feat(tasks): add coalescing queue and task lifecycle guards

- Coalescing queue: use HasPendingTaskForIssue (queued/dispatched only)
  instead of HasActiveTaskForIssue so comments during a running task
  enqueue exactly one follow-up task that picks up all new comments.
- Stale task cleanup: runtime sweeper now fails orphaned tasks when
  their runtime goes offline (daemon crash/network partition).
- Cancel-aware daemon: handleTask checks task status after execution
  and discards results if the task was cancelled mid-run (e.g. reassign).
- Terminal issue guard: ClaimTaskForRuntime auto-cancels pending tasks
  for done/cancelled issues instead of executing them.
- Race condition safety net: unique partial index ensures at most one
  pending task per issue at the DB level.
This commit is contained in:
Jiayuan 2026-03-29 17:52:35 +08:00
parent 32f795e1ef
commit b112d1f1ae
13 changed files with 148 additions and 3 deletions

View file

@ -11,6 +11,44 @@ import (
"github.com/jackc/pgx/v5/pgtype"
)
const failTasksForOfflineRuntimes = `-- name: FailTasksForOfflineRuntimes :many
UPDATE agent_task_queue
SET status = 'failed', completed_at = now(), error = 'runtime went offline'
WHERE status IN ('dispatched', 'running')
AND runtime_id IN (
SELECT id FROM agent_runtime WHERE status = 'offline'
)
RETURNING id, agent_id, issue_id
`
type FailTasksForOfflineRuntimesRow struct {
ID pgtype.UUID `json:"id"`
AgentID pgtype.UUID `json:"agent_id"`
IssueID pgtype.UUID `json:"issue_id"`
}
// Marks dispatched/running tasks as failed when their runtime is offline.
// This cleans up orphaned tasks after a daemon crash or network partition.
func (q *Queries) FailTasksForOfflineRuntimes(ctx context.Context) ([]FailTasksForOfflineRuntimesRow, error) {
rows, err := q.db.Query(ctx, failTasksForOfflineRuntimes)
if err != nil {
return nil, err
}
defer rows.Close()
items := []FailTasksForOfflineRuntimesRow{}
for rows.Next() {
var i FailTasksForOfflineRuntimesRow
if err := rows.Scan(&i.ID, &i.AgentID, &i.IssueID); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const getAgentRuntime = `-- name: GetAgentRuntime :one
SELECT id, workspace_id, daemon_id, name, runtime_mode, provider, status, device_info, metadata, last_seen_at, created_at, updated_at FROM agent_runtime
WHERE id = $1