feat(#2290): split ensure_runtime — dirs to lifecycle, listeners to mcp_sockets supervisor

- lifecycle::ensure_agent_runtime_dir(name): pure filesystem op, no
  Coordinator dep. Creates /run/hyperhive/agents/<name> without touching
  the MCP listener map.

- workers/mcp_sockets::spawn_poll(coord): 10 s reconcile loop (same shape
  as agent_sockets::spawn_poll). Converges 'agent running => MCP listener
  bound'. First tick is immediate so hive-c0re restarts re-register all
  running agents without waiting a full interval. Fixes the dead-listener-
  after-daemon-restart gap.

- All ensure_runtime() call sites updated:
  - Prebuild/Swap/WriteDropin: Coordinator::agent_dir() (pure, no IO)
  - Reconcile-Start: ensure_agent_runtime_dir + agent_dir (dir may be
    missing after reboot; listener deferred to supervisor)
  - run_create / handle_spawn: ensure_agent_runtime_dir + register_agent
    (eager on first spawn so socket ready before harness first turn)
  - apply_commit / merge_config_pr: ensure_agent_runtime_dir + agent_dir
  - Manager (auto_update): ensure_agent_runtime_dir + agent_dir
    (manager has no MCP listener; socket_server::start_manager owns it)

- ensure_runtime() retained in Coordinator with updated doc pointing at
  the preferred split form. No callers remain outside tests.
This commit is contained in:
atlas 2026-07-08 23:27:48 +02:00
commit 3d919b596f
10 changed files with 147 additions and 30 deletions

View file

@ -159,7 +159,11 @@ pub async fn run_approval_apply_commit(
approval_id: i64,
) -> Result<()> {
let approval = fetch_approval_for_worker(coord, approval_id, ApprovalKind::ApplyCommit)?;
let agent_dir = coord.ensure_runtime(&approval.agent)?;
// Create the bind-mount source dir (first-spawn may not have it yet).
// MCP listener registration is deferred to mcp_sockets::spawn_poll
// which fires within 10 s of the container coming up.
lifecycle::ensure_agent_runtime_dir(&approval.agent)?;
let agent_dir = Coordinator::agent_dir(&approval.agent);
let applied_dir = Coordinator::agent_applied_dir(&approval.agent);
coord.set_queue_step(queue_entry_id, "apply commit");
let (result, terminal_tag, is_first_spawn) =
@ -192,7 +196,8 @@ pub async fn run_approval_merge_config_pr(
approval_id: i64,
) -> Result<()> {
let approval = fetch_approval_for_worker(coord, approval_id, ApprovalKind::MergeConfigPr)?;
let agent_dir = coord.ensure_runtime(&approval.agent)?;
lifecycle::ensure_agent_runtime_dir(&approval.agent)?;
let agent_dir = Coordinator::agent_dir(&approval.agent);
let applied_dir = Coordinator::agent_applied_dir(&approval.agent);
coord.set_queue_step(queue_entry_id, "merge config pr");
let (result, terminal_tag) =