feat(coordinator): worker registry, API contract, logging & DB retry

Align the coordinator with the master PLAN.md (CTX-00, CTX-04) and harden
process startup.

- CTX-00: freeze docs/api-contract.md as the v1 source of truth for the
  Go coordinator and Python worker.
- CTX-04: worker registry — workers table (migration 0002), domain.Worker,
  RegisterWorker use case, WorkerRepository, and POST /workers/register.
- Contract alignment: claim uses `capabilities` (was `workloads`),
  COORDINATOR_TOKEN env (WORKER_AUTH_TOKEN kept as fallback), and
  GET /health now reports database readiness (503 when the DB is down).
- Logging: logs are teed to stdout and an optional rotated file (LOG_FILE)
  via lumberjack, so they survive a container rebuild.
- Startup resilience: the initial DB connection is retried with backoff,
  so the coordinator waits for Postgres to boot instead of crash-looping.
This commit is contained in:
Efremenko Arhip
2026-07-23 13:45:31 +03:00
parent 5d6390fd98
commit dc92121acc
25 changed files with 635 additions and 66 deletions
+5
View File
@@ -21,6 +21,11 @@ type ChunkInput struct {
MaxAttempts int
}
type RegisterWorkerInput struct {
Name string
Capabilities []string
}
type ClaimTaskInput struct {
WorkerID string
Workloads []string
+6
View File
@@ -62,6 +62,12 @@ type JobRepository interface {
UpdateStatus(ctx context.Context, id uuid.UUID, status domain.JobStatus, completedAt *time.Time) error
}
// WorkerRepository persists the worker registry.
type WorkerRepository interface {
Insert(ctx context.Context, w *domain.Worker) error
Get(ctx context.Context, id uuid.UUID) (*domain.Worker, error)
}
// TxManager runs a function inside one database transaction. The transaction
// travels in the context, so repositories pick it up without this port ever
// mentioning pgx.
+28
View File
@@ -0,0 +1,28 @@
package usecase
import (
"context"
"github.com/emil28092005/SciMesh/coordinator/internal/domain"
)
// RegisterWorker records a worker in the registry and hands back its identity.
type RegisterWorker struct {
workers WorkerRepository
clk Clock
}
func NewRegisterWorker(workers WorkerRepository, clk Clock) *RegisterWorker {
return &RegisterWorker{workers: workers, clk: clk}
}
func (uc *RegisterWorker) Execute(ctx context.Context, in RegisterWorkerInput) (*domain.Worker, error) {
w, err := domain.NewWorker(in.Name, in.Capabilities, uc.clk.Now())
if err != nil {
return nil, err
}
if err := uc.workers.Insert(ctx, w); err != nil {
return nil, err
}
return w, nil
}