Files
clawmates/crates/cm-scheduler/src/lib.rs
T
Omar SobhandClaude Opus 4.8 3554a3aaf2
ci / gates (push) Successful in 5s
ci / frontend (push) Successful in 23s
ci / rust (push) Failing after 27s
ci / e2e (push) Has been skipped
CI: remove k8s stages, fix the Docker-level pipeline green
Survey + fixes so the pipeline passes at the Docker level (no k8s).

- Remove k8s: drop the `sandbox-k8s` job (kind/Calico/--features k8s-tests) and the
  "Helm chart lints" gate step. release.yml was already k8s-clean.
- Rust job:
  - `cargo fmt --all` — fix pre-existing formatting drift (fmt --check was failing).
  - clippy -D warnings: fix 3 lib warnings (cm-brain sort_by_key→Reverse, cm-api
    fleet.rs doc list indentation, node_rules map_or→is_none_or).
  - Regenerate the .sqlx offline cache (was missing the cm-runtime run_loop test
    query → offline compile failed). DB-backed tests use testcontainers at runtime.
  - Set SQLX_OFFLINE=true on the rust + e2e jobs so query! macros compile against
    the committed cache deterministically (no DB needed at compile time).
- Frontend job:
  - Fix the 1 ESLint error (useAgentTelemetry: no setState-synchronously-in-effect;
    tag the slice with agentId + derive null on mismatch).
  - Fix 2 stale panel-params tests (`terminal` is a valid app id now; assert the
    current APP_IDS + use a genuinely-unknown id for the reject case).

Verified locally: fmt clean, clippy --all-targets -D warnings clean (offline),
frontend lint 0 errors, tsc clean, 86/86 frontend tests pass, build OK.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-06-26 18:15:31 -07:00

133 lines
5.3 KiB
Rust

//! Routines (spec §7.6): agent-created scheduled tasks. Due routines are
//! claimed atomically (one firing even with replicas) and each firing
//! drives a REAL run through the runtime in the routine's dedicated
//! session — gated tools inside a routine still hit the approval queue.
use cm_db::repo::{agents, routine_runs, routines, sessions, teams, topology_runs};
use cm_runtime::Runtime;
use sqlx::PgPool;
use time::OffsetDateTime;
pub use cm_runtime::scheduling::next_occurrence;
#[derive(Debug, thiserror::Error)]
pub enum ScheduleError {
#[error(transparent)]
Pattern(#[from] cm_runtime::scheduling::ScheduleError),
#[error(transparent)]
Db(#[from] cm_db::DbError),
}
pub struct Scheduler {
pool: PgPool,
runtime: Runtime,
}
impl Scheduler {
pub fn new(pool: PgPool, runtime: Runtime) -> Scheduler {
Scheduler { pool, runtime }
}
/// Fires every due routine once and reschedules it. Returns how many
/// fired. Time is a parameter so tests control the clock.
pub async fn tick(&self, now: OffsetDateTime) -> Result<usize, ScheduleError> {
let due = routines::claim_due(&self.pool, now).await?;
for routine in &due {
// Reschedule first: a firing failure must not stall the clock. A
// one-shot routine (Scheduled mode, a specific date/time) fires once
// and never reschedules.
let one_shot = routine
.action
.get("one_shot")
.and_then(|v| v.as_bool())
.unwrap_or(false);
let next = if one_shot {
None
} else {
next_occurrence(&routine.schedule_cron, now).ok()
};
routines::set_next_run(&self.pool, routine.id, next).await?;
let agent_id = cm_domain::AgentId::from(routine.agent_id);
let Ok(agent) = agents::get(&self.pool, agent_id).await else {
continue; // deleted agent: routine is orphaned
};
// Topology routine: fire the whole team's stored topology as one
// durable run (the entire team loops, not just the coordinator).
if let Some(topo) = routine.action.get("topology") {
let team_id = topo
.get("team_id")
.and_then(|v| v.as_str())
.and_then(|s| s.parse::<uuid::Uuid>().ok());
let task = topo
.get("task")
.and_then(|v| v.as_str())
.unwrap_or(routine.name.as_str());
let run_id = routine_runs::start(&self.pool, routine.id).await.ok();
let res: Result<(), String> = match team_id {
Some(tid) => match teams::get_team(&self.pool, tid, agent.workspace_id).await {
Ok(team) => topology_runs::enqueue_run(
&self.pool,
uuid::Uuid::now_v7(),
agent.workspace_id,
task,
&team.graph,
)
.await
.map_err(|e| e.to_string()),
Err(e) => Err(e.to_string()),
},
None => Err("routine topology action missing team_id".to_string()),
};
if let Some(rid) = run_id {
let (status, err) = match &res {
Ok(_) => ("ok", None),
Err(e) => ("error", Some(e.clone())),
};
let _ = routine_runs::finish(&self.pool, rid, status, err.as_deref()).await;
}
continue;
}
let message = routine.action["message"].as_str().unwrap_or_default();
if message.is_empty() {
continue;
}
// Each routine runs in one dedicated, recognizable session.
let title = format!("⏰ {}", routine.name);
let session = match sessions::list_by_agent(&self.pool, agent_id)
.await?
.into_iter()
.find(|s| s.title == title)
{
Some(existing) => existing,
None => sessions::create(&self.pool, agent_id, agent.workspace_id, &title).await?,
};
// Journal the firing for the dashboard routines panel.
let run_id = routine_runs::start(&self.pool, routine.id).await.ok();
let res = self.runtime.send_message(session.id, message).await;
if let Some(rid) = run_id {
let (status, err) = match &res {
Ok(_) => ("ok", None),
Err(e) => ("error", Some(format!("{e}"))),
};
let _ = routine_runs::finish(&self.pool, rid, status, err.as_deref()).await;
}
}
Ok(due.len())
}
/// The production loop: ticks on an interval with the real clock.
pub fn spawn(self, interval: std::time::Duration) {
tokio::spawn(async move {
let mut tick = tokio::time::interval(interval);
loop {
tick.tick().await;
let _ = self.tick(OffsetDateTime::now_utc()).await;
}
});
}
}