hyperhive/hive-c0re/src/dashboard/schedules.rs

301 lines
12 KiB
Rust

//! Scheduled-prompt + rebuild-queue endpoints for the dashboard.
//!
//! Operator-direct schedule CRUD (`/api/schedules` GET/POST, `{id}` PATCH,
//! `{id}/cancel` + `{id}/fire-now`) — the operator click *is* the approval,
//! so these skip the manager approval gate. Also the co-located
//! `/api/rebuild-queue/{id}/cancel` endpoint.
use axum::{
extract::{Path as AxumPath, State},
http::StatusCode,
response::{IntoResponse, Response},
};
use problem_details::ProblemDetails;
use crate::scheduled_prompts::ScheduleNotFoundOrCancelled;
use super::{AppState, error_problem, error_response};
/// `GET /api/schedules` — snapshot of every schedule for the
/// scheduled-prompts tab. Returns the wire shape directly
/// so the frontend can render without an extra translation layer.
pub(super) async fn api_schedules(State(state): State<AppState>) -> Response {
match state.coord.scheduled_prompts.list() {
Ok(rows) => {
let mut wire: Vec<hive_sh4re::WireSchedule> = rows
.into_iter()
.map(crate::socket_server::schedule_to_wire_public)
.collect();
// Drop ghost targets (agents that no longer exist) so the
// table never shows dead columns. Uses the reliable async
// roster snapshot here on the request path.
let live: std::collections::HashSet<String> = state
.coord
.containers_snapshot()
.await
.into_iter()
.map(|c| c.name)
.collect();
crate::socket_server::filter_ghost_schedule_targets(&mut wire, &live);
axum::Json(wire).into_response()
}
Err(e) => error_response(&format!("scheduled_prompts list: {e:#}")),
}
}
/// `POST /api/schedules` — operator-direct schedule creation
/// (mara: "user can add them manually"). Accepts the same
/// `SchedulePromptPayload` shape as the manager request flow but
/// skips the approval gate — the operator click *is* the
/// approval. The schedule lands directly with
/// `source = Operator` and the worker picks it up at fire time.
pub(super) async fn post_schedule_new(
State(state): State<AppState>,
axum::Json(payload): axum::Json<hive_sh4re::SchedulePromptPayload>,
) -> Result<Response, ProblemDetails> {
if payload.targets.is_empty() {
return Err(ProblemDetails::from_status_code(StatusCode::BAD_REQUEST)
.with_detail("schedule must have at least one target"));
}
if payload.body.trim().is_empty() {
return Err(ProblemDetails::from_status_code(StatusCode::BAD_REQUEST)
.with_detail("schedule body must be non-empty"));
}
if let Some(0) = payload.interval_seconds {
return Err(ProblemDetails::from_status_code(StatusCode::BAD_REQUEST)
.with_detail("interval_seconds must be > 0 (use None for one-shot)"));
}
let new = crate::scheduled_prompts::NewSchedule {
owner: hive_sh4re::OPERATOR_RECIPIENT.to_owned(),
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::Operator,
};
match state.coord.scheduled_prompts.submit(&new) {
Ok(id) => {
state.coord.emit_schedules_snapshot();
Ok(axum::Json(serde_json::json!({"id": id})).into_response())
}
Err(e) => Err(error_problem(&format!("schedule submit: {e:#}"))),
}
}
/// Optional JSON body for `fire-now`. Absent / empty body ⇒
/// `reset_timer = false` (back-compat: cadence stays intact).
#[derive(serde::Deserialize, Default)]
pub(super) struct FireNowBody {
#[serde(default)]
reset_timer: bool,
}
/// `POST /api/schedules/{id}/fire-now` — operator-initiated
/// out-of-band fire of a scheduled prompt. Runs the per-target
/// fan-out once immediately and reports per-target outcome counts.
/// One-shot schedules are consumed (cancelled) by a manual fire —
/// the operator's intent is "send this now, the scheduled time was
/// wrong." For recurring schedules the cadence stays intact unless
/// the body carries `{"reset_timer": true}`, in which case the
/// countdown is re-armed from now (`next_fire_at = now + interval`).
pub(super) async fn post_schedule_fire_now(
State(state): State<AppState>,
AxumPath(id): AxumPath<i64>,
body: Option<axum::Json<FireNowBody>>,
) -> Response {
let reset_timer = body.is_some_and(|axum::Json(b)| b.reset_timer);
match crate::scheduled_prompts_worker::fire_now(&state.coord, id, reset_timer).await {
Ok(report) => {
state.coord.emit_schedules_snapshot();
axum::Json(report).into_response()
}
Err(e) => error_response(&format!("fire schedule {id} now: {e:#}")),
}
}
/// `POST /api/rebuild-queue/{id}/cancel` — drop a still-fully-queued
/// DAG from the job queue. Refuses `Running` / terminal DAGs: an
/// in-flight node owns the agent's nix store + nixos-container update
/// lock and can't be safely interrupted from the queue side. Always
/// returns 200; the body is `{"cancelled": true}` on a successful
/// flip to Cancelled, `{"cancelled": false}` when the DAG was
/// Running / terminal / gone. On success a fresh `RebuildQueueChanged`
/// snapshot fires so the state flip surfaces live.
pub(super) async fn post_rebuild_queue_cancel(
State(state): State<AppState>,
AxumPath(id): AxumPath<u64>,
) -> Response {
if let Some(terminal) = state.coord.job_queue.cancel(id) {
// Fire the DAG's inline terminal hook (power-op intent revert / approval
// resolution) off the cancel roll-up, then surface the flip live.
crate::job_queue::exec::run_terminal_hook(&state.coord, &terminal).await;
state.coord.emit_rebuild_queue_snapshot();
axum::Json(serde_json::json!({"cancelled": true})).into_response()
} else {
axum::Json(serde_json::json!({"cancelled": false})).into_response()
}
}
#[derive(serde::Deserialize, Default)]
pub(super) struct CancelScheduleForm {
/// `None` / absent / empty array → cancel whole schedule.
#[serde(default)]
targets: Option<Vec<String>>,
}
#[derive(serde::Deserialize, Default)]
#[allow(
clippy::option_option,
reason = "double-Option carries three-state PATCH semantics on the wire \
(missing key = leave alone, JSON null = clear, value = set); \
collapsing to a single Option would lose the 'clear' state"
)]
pub(super) struct EditScheduleForm {
#[serde(default)]
body: Option<String>,
/// Double-`Option` semantics on the wire: missing key = leave
/// alone, explicit `null` = clear, value = set. serde's
/// `deserialize_with` trick to distinguish missing from null:
/// we wrap each editable field in its own helper. Simpler
/// here — keep them plain `Option<Option<_>>` and document
/// that the dashboard caller passes JSON `null` to clear.
#[serde(default, deserialize_with = "deserialize_some")]
description: Option<Option<String>>,
#[serde(default, deserialize_with = "deserialize_some")]
interval_seconds: Option<Option<u64>>,
#[serde(default)]
next_fire_at_unix: Option<i64>,
/// New targets to add. Replace-on-conflict: re-adding a
/// previously-cancelled target drops the tombstone and the
/// target starts fresh (operator intent on re-add = "this
/// target is active again, fresh start").
#[serde(default)]
targets_add: Option<Vec<String>>,
/// Targets to cancel. Same path as `cancel_targets`:
/// tombstones preserve audit and the parent schedule
/// auto-cancels when no active targets remain.
#[serde(default)]
targets_remove: Option<Vec<String>>,
}
/// serde adaptor: turns missing-key into `None`, explicit-null
/// into `Some(None)`, value into `Some(Some(v))`. Standard trick
/// for distinguishing "field absent" from "field set to null" in
/// JSON PATCH bodies.
fn deserialize_some<'de, T, D>(deserializer: D) -> Result<Option<T>, D::Error>
where
T: serde::Deserialize<'de>,
D: serde::Deserializer<'de>,
{
T::deserialize(deserializer).map(Some)
}
/// `PATCH /api/schedules/{id}` — partial update of an existing
/// schedule. Mutable fields: `body`, `description`,
/// `interval_seconds`, `next_fire_at_unix`, plus the target set
/// via `targets_add` / `targets_remove`. Both target lists
/// are applied in the same transaction as the scalar fields with
/// removes-before-adds; re-adding a previously-removed target
/// resets per-target history (fresh start); draining all targets
/// auto-cancels the parent schedule. JSON body uses missing-key
/// = "leave alone", explicit null = "clear" for `description` +
/// `interval_seconds`. Cancelled schedules are refused — submit
/// a new one instead. Returns the updated `WireSchedule` so the
/// caller's post-edit refresh has the new state inline.
pub(super) async fn patch_schedule(
State(state): State<AppState>,
AxumPath(id): AxumPath<i64>,
axum::Json(form): axum::Json<EditScheduleForm>,
) -> Response {
let patch = crate::scheduled_prompts::UpdateSchedule {
body: form.body,
description: form.description,
interval_seconds: form.interval_seconds,
next_fire_at_unix: form.next_fire_at_unix,
targets_add: form.targets_add,
targets_remove: form.targets_remove,
};
if let Err(e) = state.coord.scheduled_prompts.update(id, patch) {
return error_response(&format!("edit schedule {id}: {e:#}"));
}
match state.coord.scheduled_prompts.get(id) {
Ok(Some(s)) => {
let wire = crate::socket_server::schedule_to_wire_public(s);
state.coord.emit_schedules_snapshot();
axum::Json(wire).into_response()
}
Ok(None) => error_response(&format!("edit schedule {id}: row vanished post-update")),
Err(e) => error_response(&format!("re-read schedule {id}: {e:#}")),
}
}
/// `POST /api/schedules/{id}/pause` — pause a schedule so the worker
/// skips it until explicitly resumed. Idempotent; no-op on an already-
/// paused row. Returns 404 when the schedule is cancelled or not found.
pub(super) async fn post_schedule_pause(
State(state): State<AppState>,
AxumPath(id): AxumPath<i64>,
) -> Response {
match state.coord.scheduled_prompts.pause(id) {
Ok(()) => {
state.coord.emit_schedules_snapshot();
(StatusCode::OK, "ok").into_response()
}
Err(e) => {
if e.downcast_ref::<ScheduleNotFoundOrCancelled>().is_some() {
(StatusCode::NOT_FOUND, format!("{e}")).into_response()
} else {
error_response(&format!("pause schedule {id}: {e:#}"))
}
}
}
}
/// `POST /api/schedules/{id}/resume` — resume a paused schedule.
/// Idempotent; no-op on an already-active row. Returns 404 when the
/// schedule is cancelled or not found.
pub(super) async fn post_schedule_resume(
State(state): State<AppState>,
AxumPath(id): AxumPath<i64>,
) -> Response {
match state.coord.scheduled_prompts.resume(id) {
Ok(()) => {
state.coord.emit_schedules_snapshot();
(StatusCode::OK, "ok").into_response()
}
Err(e) => {
if e.downcast_ref::<ScheduleNotFoundOrCancelled>().is_some() {
(StatusCode::NOT_FOUND, format!("{e}")).into_response()
} else {
error_response(&format!("resume schedule {id}: {e:#}"))
}
}
}
}
/// `POST /api/schedules/{id}/cancel` — operator-side cancel
/// (whole schedule when no `targets` field, partial when one is
/// provided). Operator bypasses the topology check; the manager
/// surface enforces it for agent callers.
pub(super) async fn post_schedule_cancel(
State(state): State<AppState>,
AxumPath(id): AxumPath<i64>,
body: Option<axum::Json<CancelScheduleForm>>,
) -> Response {
let targets = body
.and_then(|axum::Json(b)| b.targets)
.filter(|t| !t.is_empty());
let result = match targets.as_deref() {
Some(list) => state.coord.scheduled_prompts.cancel_targets(id, list),
None => state.coord.scheduled_prompts.cancel_all(id),
};
match result {
Ok(()) => {
state.coord.emit_schedules_snapshot();
(StatusCode::OK, "ok").into_response()
}
Err(e) => error_response(&format!("cancel schedule {id}: {e:#}")),
}
}