hyperhive/hive-c0re/src/actions.rs
müde 06fdbac1ac actions::run_apply_commit through meta two-phase
approval-driven deploys now walk the meta flake via
prepare_deploy / finalize_deploy / abort_deploy so a failed
build leaves no commit in meta's deploy log:

1. capture applied/main sha for rollback
2. tag approved/<id> + building/<id>
3. ff applied/main to proposal/<id>, read-tree sync working tree
4. meta::prepare_deploy(name) — nix flake lock --update-input
   agent-<n> without committing
5. lifecycle::rebuild_no_meta — container-level only (new
   extracted helper; public lifecycle::rebuild still wraps it
   with single-phase meta sync + commit for dashboard / auto
   _update callers that don't care about rollback)
6a. on success: tag deployed/<id>, meta::finalize_deploy commits
    the staged lock with 'deploy <n> deployed/<id> <sha12>'
6b. on failure: tag failed/<id> annotated with the build error,
    git_update_ref applied/main back to prev sha, read-tree to
    main, meta::abort_deploy git-restores flake.lock

meta's git log now records only successful deploys; failures
+ denials still live in applied as annotated tags.
2026-05-16 00:32:16 +02:00

390 lines
16 KiB
Rust

//! 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::{Result, bail};
use hive_sh4re::{ApprovalKind, ApprovalStatus, HelperEvent, MANAGER_AGENT};
use crate::coordinator::{Coordinator, TransientKind};
use crate::lifecycle::{self, MANAGER_NAME};
/// Approve a pending request and run the underlying action. Dispatches on the
/// approval kind:
/// - `ApplyCommit`: read agent.nix at the approval's commit from the proposed
/// repo, copy into the applied repo, commit there, rebuild the container.
/// Synchronous — returns once the rebuild completes.
/// - `Spawn`: create + start a brand-new sub-agent container. Runs in a
/// background task so the operator's approve click returns immediately;
/// the dashboard surfaces a transient `Spawning` state until the container
/// is up. On failure, the approval is marked failed.
///
/// In all cases an `ApprovalResolved` helper event lands in the manager's
/// inbox when the work resolves.
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: running action",
);
let agent_dir = coord.ensure_runtime(&approval.agent)?;
let proposed_dir = Coordinator::agent_proposed_dir(&approval.agent);
let applied_dir = Coordinator::agent_applied_dir(&approval.agent);
let claude_dir = Coordinator::agent_claude_dir(&approval.agent);
let notes_dir = Coordinator::agent_notes_dir(&approval.agent);
match approval.kind {
ApprovalKind::ApplyCommit => {
let (result, terminal_tag) = run_apply_commit(
&coord,
&approval,
&agent_dir,
&applied_dir,
&claude_dir,
&notes_dir,
)
.await;
finish_approval(&coord, &approval, result, terminal_tag)
}
ApprovalKind::Spawn => {
// Run the spawn in the background so the approve POST returns
// immediately. The dashboard reads `transient` to render a spinner.
coord.set_transient(&approval.agent, TransientKind::Spawning);
let coord_bg = coord.clone();
let approval_bg = approval.clone();
tokio::spawn(async move {
let agent_bg = approval_bg.agent.clone();
let result = lifecycle::spawn(
&approval_bg.agent,
&coord_bg.hyperhive_flake,
&agent_dir,
&proposed_dir,
&applied_dir,
&claude_dir,
&notes_dir,
coord_bg.dashboard_port,
)
.await;
coord_bg.clear_transient(&agent_bg);
if let Err(e) = finish_approval(&coord_bg, &approval_bg, result, None) {
tracing::warn!(agent = %agent_bg, error = ?e, "spawn approval failed");
}
});
Ok(())
}
}
}
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_manager(&HelperEvent::ApprovalResolved {
id: approval.id,
agent: approval.agent.clone(),
commit_ref: approval.commit_ref.clone(),
status,
note: note.clone(),
sha: approval.fetched_sha.clone(),
tag: terminal_tag.clone(),
});
// For spawn/rebuild approvals, also surface the underlying action so
// the manager knows whether the container actually came up. 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::Spawn => coord.notify_manager(&HelperEvent::Spawned {
agent: approval.agent.clone(),
ok,
note,
sha: approval.fetched_sha.clone(),
}),
ApprovalKind::ApplyCommit => coord.notify_manager(&HelperEvent::Rebuilt {
agent: approval.agent.clone(),
ok,
note,
sha: approval.fetched_sha.clone(),
tag: terminal_tag,
}),
}
result
}
/// Tag-driven `ApplyCommit` handler. Walks the approval through the tag
/// state machine documented in `docs/approvals.md`: stamp
/// `approved/<id>` and `building/<id>` first so the audit trail
/// captures intent, then drop the candidate tree into the working dir
/// without moving HEAD, run the rebuild, and either fast-forward
/// `applied/main` to the proposal commit on success
/// (`deployed/<id>`) or annotate `failed/<id>` with the build error
/// and reset the working tree back to the last known-good main. main
/// never advances on a failed build, so a crash-and-recover doesn't
/// leave the agent pointing at a tree it can't evaluate.
async fn run_apply_commit(
coord: &Arc<Coordinator>,
approval: &hive_sh4re::Approval,
agent_dir: &std::path::Path,
applied_dir: &std::path::Path,
claude_dir: &std::path::Path,
notes_dir: &std::path::Path,
) -> (Result<()>, Option<String>) {
let id = approval.id;
let proposal_ref = format!("refs/tags/proposal/{id}");
// Defensive: submit-time should have planted proposal/<id>, but if
// the row was migrated from an older schema or the tag got pruned
// we fail early with a clear note rather than building a stale
// tree.
if let Err(e) = lifecycle::git_rev_parse(applied_dir, &proposal_ref).await {
return (
Err(anyhow::anyhow!(
"missing proposal tag {proposal_ref}: {e:#}"
)),
None,
);
}
// Capture the currently-deployed sha so we can roll applied/main
// (and the meta lock indirectly) back if the build fails.
let prev_main_sha = match lifecycle::git_rev_parse(applied_dir, "refs/heads/main").await {
Ok(s) => s,
Err(e) => return (Err(anyhow::anyhow!("read applied/main: {e:#}")), None),
};
if let Err(e) = lifecycle::git_tag(applied_dir, &format!("approved/{id}"), &proposal_ref).await
{
return (Err(anyhow::anyhow!("plant approved/{id}: {e:#}")), None);
}
if let Err(e) = lifecycle::git_tag(applied_dir, &format!("building/{id}"), &proposal_ref).await
{
return (Err(anyhow::anyhow!("plant building/{id}: {e:#}")), None);
}
// Fast-forward applied/main to proposal/<id> + sync the working
// tree. Meta input pins `?ref=main`, so this is what makes nix
// re-lock to the proposal commit on the prepare_deploy step
// below. On build failure we roll main back to prev_main_sha so
// a crash leaves the agent on its last-good tree.
if let Err(e) =
lifecycle::git_update_ref(applied_dir, "refs/heads/main", &proposal_ref).await
{
return (
Err(anyhow::anyhow!("ff main to {proposal_ref}: {e:#}")),
None,
);
}
if let Err(e) = lifecycle::git_read_tree_reset(applied_dir, "refs/heads/main").await {
// main is ahead; working tree didn't sync. Roll main back to
// keep the two consistent before bailing.
let _ = lifecycle::git_update_ref(applied_dir, "refs/heads/main", &prev_main_sha).await;
return (
Err(anyhow::anyhow!("read-tree to main: {e:#}")),
None,
);
}
// Phase 1 of the meta two-phase deploy: relock without committing.
if let Err(e) = crate::meta::prepare_deploy(&approval.agent).await {
let _ = lifecycle::git_update_ref(applied_dir, "refs/heads/main", &prev_main_sha).await;
let _ = lifecycle::git_read_tree_reset(applied_dir, "refs/heads/main").await;
return (
Err(anyhow::anyhow!("meta prepare_deploy: {e:#}")),
None,
);
}
// Container-level rebuild against meta#<name>.
let build_result = lifecycle::rebuild_no_meta(
&approval.agent,
agent_dir,
applied_dir,
claude_dir,
notes_dir,
)
.await;
match build_result {
Ok(()) => {
let tag = format!("deployed/{id}");
if let Err(e) = lifecycle::git_tag(applied_dir, &tag, &proposal_ref).await {
tracing::warn!(agent = %approval.agent, %id, error = ?e, "plant deployed tag failed");
}
if let Err(e) = crate::meta::finalize_deploy(
&approval.agent,
approval.fetched_sha.as_deref().unwrap_or(&proposal_ref),
&tag,
)
.await
{
// The build itself succeeded — meta lock landed but
// couldn't be committed. Surface as a soft warn so the
// operator can git-commit by hand if they care.
tracing::warn!(agent = %approval.agent, %id, error = ?e, "meta finalize_deploy failed");
}
// Don't ignore the coord pointer — keeps the borrow alive
// for future tracing additions without re-plumbing.
let _ = coord;
(Ok(()), Some(tag))
}
Err(e) => {
let tag = format!("failed/{id}");
let body = format!("{e:#}");
if let Err(te) =
lifecycle::git_tag_annotated(applied_dir, &tag, &proposal_ref, &body).await
{
tracing::warn!(agent = %approval.agent, %id, error = ?te, "annotate failed tag failed");
}
// Roll main back to last known-good so the on-disk state
// matches what nixos-container last successfully built.
if let Err(re) =
lifecycle::git_update_ref(applied_dir, "refs/heads/main", &prev_main_sha).await
{
tracing::warn!(agent = %approval.agent, %id, error = ?re, "main rollback failed");
}
if let Err(re) = lifecycle::git_read_tree_reset(applied_dir, "refs/heads/main").await {
tracing::warn!(agent = %approval.agent, %id, error = ?re, "rollback read-tree failed");
}
// Drop the staged meta lock change so the deploy log
// only ever shows successes.
if let Err(ae) = crate::meta::abort_deploy().await {
tracing::warn!(agent = %approval.agent, %id, error = ?ae, "meta abort_deploy failed");
}
let _ = coord;
(Err(e), Some(tag))
}
}
}
/// 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.
/// Refuses the manager (declarative; would fight with the host's nixos config).
pub async fn destroy(coord: &Coordinator, name: &str, purge: bool) -> Result<()> {
if name == MANAGER_NAME || name == MANAGER_AGENT {
bail!("refusing to destroy the manager ({name})");
}
tracing::info!(%name, purge, "destroy");
coord.set_transient(name, TransientKind::Destroying);
let result = lifecycle::destroy(name).await;
if result.is_err() {
coord.clear_transient(name);
}
result?;
coord.unregister_agent(name);
let runtime = Coordinator::agent_dir(name);
if runtime.exists() {
let _ = std::fs::remove_dir_all(&runtime);
}
if purge {
for dir in [
Coordinator::agent_state_root(name),
Coordinator::agent_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"
},
);
coord.clear_transient(name);
coord.notify_manager(&HelperEvent::Destroyed {
agent: name.to_owned(),
});
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.hyperhive_flake, coord.dashboard_port, &agents).await
}
pub async 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");
let mut tag = None;
if let Some(a) = approval {
let sha = a.fetched_sha.clone();
// ApplyCommit approvals leave a `denied/<id>` tag on the
// proposal commit so rejected configs are first-class git
// objects — `git show denied/<id>` in the manager's applied
// mount yields both the tree the operator rejected and (in
// the annotated body) the reason. Spawn approvals have no
// commit to tag, so they fall through unannotated.
if matches!(a.kind, ApprovalKind::ApplyCommit) {
let applied_dir = Coordinator::agent_applied_dir(&a.agent);
let proposal_ref = format!("refs/tags/proposal/{id}");
if lifecycle::git_rev_parse(&applied_dir, &proposal_ref)
.await
.is_ok()
{
let tag_name = format!("denied/{id}");
let body = note.unwrap_or("").to_owned();
if let Err(e) = lifecycle::git_tag_annotated(
&applied_dir,
&tag_name,
&proposal_ref,
&body,
)
.await
{
tracing::warn!(%id, error = ?e, "plant denied tag failed");
} else {
tag = Some(tag_name);
}
}
}
coord.notify_manager(&HelperEvent::ApprovalResolved {
id: a.id,
agent: a.agent,
commit_ref: a.commit_ref,
status: ApprovalStatus::Denied,
note: note.map(String::from),
sha,
tag,
});
}
Ok(())
}