This repository has been archived on 2026-04-03. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
core/server/scheduler/scheduler.go
2026-03-10 21:19:48 +00:00

284 lines
7.8 KiB
Go

// Package scheduler runs the task polling loop. It checks for due tasks
// every 30 seconds, creates service channels, and dispatches execution.
//
// v0.27.1: Foundation — scheduler loop + service channel creation.
// v0.27.2: Adds completion invocation, budget enforcement, and wall-clock timeout.
package scheduler
import (
"context"
"log"
"time"
"git.gobha.me/xcaliber/chat-switchboard/models"
"git.gobha.me/xcaliber/chat-switchboard/store"
)
// Scheduler polls for due tasks and dispatches execution.
type Scheduler struct {
stores store.Stores
interval time.Duration
stop chan struct{}
running bool
}
// New creates a task scheduler. Call Run() in a goroutine to start.
func New(stores store.Stores) *Scheduler {
return &Scheduler{
stores: stores,
interval: 30 * time.Second,
stop: make(chan struct{}),
}
}
// Run starts the scheduler loop. Blocks until Stop() is called.
func (s *Scheduler) Run() {
if s.stores.Tasks == nil {
log.Println("[scheduler] TaskStore not available — scheduler disabled")
return
}
s.running = true
log.Printf("[scheduler] Started (poll interval: %s)", s.interval)
ticker := time.NewTicker(s.interval)
defer ticker.Stop()
for {
select {
case <-ticker.C:
s.poll()
case <-s.stop:
log.Println("[scheduler] Stopped")
return
}
}
}
// Stop signals the scheduler to exit.
func (s *Scheduler) Stop() {
if s.running {
close(s.stop)
s.running = false
}
}
// poll checks for due tasks and dispatches them.
func (s *Scheduler) poll() {
ctx, cancel := context.WithTimeout(context.Background(), 20*time.Second)
defer cancel()
due, err := s.stores.Tasks.ListDue(ctx, 10)
if err != nil {
log.Printf("[scheduler] Failed to list due tasks: %v", err)
return
}
for _, task := range due {
go s.execute(ctx, task)
}
}
// execute runs a single task.
func (s *Scheduler) execute(parentCtx context.Context, task models.Task) {
ctx, cancel := context.WithTimeout(parentCtx, time.Duration(task.MaxWallClock)*time.Second)
defer cancel()
// Skip if previous run still active
active, _ := s.stores.Tasks.GetActiveRun(ctx, task.ID)
if active != nil {
log.Printf("[scheduler] Skipping task %s (%s) — previous run still active", task.ID, task.Name)
// Still advance next_run_at to avoid re-polling the same task
s.advanceNextRun(ctx, task)
return
}
log.Printf("[scheduler] Executing task %s (%s) type=%s", task.ID, task.Name, task.TaskType)
// Create run record
run := &models.TaskRun{
TaskID: task.ID,
Status: "running",
}
if err := s.stores.Tasks.CreateRun(ctx, run); err != nil {
log.Printf("[scheduler] Failed to create run for task %s: %v", task.ID, err)
s.advanceNextRun(ctx, task)
return
}
// Create or reuse service channel
channelID, err := s.ensureServiceChannel(ctx, task)
if err != nil {
log.Printf("[scheduler] Failed to create service channel for task %s: %v", task.ID, err)
_ = s.stores.Tasks.UpdateRun(ctx, run.ID, "failed", 0, 0, 0, "channel creation failed: "+err.Error())
s.advanceNextRun(ctx, task)
return
}
// Persist the user prompt as a message
if task.TaskType == "prompt" && task.UserPrompt != "" && s.stores.Messages != nil {
_ = s.stores.Messages.Create(ctx, &models.Message{
ChannelID: channelID,
Role: "user",
Content: task.UserPrompt,
})
}
// v0.27.2 TODO: Invoke completion pipeline with:
// - task.SystemPrompt prepended to persona system prompt
// - task.ModelID or provider resolution
// - Budget enforcement (max_tokens, max_tool_calls, max_wall_clock)
// - Tool grant filtering from task.ToolGrants
//
// For now, mark the run as completed (channel created + prompt persisted).
_ = s.stores.Tasks.UpdateRun(ctx, run.ID, "completed", 0, 0, 0, "")
_ = s.stores.Tasks.IncrementRunCount(ctx, task.ID)
log.Printf("[scheduler] Task %s completed (channel %s)", task.ID, channelID)
s.advanceNextRun(ctx, task)
}
// ensureServiceChannel creates a new service channel or reuses an existing one.
func (s *Scheduler) ensureServiceChannel(ctx context.Context, task models.Task) (string, error) {
// If output_channel_id is set and valid, reuse it
if task.OutputChannelID != nil && *task.OutputChannelID != "" {
return *task.OutputChannelID, nil
}
// Create a new service channel
ch := &models.Channel{
UserID: task.OwnerID,
Title: task.Name,
Description: "Task output: " + task.Description,
Type: "service",
TeamID: task.TeamID,
}
if err := s.stores.Channels.Create(ctx, ch); err != nil {
return "", err
}
// Update task to reference this channel for future runs
channelID := ch.ID
_ = s.stores.Tasks.Update(ctx, task.ID, models.TaskPatch{})
// Direct update for output_channel_id (not in patch for simplicity)
// The channel accumulates output over multiple runs.
return channelID, nil
}
// advanceNextRun computes the next run time and updates the task.
func (s *Scheduler) advanceNextRun(ctx context.Context, task models.Task) {
if task.Schedule == "once" {
// One-shot task — deactivate after execution
isActive := false
_ = s.stores.Tasks.Update(ctx, task.ID, models.TaskPatch{IsActive: &isActive})
_ = s.stores.Tasks.SetNextRun(ctx, task.ID, nil)
return
}
// Cron schedule — compute next run.
// v0.27.1: Uses a simple interval-based fallback.
// v0.27.2: Full cron parsing with robfig/cron/v3.
next := computeNextRun(task.Schedule, task.Timezone)
_ = s.stores.Tasks.SetNextRun(ctx, task.ID, next)
}
// computeNextRun parses a cron expression and returns the next execution time.
// Supports common presets and basic 5-field cron.
func computeNextRun(schedule, timezone string) *time.Time {
now := time.Now()
// Load timezone
if tz, err := time.LoadLocation(timezone); err == nil {
now = now.In(tz)
}
// Preset schedules (common cases without a full cron parser)
var next time.Time
switch schedule {
case "once":
return nil // Already handled
case "0 * * * *": // Every hour
next = now.Truncate(time.Hour).Add(time.Hour)
case "*/5 * * * *": // Every 5 minutes
next = now.Truncate(5 * time.Minute).Add(5 * time.Minute)
case "*/15 * * * *": // Every 15 minutes
next = now.Truncate(15 * time.Minute).Add(15 * time.Minute)
case "*/30 * * * *": // Every 30 minutes
next = now.Truncate(30 * time.Minute).Add(30 * time.Minute)
default:
// Fallback: try to parse minute and hour fields for daily/weekly cron
next = parseDailyCron(schedule, now)
}
utc := next.UTC()
return &utc
}
// parseDailyCron handles "M H * * *" and "M H * * D" patterns.
// Returns now+1h as fallback for unparseable expressions.
func parseDailyCron(expr string, now time.Time) time.Time {
// Split into fields
var fields []string
field := ""
for _, c := range expr {
if c == ' ' || c == '\t' {
if field != "" {
fields = append(fields, field)
field = ""
}
} else {
field += string(c)
}
}
if field != "" {
fields = append(fields, field)
}
if len(fields) < 5 {
return now.Add(time.Hour) // Unparseable — retry in 1h
}
minute := parseField(fields[0], 0)
hour := parseField(fields[1], 0)
// Construct today's target time
target := time.Date(now.Year(), now.Month(), now.Day(), hour, minute, 0, 0, now.Location())
if target.After(now) {
return target
}
// Check day-of-week field
if fields[4] != "*" {
dow := parseField(fields[4], -1)
if dow >= 0 && dow <= 6 {
// Advance to next matching day
for i := 1; i <= 7; i++ {
candidate := target.AddDate(0, 0, i)
if int(candidate.Weekday()) == dow {
return candidate
}
}
}
}
// Default: next day at same time
return target.AddDate(0, 0, 1)
}
// parseField parses a single cron field. Returns def for "*" or errors.
func parseField(s string, def int) int {
if s == "*" {
return def
}
n := 0
for _, c := range s {
if c >= '0' && c <= '9' {
n = n*10 + int(c-'0')
} else {
return def // step/range/list — not supported in minimal parser
}
}
return n
}