parks the rollback ref,
/// fast-forward-merges the PR (THE merge), then opens the deploy.
///
/// The ref is parked *before* the merge, so a hive-c0re crash anywhere from
/// here on still leaves [`run_deploy_tail`] enough to undo. If the merge itself
/// fails, `main` never moved and the tail's compensation is a no-op against the
/// same sha — harmless, and cheaper than trying to be clever about it.
///
/// Returning `Ok` is the signal for the caller to grow the rebuild subgraph into
/// this DAG under this node; the build itself does not happen here.
///
/// # Errors
///
/// Returns an error if the approval can't be loaded, if reading or parking the
/// pre-merge `main` sha fails, if the forge refuses the fast-forward merge
/// (including a head that drifted between verify and merge), or if
/// fast-forwarding `applied/main` / `meta::prepare_deploy` fails. From the merge
/// onward a failure is *not* retryable on its own — [`run_deploy_tail`] runs
/// `AfterAny` to compensate.
pub async fn run_deploy_apply(coord: &Arc<Coordinator>, approval_id: i64) -> Result<()> {
    let ctx = deploy_ctx(coord, approval_id)?;
    let agent = ctx.approval.agent.as_str();
    let pr = ctx.pr;

    let prev_main = lifecycle::git_rev_parse(&ctx.applied_dir, "refs/heads/main")
        .await
        .map_err(|e| anyhow::anyhow!("read applied/main: {e:#}"))?;
    lifecycle::git_update_ref(&ctx.applied_dir, &rollback_ref(approval_id), &prev_main)
        .await
        .map_err(|e| anyhow::anyhow!("park rollback ref for approval {approval_id}: {e:#}"))?;

    // THE merge: fast-forward-only merge the reviewed head to `main` via the
    // forge API, pinned to the reviewed sha (`head_commit_id`). This one call
    // both advances `main` to the reviewed head and marks the PR merged — no
    // direct push to the protected branch. A failure here means `main` was NOT
    // advanced, so it's fatal: we must not deploy a head the forge didn't merge.
    match crate::forge::merge_config_pr_ff(&ctx.repo, pr, &ctx.reviewed).await {
        Ok(()) => {}
        Err(crate::forge::ForgeMergeError::HeadDrift { expected, actual }) => bail!(
            "PR #{pr} head drifted before merge (reviewed {expected}, now {actual}); re-review before merging"
        ),
        Err(e) => bail!("ff-merge PR #{pr}: {e}"),
    }

    prepare_applied_target(agent, &ctx.applied_dir, &ctx.reviewed, &prev_main).await
}

/// `DeployTail` node body — compensation + bookkeeping, `AfterAny` the apply
/// node so it runs on every outcome including a cancel-cascade. Infallible by
/// construction: it is the recovery step, so it has nothing to hand a failure
/// to. Every fallible call inside warns and continues.
///
/// 1. If the rollback ref survived, the deploy did not confirm good: tag the
///    merged commit `failed/<id>` (annotated with the DAG's first error, while
///    that sha is still reachable), then roll `applied/main` back to the parked
///    sha, resync the working tree, and drop the staged meta lock so the deploy
///    log only ever shows successes.
/// 2. Mirror the agent's config repo to the forge. `main` is already ff'd by
///    the merge, so only the `deployed/<id>` / `failed/<id>` tag refspec
///    actually lands — that's what gives the merged commit a forge-visible
///    deploy marker.
///
/// Takes `agent` from the node payload rather than the approval row so it still
/// works if the row vanished underneath the DAG (deny race, purge).
pub async fn run_deploy_tail(
    coord: &Arc<Coordinator>,
    queue_entry_id: Option<u64>,
    agent: &str,
    approval_id: i64,
) {
    let applied_dir = crate::paths::applied_dir(agent);
    let rollback = rollback_ref(approval_id);
    if let Ok(prev_main) = lifecycle::git_rev_parse(&applied_dir, &rollback).await {
        // Belt and braces: `run_deploy_apply` drops the ref before it plants
        // `deployed/<id>`, so seeing both means the *delete* failed on an
        // otherwise-successful deploy. Rolling back there would be the worst
        // outcome this node can produce, so the tag wins.
        if lifecycle::git_rev_parse(&applied_dir, &format!("deployed/{approval_id}"))
            .await
            .is_ok()
        {
            tracing::warn!(
                %agent, approval_id,
                "deploy tail: rollback ref outlived a successful deploy; dropping it without compensating"
            );
        } else {
            // Mark the commit that failed to deploy, before undoing the merge
            // that put it on `main`. After the rollback below, that sha is only
            // reachable through this tag.
            //
            // Gated on `main` having actually moved: the rollback ref is parked
            // *before* the merge, so its existence alone doesn't mean a merge
            // happened. A pre-merge rejection (drift gate, eval failure, or the
            // ff-merge itself failing) has no deployed commit to blame, and
            // tagging the previous — innocent — head would point the operator at
            // a commit that never got near a container.
            //
            // The annotation is read off the DAG rather than passed down from
            // the node that failed: this node runs `AfterAny` its subject, so by
            // now that node has settled `Failed` with its error recorded.
            if let Ok(merged) = lifecycle::git_rev_parse(&applied_dir, "refs/heads/main").await
                && merged != prev_main
            {
                let tag = format!("failed/{approval_id}");
                let body = queue_entry_id
                    .and_then(|dag_id| coord.job_queue.first_error(dag_id))
                    .unwrap_or_else(|| "deploy failed".to_owned());
                if let Err(e) =
                    lifecycle::git_tag_annotated(&applied_dir, &tag, &merged, &body).await
                {
                    tracing::warn!(%agent, approval_id, error = ?e, "deploy tail: annotate failed tag failed");
                }
            }

            if let Err(e) =
                lifecycle::git_update_ref(&applied_dir, "refs/heads/main", &prev_main).await
            {
                tracing::warn!(%agent, approval_id, error = ?e, "deploy tail: main rollback failed");
            }
            if let Err(e) = lifecycle::git_read_tree_reset(&applied_dir, "refs/heads/main").await {
                tracing::warn!(%agent, approval_id, error = ?e, "deploy tail: rollback read-tree failed");
            }
            if let Err(e) = crate::meta::abort_deploy().await {
                tracing::warn!(%agent, approval_id, error = ?e, "deploy tail: meta abort_deploy failed");
            }
        }
        if let Err(e) = lifecycle::git_delete_ref(&applied_dir, &rollback).await {
            tracing::warn!(%agent, approval_id, error = ?e, "deploy tail: drop rollback ref failed");
        }
    }

    if let Err(e) = crate::forge::push_config(agent).await {
        tracing::warn!(%agent, error = ?e, "forge: push_config after merge failed");
    }
}

/// Max stderr bytes to inline in a PR failure comment. Keeps the comment
/// readable and under forge's size limits while still carrying the tail
/// where the nix/build error actually surfaces.
const PR_FAIL_LOG_TAIL_BYTES: usize = 4000;

/// On a failed `MergeConfigPr` deploy, post the failing build log back to the
/// config PR as a comment so the manager sees the rejection reason on the PR
/// itself. Best-effort: any error here is logged, never allowed to disturb the
/// approval-resolution path.
///
/// The failing `build_log` row is located heuristically: the most recent `fail`
/// row for this agent that started at/after the approval was decided (i.e. when
/// its deploy DAG was submitted). Because deploys are serialised per agent
/// through the queue, that is the step which just failed — `verify`,
/// `prepare-deploy`, `prebuild`, or the container rebuild. Pre-build failures
/// (drift gate, fetch) create no `build_log` row, so the comment then carries
/// only the error text.
async fn post_merge_failure_to_pr(
    coord: &Arc<Coordinator>,
    approval: &hive_sh4re::Approval,
    err: &anyhow::Error,
) {
    let Ok(pr) = approval.commit_ref.parse::<u64>() else {
        return;
    };
    let repo = crate::forge::config_repo(approval.agent.as_str());
    let since_ts = approval
        .resolved_at
        .unwrap_or(approval.requested_at)
        .timestamp();

    let log_section = coord
        .build_logs
        .list_recent_for_agent(approval.agent.as_str(), 10)
        .ok()
        .and_then(|rows| {
            rows.into_iter()
                .find(|r| r.status.as_deref() == Some("fail") && r.started_at >= since_ts)
        })
        .and_then(|row| coord.build_logs.get_full(row.id).ok().flatten())
        .map(|full| {
            let tail = tail_bytes(full.stderr.trim_end(), PR_FAIL_LOG_TAIL_BYTES);
            format!(
                "\n\n**Failing step:** `{}` (build log #{})\n\n```\n{tail}\n```",
                full.header.kind, full.header.id
            )
        })
        .unwrap_or_default();

    let body = format!(
        "## ⚠️ config deploy failed\n\n\
         Approval #{} to merge this PR could not be deployed:\n\n\
         ```\n{err:#}\n```{log_section}",
        approval.id
    );

    if let Err(e) = crate::forge::post_pr_comment(&repo, pr, &body).await {
        tracing::warn!(agent = %approval.agent, %pr, error = ?e, "post merge-failure comment to PR failed");
    }
}

/// Return the last `max_bytes` of `s`, snapped to a char boundary, prefixed
/// with an elision marker when truncated.
fn tail_bytes(s: &str, max_bytes: usize) -> String {
    if s.len() <= max_bytes {
        return s.to_owned();
    }
    let mut start = s.len() - max_bytes;
    while start < s.len() && !s.is_char_boundary(start) {
        start += 1;
    }
    format!("[… truncated …]\n{}", &s[start..])
}

/// Inline (non-queued) handler for `ApprovalKind::SchedulePrompt`.
/// On approve, decode the `SchedulePromptPayload` JSON from the
/// approval's `commit_ref`, insert a row into `scheduled_prompts`
/// (with `source = Approval { id }`), and fire `ApprovalResolved`.
/// The worker takes over from here — fan-out at fire time.
async fn run_approval_schedule_prompt(
    coord: &Coordinator,
    approval: hive_sh4re::Approval,
) -> Result<()> {
    let result: Result<()> = async {
        let payload: hive_sh4re::SchedulePromptPayload = serde_json::from_str(&approval.commit_ref)
            .context("decode SchedulePromptPayload from approval.commit_ref")?;
        coord
            .scheduled_prompts
            .submit(&crate::scheduled_prompts::NewSchedule {
                owner: approval.agent.to_string(),
                targets: payload.targets,
                body: payload.body,
                first_fire_at_unix: payload.first_fire_at_unix,
                interval_seconds: payload.interval_seconds,
                description: payload.description,
                source: crate::scheduled_prompts::ScheduleSource::Approval { id: approval.id },
            })
            .map(|_| ())
            .context("insert scheduled prompt")
    }
    .await;
    finish_approval(coord, &approval, result, None).await
}

/// Resolve an approval row from how its DAG's work ended — the body of the
/// [`NodeKind::ResolveApproval`] tail node. Every approval-carrying template
/// resolves here, deploys included: the deploy pipeline is ordinary queue nodes,
/// so the work's terminal state is the authoritative outcome and there's no
/// in-node resolution to skip around.
///
/// `outcome` is the one the calling node was built to report — a template emits
/// one tail per outcome, so success, failure and cancel each arrive here from
/// their own node rather than from one node branching.
///
/// [`NodeKind::ResolveApproval`]: crate::job_queue::NodeKind::ResolveApproval
pub(crate) async fn resolve_approval_dag(
    coord: &Arc<Coordinator>,
    approval_id: i64,
    outcome: crate::job_queue::TerminalState,
    error: Option<&str>,
) {
    use crate::job_queue::TerminalState;
    let approval = match coord.approvals.get(approval_id) {
        Ok(Some(a)) => a,
        Ok(None) => {
            tracing::warn!(approval_id, "approval dag terminal: row no longer exists");
            return;
        }
        Err(e) => {
            tracing::warn!(approval_id, error = ?e, "approval dag terminal: row read failed");
            return;
        }
    };
    let result: Result<()> = match outcome {
        TerminalState::Done => Ok(()),
        // `Skipped` never reaches here — no template emits a tail for it — but it
        // reads the same to an operator either way: the work did not happen.
        TerminalState::Cancelled | TerminalState::Skipped => {
            Err(anyhow::anyhow!("cancelled before completion"))
        }
        TerminalState::Failed => Err(anyhow::anyhow!("{}", error.unwrap_or("job dag failed"))),
    };
    let mut terminal_tag = None;
    match approval.kind {
        ApprovalKind::Spawn => {
            // Post-spawn forge bookkeeping (user, config repo mirror, meta
            // access) — warn-only, then the resolution events + a rescan so
            // the dashboard reflects the post-spawn state either way.
            if result.is_ok() {
                forge_after_first_spawn(coord, approval.agent.as_str()).await;
            } else {
                coord.rescan_containers_and_emit().await;
                crate::dashboard::emit_tombstones_snapshot(coord).await;
            }
        }
        ApprovalKind::MergeConfigPr => {
            terminal_tag = deploy_terminal_tag(approval.agent.as_str(), approval_id, outcome).await;
            // On a failed deploy, surface the failing build log back onto the
            // PR so the manager sees why it was rejected without leaving the
            // forge. Posted here rather than inside a node because this is the
            // one place that holds the DAG's definitive error — a `MergeVerify`
            // rejection and a `DeployApply` build failure both land here.
            if let Err(e) = &result {
                post_merge_failure_to_pr(coord, &approval, e).await;
            }
        }
        _ => {}
    }
    if let Err(e) = finish_approval(coord, &approval, result, terminal_tag).await {
        tracing::warn!(approval_id, error = ?e, "approval dag resolved with failure");
    }
}

/// Which bookkeeping tag a settled deploy DAG actually planted, for the
/// `Rebuilt` event's `tag` field. The state picks the candidate name, but the
/// applied repo has the final say: a pre-merge rejection (`MergeVerify` drift
/// gate, eval failure) fails the DAG without ever planting `failed/<id>`, and
/// tag plants are best-effort. Reporting a tag that isn't there would send the
/// manager looking for a ref that doesn't exist.
async fn deploy_terminal_tag(
    agent: &str,
    approval_id: i64,
    outcome: crate::job_queue::TerminalState,
) -> Option<String> {
    use crate::job_queue::TerminalState;
    let candidate = match outcome {
        TerminalState::Done => format!("deployed/{approval_id}"),
        // Nothing ran, so nothing was planted.
        TerminalState::Cancelled | TerminalState::Skipped => return None,
        TerminalState::Failed => format!("failed/{approval_id}"),
    };
    lifecycle::git_rev_parse(&crate::paths::applied_dir(agent), &candidate)
        .await
        .ok()
        .map(|_| candidate)
}

/// Re-fetch an approval row from sqlite for a queue-worker dispatch.
/// Bails if the row is gone (deny race), if its kind doesn't match,
/// or if the lookup itself fails. The kind check is defensive — the
/// queue's `dispatch` already routes by `QueueKind`, but the approval
/// kind is the authoritative source of truth and a mismatch points
/// at a deeper bug we'd want to surface.
fn fetch_approval_for_worker(
    coord: &Coordinator,
    approval_id: i64,
    expected_kind: ApprovalKind,
) -> Result<hive_sh4re::Approval> {
    let approval = coord
        .approvals
        .get(approval_id)
        .map_err(|e| anyhow::anyhow!("read approval {approval_id}: {e:#}"))?
        .ok_or_else(|| anyhow::anyhow!("approval {approval_id} no longer exists"))?;
    if approval.kind != expected_kind {
        bail!(
            "approval {approval_id} kind mismatch: queue expected {expected_kind:?}, row is {actual:?}",
            actual = approval.kind
        );
    }
    Ok(approval)
}

/// Forge bookkeeping run once after the very first container spawn:
/// create the per-agent forge user, mirror the applied repo, and grant
/// read access to core/meta. Also rescans containers so the dashboard
/// reflects the post-spawn state.
async fn forge_after_first_spawn(coord: &Arc<Coordinator>, agent: &str) {
    if let Err(e) = crate::forge::ensure_user_for(agent).await {
        tracing::warn!(%agent, error = ?e, "forge: ensure_user after first spawn failed");
    }
    if let Err(e) = crate::forge::ensure_config_repo(agent).await {
        tracing::warn!(%agent, error = ?e, "forge: ensure_config_repo after first spawn failed");
    }
    if let Some(core_token) = crate::forge::core_token()
        && let Err(e) = crate::forge::meta_read_access(agent, &core_token).await
    {
        tracing::warn!(%agent, error = ?e, "forge: meta_read_access after first spawn failed");
    }
    if let Err(e) = crate::forge::ensure_meta_remote(agent).await {
        tracing::warn!(%agent, error = ?e, "forge: ensure_meta_remote after first spawn failed");
    }
    coord.rescan_containers_and_emit().await;
    crate::dashboard::emit_tombstones_snapshot(coord).await;
}

/// Inline (non-queued) handler for `ApprovalKind::InitConfig`. Just
/// seeds the proposed git repo + the per-agent dirs — sub-second
/// work that doesn't justify a queue card.
async fn run_approval_init_config(
    coord: &Coordinator,
    approval: hive_sh4re::Approval,
    proposed_dir: std::path::PathBuf,
    claude_dir: std::path::PathBuf,
    notes_dir: std::path::PathBuf,
) -> Result<()> {
    let result: Result<()> = async {
        // Place the new child under its requesting parent (carried in
        // commit_ref by submit_init_config). An empty commit_ref means
        // no explicit parent was named (privileged manager socket, or an
        // approval queued before the new-child feature) — write no edge
        // and let `topology::reconcile` assign the default position on
        // first spawn, so this path never names a specific root agent.
        if !approval.commit_ref.is_empty() {
            crate::topology::add_child(approval.agent.as_str(), &approval.commit_ref)
                .map_err(|e| anyhow::anyhow!("topology add_child: {e}"))?;
        }
        // Create the agent's state root as a btrfs subvolume FIRST, before
        // any dir-seed touches it. `ensure_agent_state_subvolume` is
        // progressive ("root exists → skip"), and `setup_proposed` does a
        // `create_dir_all` on the proposed-config path which would
        // materialise the state root as a plain directory — after which
        // the subvolume create is silently skipped and the agent never
        // lands on a subvolume (no quota, no snapshot). Order matters.
        lifecycle::ensure_agent_state_subvolume(approval.agent.as_str()).await?;
        lifecycle::setup_proposed(&proposed_dir, approval.agent.as_str()).await?;
        lifecycle::ensure_claude_dir(&claude_dir)?;
        lifecycle::ensure_state_dir(&notes_dir)?;
        Ok(())
    }
    .await;
    if result.is_ok()
        && let Err(e) = crate::forge::ensure_meta_remote(approval.agent.as_str()).await
    {
        tracing::warn!(agent = %approval.agent, error = ?e, "forge: ensure_meta_remote after init_config failed");
    }
    finish_approval(coord, &approval, result, None).await
}

async fn finish_approval(
    coord: &Coordinator,
    approval: &hive_sh4re::Approval,
    result: Result<()>,
    terminal_tag: Option<String>,
) -> Result<()> {
    let (status, note, ok) = match &result {
        Ok(()) => (ApprovalStatus::Approved, None, true),
        Err(e) => {
            let note = format!("{e:#}");
            let _ = coord.approvals.mark_failed(approval.id, &note);
            (ApprovalStatus::Failed, Some(note), false)
        }
    };
    coord.notify_submitter(
        approval.id,
        &HelperEvent::ApprovalResolved {
            id: approval.id,
            agent: approval.agent.to_string(),
            commit_ref: approval.commit_ref.clone(),
            status,
            note: note.clone(),
            sha: approval.fetched_sha.clone(),
            tag: terminal_tag.clone(),
        },
    );
    // Phase 5b: also fire on the dashboard event channel so the
    // browser moves the row out of pending into history without a
    // snapshot refetch. `approved` rows that succeed get the
    // approval's logged resolved_at indirectly via `Utc::now()`;
    // failures already wrote it via mark_failed above.
    let approval_kind = approval.kind.as_str();
    let sha_short = approval
        .fetched_sha
        .as_deref()
        .map(|s| s[..s.len().min(12)].to_owned());
    let status_str = if ok { "approved" } else { "failed" };
    coord.emit_approval_resolved(crate::coordinator::ApprovalResolved {
        id: approval.id,
        agent: approval.agent.as_str(),
        approval_kind,
        sha_short,
        status: status_str,
        note: note.clone(),
        description: approval.description.clone(),
    });
    // For spawn/rebuild/init_config approvals, also surface the underlying
    // action so the manager knows whether the lifecycle step succeeded.
    // The ApprovalResolved event already carries the same `ok` signal but
    // separating it lets the manager react to the lifecycle change
    // without having to special-case approvals.
    match approval.kind {
        ApprovalKind::InitConfig => {
            if ok {
                let _ = coord
                    .push_todo_submitter(
                        approval.id,
                        "core",
                        Some(format!("config_ready:{}", approval.agent)),
                        format!(
                            "agent '{}' config repo ready — edit + apply",
                            approval.agent
                        ),
                        None,
                    )
                    .await;
            }
        }
        ApprovalKind::Spawn => {
            let summary = if ok {
                format!("agent '{}' spawned", approval.agent)
            } else {
                format!(
                    "agent '{}' spawn FAILED: {}",
                    approval.agent,
                    note.as_deref().unwrap_or("unknown error")
                )
            };
            let _ = coord
                .push_todo_submitter(
                    approval.id,
                    "core",
                    Some(format!("spawned:{}", approval.agent)),
                    summary,
                    None,
                )
                .await;
        }
        // MergeConfigPr ends in a container rebuild — surface a Rebuilt
        // lifecycle event. (It is never a first spawn — the agent already
        // exists — so it never needs the Spawned arm above.)
        ApprovalKind::MergeConfigPr => {
            let summary = crate::coordinator::rebuilt_todo_summary(
                approval.agent.as_str(),
                ok,
                note.as_deref(),
                approval.fetched_sha.as_deref(),
                terminal_tag.as_deref(),
            );
            let _ = coord
                .push_todo_submitter(
                    approval.id,
                    "core",
                    Some(format!("rebuilt:{}", approval.agent)),
                    summary,
                    None,
                )
                .await;
        }
        // UpdateMetaInputs / SchedulePrompt: ApprovalResolved already
        // carries the result. No separate lifecycle event needed.
        ApprovalKind::UpdateMetaInputs | ApprovalKind::SchedulePrompt => {}
    }
    result
}

/// Open the deploy for the config-PR flow: fast-forward `applied/main` to
/// `target`, sync the working tree, and run phase 1 of the meta two-phase
/// deploy. The container rebuild that used to run inline here is now the
/// subgraph [`run_deploy_apply`]'s node grows into the DAG, and the closing half
/// is [`run_finalize_deploy`].
///
/// **Undo is not this function's job.** Every early return here leaves the
/// applied repo dirty on purpose — [`run_deploy_tail`] owns compensation, and
/// it runs whether this returns `Err`, panics, or never returns at all because
/// hive-c0re was restarted underneath it. That's the whole point of parking the
/// pre-merge sha in a git ref instead of a local variable.
///
/// Caller-specific bits stay OUT of here: fetching the PR head, the
/// `verify_commit` gate, and the ff-merge. The agent always already exists here
/// (a merge is never a first spawn), so there's no `sync_agents` step — the
/// operator `Spawn` flow owns first-time meta registration.
async fn prepare_applied_target(
    agent: &str,
    applied_dir: &std::path::Path,
    target: &str,
    expected_main: &str,
) -> Result<()> {
    // Fast-forward applied/main to target + sync the working tree. Meta input
    // pins `?ref=main`, so this is what makes nix re-lock to the target commit
    // on the prepare_deploy step below.
    //
    // Compare-and-swap, not a bare set: `main` must still be the sha the caller
    // read before the merge. A plain `update-ref` here moves the branch to
    // `target` whatever it currently points at, which turns "fast-forward" into
    // "discard anything that landed in the meantime" — the ancestry gate in
    // run_deploy_merge_verify only proves the target is safe against the `main`
    // observed *then*, so this is what makes that proof still true *now*.
    lifecycle::git_update_ref_cas(applied_dir, "refs/heads/main", target, expected_main)
        .await
        .map_err(|e| {
            anyhow::anyhow!("ff main {expected_main} -> {target} (concurrent move?): {e:#}")
        })?;
    lifecycle::git_read_tree_reset(applied_dir, "refs/heads/main")
        .await
        .map_err(|e| anyhow::anyhow!("read-tree to main: {e:#}"))?;

    // Phase 1 of the meta two-phase deploy: relock without committing. The
    // staged lock then stays uncommitted across the whole appended rebuild —
    // which is why the `MetaWindow` is held by the deploy root, not by a node.
    crate::meta::prepare_deploy(agent)
        .await
        .map_err(|e| anyhow::anyhow!("meta prepare_deploy: {e:#}"))
}

/// `FinalizeDeploy` node body — phase 2 of the meta two-phase deploy, run once
/// the appended rebuild subgraph has built, swapped, and brought the container
/// back up.
///
/// Drops the rollback ref *first*: from here the deploy is good and
/// [`run_deploy_tail`] must not roll `main` back. Ordering that ahead of the tag
/// plant is what makes the tail's `deployed/<id>` cross-check a second line of
/// defence rather than the only one. No agent kick — the rebuild's own
/// `PostSwap` already did it.
///
/// # Errors
///
/// Returns an error if the approval can't be loaded, if dropping the rollback
/// ref fails, or if planting the `deployed/<id>` tag fails. Those two git writes
/// *are* the deploy's "confirmed good" signal, so warning past them would let
/// this node report success while leaving the tail looking at the git state of a
/// failure — and the tail would then compensate a good deploy. A failing
/// `meta::finalize_deploy` is deliberately *not* an error: the container is
/// already running the new config by then, and the staged `flake.lock` it
/// couldn't commit is something the operator can land by hand.
pub async fn run_finalize_deploy(coord: &Arc<Coordinator>, approval_id: i64) -> Result<()> {
    let ctx = deploy_ctx(coord, approval_id)?;
    let agent = ctx.approval.agent.as_str();
    let target = ctx.reviewed.as_str();

    lifecycle::git_delete_ref(&ctx.applied_dir, &rollback_ref(approval_id))
        .await
        .map_err(|e| anyhow::anyhow!("drop rollback ref for approval {approval_id}: {e:#}"))?;

    let tag = format!("deployed/{approval_id}");
    lifecycle::git_tag(&ctx.applied_dir, &tag, target)
        .await
        .map_err(|e| anyhow::anyhow!("plant {tag}: {e:#}"))?;

    if let Err(e) = crate::meta::finalize_deploy(agent, target, &tag).await {
        tracing::warn!(%agent, approval_id, error = ?e, "meta finalize_deploy failed");
    }
    Ok(())
}

/// Tear down a sub-agent container. By default this is non-destructive to
/// persistent state: the proposed/applied config repos and the Claude
/// credentials dir under `/var/lib/hyperhive/{agents,applied}/<name>/` are
/// kept, so recreating an agent of the same name reuses prior config + creds
/// (no re-login). The ephemeral runtime dir under `/run/hyperhive/agents/`
/// is cleared because its contents (the mcp socket) don't survive restarts
/// anyway. With `purge=true` the persistent trees are also wiped — config
/// history, claude creds, notes — there is no undo.
/// The bootstrap/root container is destroyable like any other: it's
/// imperative infra that `auto_update::ensure_root_agent` recreates on the
/// next hive-c0re startup if absent, so destroying it is transient rather
/// than something to refuse at the API.
pub async fn destroy(coord: &Arc<Coordinator>, name: &str, purge: bool) -> Result<()> {
    tracing::info!(%name, purge, "destroy");
    // Guard auto-clears on the success path's final scope exit and on
    // every early-return / cancellation along the way.
    // Destroy has no queue node behind it, so nothing in the graph says this
    // container is going away on purpose — without this the crash watcher
    // reports every destroy as a crash and the manager tries to recover it.
    let guard = coord.suppress_crash_watch(name);
    lifecycle::destroy(name).await?;
    coord.unregister_agent(name);
    let runtime = crate::paths::agent_runtime_dir(name);
    if runtime.exists() {
        let _ = std::fs::remove_dir_all(&runtime);
    }
    if purge {
        // The state root may be a btrfs subvolume: a subvolume root
        // can't be removed with rmdir/`remove_dir_all`, so delete it via
        // hive-priv (root) first. No-op for plain-dir agents — the loop below
        // then handles the plain-dir state root plus the applied dir.
        if let Err(e) = crate::priv_client::delete_agent_subvolume(name).await {
            tracing::warn!(error = ?e, %name, "purge: delete state subvolume failed");
        }
        // A malformed name can't have a persistent state tree (the state dir
        // is only ever created under a validated Ident), so its removal is a
        // no-op — skip the state-dir sweep and just clear the applied dir.
        let state_dir = hive_types::Ident::parse(name)
            .ok()
            .map(|id| crate::paths::agent_state_dir(&id));
        for dir in state_dir
            .into_iter()
            .chain([crate::paths::applied_dir(name)])
        {
            if dir.exists()
                && let Err(e) = std::fs::remove_dir_all(&dir)
            {
                tracing::warn!(error = ?e, dir = %dir.display(), "purge: remove failed");
            }
        }
    }
    // Meta flake: drop the agent's input + nixosConfiguration so a
    // future spawn under the same name re-seeds cleanly, and so the
    // meta lock doesn't reference a vanished applied repo. Log + keep
    // going on failure — destroy already succeeded at the
    // nixos-container level, the meta repo is just bookkeeping.
    if let Err(e) = sync_meta_after_lifecycle(coord).await {
        tracing::warn!(error = ?e, %name, "meta sync after destroy failed");
    }
    let _ = coord.approvals.fail_pending_for_agent(
        name,
        if purge {
            "agent purged"
        } else {
            "agent destroyed"
        },
    );
    // Drop the durable power intent — a future agent of the same name
    // seeds fresh from its observed state.
    if let Err(e) = coord.power.remove(name) {
        tracing::warn!(%name, error = ?e, "agent_power: remove on destroy failed");
    }
    drop(guard);
    let _ = coord
        .push_todo(
            hive_sh4re::MANAGER_AGENT,
            "core",
            Some(format!("destroyed:{name}")),
            format!("agent '{name}' destroyed"),
            None,
        )
        .await;
    // Container row disappeared — rescan so the dashboard fires
    // `ContainerRemoved` for the gone row, then emit the
    // tombstones snapshot (gained one on destroy, lost one on
    // purge — recompute either way).
    coord.rescan_containers_and_emit().await;
    crate::dashboard::emit_tombstones_snapshot(coord).await;
    // Re-emit the schedules snapshot: the rescan above refreshed the live
    // roster, so any schedule that still targets the just-destroyed agent
    // now drops that ghost column live (no page reload needed).
    coord.emit_schedules_snapshot();
    // Update tmpfiles.d to remove the destroyed agent's dirs from the
    // boot-time pre-creation list. Best-effort: failure is logged only.
    tokio::spawn(lifecycle::sync_tmpfiles());
    Ok(())
}

/// Rerender the meta flake from whatever containers still exist on
/// disk. Called after lifecycle ops that change the agent set (today:
/// destroy). Idempotent — a no-op when nothing changed.
async fn sync_meta_after_lifecycle(coord: &Coordinator) -> Result<()> {
    let agents = lifecycle::agents_for_meta_listing().await?;
    crate::meta::sync_agents(&coord.hive_env(), &agents).await
}

pub fn deny(coord: &Coordinator, id: i64, note: Option<&str>) -> Result<()> {
    let approval = coord.approvals.get(id)?;
    coord.approvals.mark_denied(id, note)?;
    tracing::info!(%id, note, "approval denied");
    if let Some(a) = approval {
        let sha = a.fetched_sha.clone();
        let approval_kind = a.kind.as_str();
        let sha_short = sha.as_deref().map(|s| s[..s.len().min(12)].to_owned());
        let description = a.description.clone();
        let agent_owned = a.agent.clone();
        coord.notify_submitter(
            a.id,
            &HelperEvent::ApprovalResolved {
                id: a.id,
                agent: a.agent.to_string(),
                commit_ref: a.commit_ref,
                status: ApprovalStatus::Denied,
                note: note.map(String::from),
                sha,
                // A denied config PR carries no git tag — it stays open on the forge.
                tag: None,
            },
        );
        coord.emit_approval_resolved(crate::coordinator::ApprovalResolved {
            id,
            agent: agent_owned.as_str(),
            approval_kind,
            sha_short,
            status: "denied",
            note: note.map(String::from),
            description,
        });
    }
    Ok(())
}