@ultimat3/jobs 24.0.0 → 25.1.0

package/CLAUDE.md

@@ -47,7 +47,7 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
 - **`SQL_JOBS_TABLE` is the ONE install point** for every durable table (`x_jobs`, `x_job_*`, `x_backfills`,
   `x_outbox`, `x_scheduler_*`). A NEW table is also a name in
   `packages/cli/src/framework-schema.ts`. A shipped table grows by `alter table ... add column if
-  not exists`. Its comments carry NO apostrophes and NO semicolons (`dev-queue.ts` splits on `;`; `driver-pg-sql.test.ts` checks
+  not exists`. Its comments carry NO apostrophes and NO semicolons (it splits on `;`; `driver-pg-sql.test.ts` checks
   quote parity).
 - **`claim({ queues: [] })` is REFUSED by every driver** (`assertClaimQueues`,
   `X_JOB_CLAIM_QUEUES_EMPTY`); the memory driver's reads are `async` so a refusal rejects on both.
@@ -67,13 +67,13 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
 - Drivers implement the six `JobDriver` methods plus optional `introspect`, `backfills`, `leases`. New
   capabilities go behind the interface. `inspect.ts` returns plain JSON for CLI, `/_x` and MCP.
 - Step results are persisted BEFORE the step returns. All time is epoch ms (`nowMs()`, `clock.ts`).
-- **`createPgLeader` is correct only on a DEDICATED connection**; boot uses `createPgLeaseLeader`.
+- **`postgresLeader` is correct only on a DEDICATED connection**; boot uses `postgresLeaseLeader`.
 
 ## Rules — numbers and limits
 
 - **Every numeric knob is refused when not FINITE** — core's `finiteOption()` (a bound) and
-  `finiteCount()` (a count, caller's minimum); `worker-options.ts` is where `createWorker` reads them.
-  **`bun run finite-bounds` is a floor, never proof**: `createLimiter`'s five numbers are screened
+  `finiteCount()` (a count, caller's minimum); `worker-options.ts` is where `jobWorker` reads them.
+  **`bun run finite-bounds` is a floor, never proof**: `concurrencyLimiter`'s five numbers are screened
   with min 0 (zero is a HARD STOP). **A row count is `finiteCount` (min 0)**; `retry.attempts` is one with min 1.
 - **`WorkerOptions.concurrency` is read by OWN key** — a queue named `constructor`
   (`worker-slots.test.ts`).
@@ -98,16 +98,14 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
 - The scheduler's key is occurrence-scoped (`task:occurrenceMs:jobKey`); `task.enqueue()` uses the
   job's plain key.
 - **TWO shutdown hooks per worker, one per PHASE**: `accept` is `stopAccepting()` (flip state, clear
-  the poll timer, abort held runs); `close` is the teardown. `stop()` hands both back in a `finally`;
+  the poll timer, arm the drain cut-off — it aborts nothing); `close` is the teardown. `stop()` hands both back in a `finally`;
   `start()` refuses while draining.
-- **A claimed job is counted with core's `beginWork()`**, so the drain's in-flight phase does the
-  waiting. **The teardown's wait is bounded on SIGTERM** (`settleAllBy` in `drain-wait.ts`,
-  `jobs.worker.drain-abandoned`) and unbounded on a manual `stop()`. A worker always reaches `'stopped'`;
-  `state` is set in the `finally`. **One teardown, joined.**
-- **SIGTERM reaches the job**: the worker's one `AbortController` (`drainSignal`) is composed into every
-  run (`worker-run.ts`); `stopAccepting(reason)` aborts it with `JobDrainedError` (`X_DRAINING`). A
-  drained attempt settles as **`interrupted`** (`nack`, `countsAsAttempt: false`, no park, no dead
-  letter), read off the SIGNAL. `WorkerStats.interrupted`; `worker-drain-signal.test.ts`.
+- **A claimed job is counted with core's `beginWork()`**: the drain's in-flight phase waits. The
+  teardown's wait is bounded on SIGTERM (`drain-wait.ts`), unbounded on `stop()`; one teardown, joined.
+- **A deploy lets a running job FINISH**: SIGTERM only stops claiming. `drainSignal` aborts
+  (`X_DRAINING`) at `deadlineAt − margin` (`worker-drain-cutoff.ts`), then held claims go back
+  uncounted (`worker-held.ts`). Settles **`interrupted`**; `docs/history/jobs.md`, "Drain, 2026-10".
+- **`X_RATE_LIMITED` defers uncounted** (`rateLimitDeferralMs`).
 - **The drain waits out the claim round it races** — `tick()` registers its round in `rounds`
   synchronously with its guard.
 - **A fleet slot is taken INSIDE a `try`, released AWAITED, and HELD, not owned**: `false`, or a TTL
@@ -123,7 +121,8 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
 - **The claim loop re-arms on the PASS, never the jobs**; `tick()` resolves with that pass's executions.
 - **A deadline CANCELS, then fails the attempt**, never the reverse (`raceTimeout`, `withStepTimeout`);
   the attempt is cancelled in `executeJob`'s `finally`.
-- **A cancelled runner writes NOTHING** — `put()` in `steps.ts` (`X_ABORTED`), and the STORE fences
+- **A cancelled runner writes NOTHING** — `put()` in `steps.ts` (`X_ABORTED`) — save a fenced
+  `X_DRAINING` on a live attempt: a step done in the drain is recorded once. The STORE fences
   the claim (`StepFence`, `SQL_STEP_PUT` as `SQL_ACK`: `X_JOB_LEASE_LOST`). `executeJob` passes it.
 - **`traceparent` is stamped at ENQUEUE time, in `outbox.ts`**, and an empty `spanId` sends none.
 - **The scheduler runs one dispatch round at a time**; every other `tick()` joins it; `stop()` waits it
@@ -140,8 +139,8 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
 - **Suspension is control flow, and a SHED is not a suspension**: `StepSuspension` →
   `nack({ countsAsAttempt: false, park: true })`; a shed is `countsAsAttempt: false` without `park`,
   stays `ready`, logs `jobs.worker.shed` (no `last_error`). `driver-parity.test.ts`.
-- **A run's acquisitions are handed back even when the wiring throws** (`worker-run.ts`: `context()`
-  above the heartbeat; `createRunSignal` and `fleetSlots.startRenewal` inside the `try`).
+- **A wiring throw hands back the run's holdings, and its ROW until `executeJob` starts**
+  (`worker-run.ts`), as a failed shed does its job (`worker-admit.ts`).
 - **`step.run` hydrates the run's steps from ONE `store.list(runId)`**; `sleep` and `waitForEvent`
   record replays through `trace()`. **`claimName` reads a Set**; `usedNames()` keeps
   `MAX_TRACE_NAMES` (200).
@@ -155,9 +154,8 @@ Tier 3. The `job` + `task` primitives, durable steps, transactional outbox, queu
   suite (memory + real pg).
 - **A settle answers whether it landed**; a miss is `jobs.settle.unowned`, not a throw.
 - **The counter moves in the SETTLING statement** (`driver-pg-settle-sql.ts`): one-minute bucket per
-  job name; `nackOutcome()` decides what a nack adds (a shed, a suspension, a drain: nothing), and
-  `ack({ counted: false })` — `x jobs drain` — adds nothing. The scheduler leader folds tiers
-  (`rollupCounters`), at most once a bucket.
+  job name; `nackOutcome()` decides what a nack adds (a shed, a suspension, a drain: nothing).
+  The scheduler leader folds tiers (`rollupCounters`), at most once a bucket.
 - **`list()` is KEYSET** (`after: jobCursor(lastRow)`, newest first by `(created_at, id)`); the pg
   seek reads the cursor row's own `created_at` — the cursor's ms is rounded. A page past
   `MAX_JOB_PAGE` or a foreign cursor is `X_JOB_PAGE_INVALID`, never a bare invariant.
@@ -197,7 +195,7 @@ Long form: `docs/history/jobs.md`, "the cross-process wake".
 - **`idle-cost.test.ts` / `queue-wake.test.ts` count statements per idle minute** — scheduler 6,
   worker and relay 30 with no wake, 12 with. Raising one is a regression.
 - **The memory driver stores a payload's JSON form**, as pg binds it (`driver-settle-parity.test.ts`).
-- **The event bus has ONE clock**: `createPgEventBus` takes no `clock`; `EventLookup.now()` is
+- **The event bus has ONE clock**: `postgresEventBus` takes no `clock`; `EventLookup.now()` is
   REQUIRED, stamps a NEW wait, and calls the TIMEOUT (asked once the runner thinks time is up).
   `purgeExpired()` is awaited and counted; `eventsPurgeTarget(bus)` is its `PurgeTarget`.
 
@@ -228,8 +226,9 @@ Long form: [`docs/history/jobs.md`](../../docs/history/jobs.md), "Moved 2026-10-
 - **`purge()`** is the one caller of every `purgeExpired()`: one table per `step.run`, one clock
   reading per pass, duplicate names refused.
 - **`exportRows()`**: one object per PAGE, named by page index; NO cross-tenant escape.
-- **`webhook()`** delivers ONE event to ONE endpoint; no steps; every attempt recorded before the
-  throw. **The wire format is core's**, re-exported.
+- **`webhook()`**: ONE event to ONE endpoint, no steps; each attempt but a CANCELLED one recorded
+  before the throw; `ledger.isDisabled` gates the socket. **The wire format is core's.** An org
+  tenant reads `orgId` OFF THE INPUT; none, or not the run's org: TERMINAL `X_JOB_TENANT_MISMATCH`.
 - A `-fixture.ts` file does not ship; `backfill-pass-fixture.ts` raises a plain `Error` subclass on
   purpose (it stands in for app code).
 
@@ -255,28 +254,28 @@ Long form: [`docs/history/jobs.md`](../../docs/history/jobs.md), "Moved 2026-10-
 | `steps-timeout.ts` / `steps-suspension.ts` | a step's ceiling; `StepSuspension` and the timed-out marker |
 | `outbox.ts` | staging in a `Tx`, the store seam, the ambient `JobsFacade` slot |
 | `outbox-relay.ts` | the relay: the poll timer, one pass, and its TWO shutdown hooks |
-| `outbox-pg.ts` | `createPgOutboxStore` — `stage()` on the caller's OWN connection, claim on the pool |
+| `outbox-pg.ts` | `postgresOutboxStore` — `stage()` on the caller's OWN connection, claim on the pool |
 | `outbox-lease.ts` | the claim lease's one definition and its one normalisation, for both stores |
 | `leases.ts` | `LeaseStore` — fleet-wide slots, the memory one, `jobLeaseKey` |
 | `concurrency.ts` | `job.concurrency` as declared, resolved once: `KeyedConcurrency`, `WhenBusy`, the declaration and key refusals |
 | `errors-concurrency.ts` | every concurrency refusal's class; codes stay in `errors.ts` |
 | `worker-key-busy.ts` | one run refused by its key: settled `failed`, body never run |
 | `metrics.ts` | `queue_oldest_ready_seconds` and `queue_dead_jobs`, the two alertable gauges |
-| `scheduler-pg.ts` | `pgSchedulerState` (the durable watermark, the atomic fire) + `createPgLeaseLeader` |
-| `events-pg.ts` | `createPgEventBus` — `step.waitForEvent` across processes |
+| `scheduler-pg.ts` | `postgresSchedulerState` (the durable watermark, the atomic fire) + `postgresLeaseLeader` |
+| `events-pg.ts` | `postgresEventBus` — `step.waitForEvent` across processes |
 | `driver.ts` | `JobDriver` contract + wire records |
-| `driver-pg.ts` | default driver, and `createPgLeader` |
+| `driver-pg.ts` | default driver, and `postgresLeader` |
 | `driver-pg-ddl.ts` | `SQL_JOBS_TABLE` — the ONE install point. Its comments carry no `;` and no `'` |
 | `driver-pg-jobs-sql.ts` | every statement returning a whole `x_jobs` row, and `JOB_ROW_COLUMNS`; re-exported from `driver-pg-sql.ts` |
 | `driver-pg-rows.ts` | a Postgres row → a wire record: `JobRow`/`StepRow`/`BackfillRow` and their mappings |
 | `driver-memory.ts` / `claim-exhausted.ts` | `x dev` / tests; a buried row's log line and `onSettled` |
-| `driver-redis.ts`, `driver-nats.ts` | honest `X_NOT_IMPLEMENTED` stubs |
 | `retry.ts` | the dead-letter decision, and this package's option names over core's `backoffDelay` — no curve of its own |
 | `retry-classification.ts` | the other half: what the thrown error says, and the stop reason |
 | `execute.ts` / `run-deadline.ts` | `executeJob` — one claimed job run and settled; the run's deadline: cancel, then fail |
 | `heartbeat.ts` | one claimed job's lease: the renewal interval and the loss it reports |
 | `renewal-timer.ts` | the renewal interval and its `stopped()` latch |
 | `worker.ts` | `worker` role, claim round, drain |
+| `worker-drain-cutoff.ts` / `worker-held.ts` / `worker-tally.ts` | drain cut-off · held claims · counters |
 | `worker-admit.ts` | may this claimed job start: the limiter, the fleet slot, and the shed / refusal |
 | `worker-registry.ts` | one worker's registry row: announce, heartbeat, forget |
 | `worker-types.ts` | the worker's public contract: `WorkerOptions`, `WorkerStats`, `Worker` |
@@ -303,6 +302,7 @@ Long form: [`docs/history/jobs.md`](../../docs/history/jobs.md), "Moved 2026-10-
 | `worker-loop.ts` | the claim loop's timer: wake, `again`, the kicks |
 | `driver-pg-outbox-sql.ts` | the `x_outbox` statements |
 | `errors-operator.ts` / `errors-requeue.ts` | the operator verbs' refusals; `requeue`'s |
+| `errors-tenant.ts` | `JobTenantMismatchError` |
 
 Which `-fixture.ts` harness each suite shares, and what each `.job.` suite proves:
 `docs/history/jobs.md`, "Moved 2026-10-01 — test harnesses".

package/README.md

@@ -192,7 +192,7 @@ input. The tenant is a fact about the work, so the job declares it.
 expires, so on a bus shared by one `bun test` process an answer one test published resumes the
 next test's wait — call it between tests.
 
-The event bus has ONE clock. `createPgEventBus({ executor })` stamps `publishedAt` and the expiry
+The event bus has ONE clock. `postgresEventBus({ executor })` stamps `publishedAt` and the expiry
 with the database's `now()` — it takes no `clock` — and `bus.now()` answers that same clock. A
 consumer that wants "published after I asked" (`@ultimat3/scraping`'s `eventPrompt`) reads its
 "asked at" from `bus.now()`, never from its own process: a skew between two pods must not decide
@@ -502,13 +502,17 @@ subscription table, one `enqueue` per endpoint.
 import { memoryWebhookLedger, webhook } from '@ultimat3/jobs';
 
 declare const db: {
-  endpoints: { byId(id: string): Promise<{ id: string; url: string; secret: string } | null> };
+  endpoints: {
+    byId(id: string): Promise<{ id: string; orgId: string; url: string; secret: string } | null>;
+  };
   events: { byId(id: string): Promise<{ topic: string; body: string } | null> };
 };
 
 export const deliver = webhook({
   name: 'partner.webhooks',
-  tenant: 'none',
+  // The org that owns the endpoint, carried on every enqueue — or `tenant: 'none'` for endpoints
+  // no tenant owns. `tenant` is synchronous over the input, so the org rides beside the two ids.
+  tenant: ({ orgId }) => orgId,
   // Read once per ATTEMPT and never checkpointed: the endpoint carries a secret, and a step's
   // output is written to `x_job_steps`.
   endpoint: ({ endpointId }) => db.endpoints.byId(endpointId),
@@ -518,11 +522,11 @@ export const deliver = webhook({
 });
 
 // The fan-out is yours, because the subscription table is yours.
-declare function subscribersOf(topic: string): Promise<readonly { id: string }[]>;
+declare function subscribersOf(topic: string): Promise<readonly { id: string; orgId: string }[]>;
 declare const event: { readonly id: string };
 
 for (const endpoint of await subscribersOf('orders.paid')) {
-  await deliver.enqueue({ endpointId: endpoint.id, eventId: event.id });
+  await deliver.enqueue({ endpointId: endpoint.id, eventId: event.id, orgId: endpoint.orgId });
 }
 ```
 
@@ -537,9 +541,11 @@ x-ultimate-webhook-signature: t=1700000000,v1=<hex hmac-sha256>
 
 The receiving half is `verifyWebhookSignature(request, { secret })` in `@ultimat3/http`. The format
 itself — the canonical string, the mac and the header names — is **one module in `@ultimat3/core`**
-(`webhook-signature.ts`), re-exported by both packages and re-declared by neither: this package
-signs, `http` verifies, and neither may import the other, so the one copy lives at the tier both
-can reach. Same argument `timing-safe-equal.ts` makes for itself.
+(`webhook-signature.ts`), imported from `@ultimat3/core` by both packages and re-declared by
+neither: this package signs, `http` verifies, and neither may import the other, so the one copy
+lives at the tier both can reach. A receiver or a test imports `WEBHOOK_SIGNATURE_HEADER`,
+`webhookSignature` and the rest from `@ultimat3/core` — 25.0.0 dropped this package's
+re-exports (`X_HELPER_COPY`). Same argument `timing-safe-equal.ts` makes for itself.
 
 | Rule | Why |
 |---|---|
@@ -550,9 +556,27 @@ can reach. Same argument `timing-safe-equal.ts` makes for itself.
 | `redirect: 'manual'` | following a 3xx would re-POST a body signed for one host to whatever the receiver named |
 | the endpoint is never checkpointed | a `step.run` output lands in `x_job_steps`, and the endpoint carries the secret |
 | every attempt is recorded **before** the throw | a failure the ledger cannot see is a failure the consecutive count cannot see, which is an endpoint that never gets disabled |
-| a `Retry-After` the receiver names is honoured | `X_WEBHOOK_DELIVERY_THROTTLED` carries `meta.retryAfterSeconds`, which the nack waits out (clamped by `retry.maxDelay`) rather than guessing a curve against an answer it already has |
+| a `Retry-After` the receiver names is honoured | `X_WEBHOOK_DELIVERY_THROTTLED` carries `meta.retryAfterSeconds`, which the nack waits out — read by core's `retryAfterSecondsOf` (delta-seconds, or an HTTP-date against the response's own `Date`; `0` or a past date is unstated), clamped by `retry.maxDelay`, plus core's `jitterStatedDelay` spread so deliveries handed one instant do not wake together |
+| `WebhookLedger.isDisabled(endpointId)` is asked before every socket, beside the row's own `disabled` | `disableAfter` writes only the ledger: a verdict nobody asks for again is an endpoint that keeps receiving POSTs. Answer it from the column your `disable` sets |
+| the deadline and a lost lease abort `fetch`; a failure that abort caused writes no ledger row | the nack behind them hands the job to another worker at once, so a request left open is a duplicate delivery, and an abandoned attempt's failure would count toward `disableAfter` |
+| the DRAIN never aborts a POST already on the wire; it stops one not yet sent | torn down, the job goes to the next pod, which re-POSTs the same event on every deploy. Finished, it is recorded like any other outcome — a real failure during the drain included |
 | re-enabling is always yours | an endpoint the framework un-disabled on its own is a retry loop with no end |
 | `WebhookLedger` is a seam, not a table | retention is seven years for one business and thirty days for the next, so shipping a schema would ship one of those answers |
+| an org-owned delivery carries `orgId` on its input | `tenant` is a synchronous function of the input, so an org looked up from the endpoint id would be a read before the run has an org to read under. `tenant: ({ orgId }) => orgId` needs it on every enqueue, and both seams are handed it. A tenant that reads no `orgId` (`'none'`, or 25.0.0's `({ endpointId }) => …`) enqueues without one, as before |
+| the payload's org is the run's org, or the delivery dies | a tenant that names no org for the payload, or an `orgId` that is not the org the run is under (with `tenant: 'none'`, any `orgId`), is `X_JOB_TENANT_MISMATCH` before either seam reads — **terminal**, dead-lettered on attempt 1, because the same row is refused on every attempt and by `x jobs retry` |
+
+**Upgrading a webhook to `tenant: ({ orgId }) => orgId`.** Deliveries already queued without an
+`orgId` dead-letter on their next attempt with `X_JOB_TENANT_MISMATCH`, and a retry cannot add the
+field. Drain the queue before deploying the new declaration, or re-enqueue what dead-letters with its
+org: `x jobs ls --state dead --name partner.webhooks --json`, then `deliver.enqueue({ endpointId, eventId, orgId })` for each.
+
+**Set `timeout` below the drain budget.** A webhook has no timeout unless you declare one, and a
+POST on the wire when SIGTERM lands runs until the receiver answers. With a `timeout`, a drained
+request is still torn down at the attempt's deadline — where `executeJob` hands the job on — and
+writes no ledger row. Without one, the only bound is `configureLifecycle({ deadlineMs })`, 25 s by
+default: past it the worker logs `jobs.worker.drain-abandoned` and exits, and the row comes back
+only when its lease lapses, as a COUNTED attempt the receiver may already have processed.
+`timeout: '10s'` against the default budget ends every drained delivery inside it.
 
 ## The deadline cancels
 
@@ -670,15 +694,15 @@ things have to be true in a process:
 | Step | Call |
 |---|---|
 | the table exists | ships in `SQL_JOBS_TABLE` — applying the queue DDL is enough |
-| the facade is installed | `setJobsFacade(createJobsFacade({ store, driver }, currentTx))` |
-| the relay is running | `createOutboxRelay({ store, driver }).start()` |
+| the facade is installed | `setJobsFacade(outboxJobsFacade({ store, driver }, currentTx))` |
+| the relay is running | `outboxRelay({ store, driver }).start()` |
 
-`start()` registers the same two shutdown hooks `createWorker` does — `accept` stops polling
+`start()` registers the same two shutdown hooks `jobWorker` does — `accept` stops polling
 (the worker's also aborts every held job's `ctx.signal`), `close` waits out the pass in flight
 under the drain's deadline — and `stop()` hands both back.
 `drainOnShutdown: false` opts out, for a caller that drives its own teardown.
 
-with `store = createPgOutboxStore({ executor, txExecutor })`. `txExecutor` is what makes it
+with `store = postgresOutboxStore({ executor, txExecutor })`. `txExecutor` is what makes it
 transactional: `stage()` runs on the CALLER'S connection, never the pool. With nothing installed,
 `jobsFacade()` answers a fallback whose `currentTx` is `() => undefined` and every enqueue
 publishes straight to the driver — deliberate, so a script and a test enqueue with no wiring, but
@@ -713,7 +737,7 @@ What the lease buys, precisely:
 | a relay that died mid-batch stranding its rows forever | anything a **non-idempotent** handler does on its second run |
 | — | a lapsed visibility lease re-delivering a job that is still running |
 
-The memory store (`createMemoryOutboxStore`, `x dev` and tests) **drops** a published row —
+The memory store (`memoryOutboxStore`, `x dev` and tests) **drops** a published row —
 `retained()` is the relay's backlog, not a running total; the pg store keeps `published_at` as
 the audit trail this map is not. A relay pass that throws is logged as `jobs.outbox.tick-failed`
 and the loop re-arms: an unobserved rejection would end the process with rows still staged.
@@ -730,17 +754,21 @@ One interface: `enqueue`, `claim` (visibility timeout), `ack(jobId, { workerId,
 `backfills` and `leases`. Both settles are fenced on the CLAIM — `claimOf(claimed)` is the
 `{ workerId, claim }` a `ClaimedJob` carries — and answer whether they landed. Zero job-code change
 between them — swapping is `setJobDriver(other)`, and there is **no `jobs.driver` config line**:
-`JobsConfig.driver` has no reader and boot always builds `createPgDriver`.
+`JobsConfig.driver` has no reader and boot always builds `postgresJobDriver`.
 
 | Driver | Status | Backing | Use |
 |---|---|---|---|
 | `pg` | **default** | `SELECT ... FOR UPDATE SKIP LOCKED`, a partial unique index on `(name, coalesce(tenant_id, ''), idempotency_key)` over live rows (`x_jobs_name_tenant_idempotency_live_idx`), lease-based leader, `x_job_leases` | zero-infra start, most apps |
 | `memory` | complete | in-process maps | `x dev`, tests |
-| `redis` | interface-complete, `X_NOT_IMPLEMENTED` | Streams + consumer groups | planned |
-| `nats` | interface-complete, `X_NOT_IMPLEMENTED` | JetStream work queue | planned |
 
-The pg SQL is exported verbatim (`SQL_CLAIM`, `SQL_ENQUEUE`, `SQL_NACK`, …) so an agent
-debugging a stuck queue can read and run the exact statement.
+There is **no NATS or Redis jobs driver**: `createNatsDriver` and `createRedisDriver`, all-throw
+stubs, were deleted in 25.0.0. A real `redisJobDriver()` would arrive as a minor.
+
+The pg SQL lives verbatim in `src/driver-pg-*sql.ts` (`SQL_CLAIM`, `SQL_ENQUEUE`, `SQL_NACK`, …)
+so an agent debugging a stuck queue can read and run the exact statement. The barrel exports
+only the statement another package runs: `SQL_JOBS_TABLE` (the install) — 25.0.0 took the rest
+off, `SQL_CLAIM` and `SQL_OUTBOX_RELEASE` included (their array-parameter proofs are this package's
+`driver-pg-array.live.test.ts`).
 
 **A lease that lapses on a row's final attempt is buried by the claim.** `claim` re-takes a
 `running` row whose lease lapsed — the worker died — but one already at `attempt >= maxAttempts`
@@ -754,7 +782,7 @@ the job's `onSettled`, and the worker's claim round does exactly that. The row c
 `maxAttempts` and not the policy, so the CALLER names the jobs declaring `retry.deadLetter: false`
 (`ClaimOptions.dropExhausted` — the worker reads them off its registry): those rows are buried
 `failed` and announced `dropped`, every other one `dead` / `dead-lettered`. A caller that names
-none (`x jobs drain`) buries every such row `dead`.
+none buries every such row `dead`.
 
 A driver you write reads a nack's target state through `nackState(options)` — `dead`
 (`deadLetter`), `failed` (`fail`, terminal and out of the dead-letter queue), `suspended` (`park`)
@@ -765,8 +793,8 @@ or `ready` — so a new branch cannot land in one driver and not another. Its le
 
 | Role | Entry | Behaviour |
 |---|---|---|
-| `worker` | `createWorker({ driver, context, queues, concurrency })` | per-queue pools, lease heartbeat, SIGTERM drain: stop claiming → finish in-flight → close |
-| `scheduler` | `createScheduler({ driver, leader, state })` | one dispatch round at a time, catch-up policy, SIGTERM drain: stop dispatching → finish the round → release the lock |
+| `worker` | `jobWorker({ driver, context, queues, concurrency })` | per-queue pools, lease heartbeat, SIGTERM drain: stop claiming → finish in-flight → close. `concurrency` is a number for every queue or a table per queue; a queue it does not name gets core's `JOBS_CONCURRENCY_DEFAULT` (8 — this package's own default was 5 before 25.0.0) |
+| `scheduler` | `jobScheduler({ driver, leader, state })` | one dispatch round at a time, catch-up policy, SIGTERM drain: stop dispatching → finish the round → release the lock |
 
 Both roles register the same **pair** of hooks and bound the `close` half the same way. The
 scheduler's abandoned case differs in one respect: a round still enqueueing keeps the lease rather
@@ -798,24 +826,24 @@ update runs two leaders.
 
 ```ts
 import {
-  createPgLeaseLeader,
-  createScheduler,
+  postgresLeaseLeader,
+  jobScheduler,
   type JobDriver,
   type PgExecutor,
-  pgSchedulerState,
+  postgresSchedulerState,
 } from '@ultimat3/jobs';
 
 declare const driver: JobDriver;
 declare const executor: PgExecutor;   // see "A `PgExecutor`" below
 
-createScheduler({
+jobScheduler({
   driver,
-  state: pgSchedulerState(executor),
-  leader: createPgLeaseLeader({ executor }),
+  state: postgresSchedulerState(executor),
+  leader: postgresLeaseLeader({ executor }),
 });
 ```
 
-`createPgLeaseLeader` and not `createPgLeader`: `pg_try_advisory_lock` is scoped to a Postgres
+`postgresLeaseLeader` and not `postgresLeader`: `pg_try_advisory_lock` is scoped to a Postgres
 *session*, and the executor this package is handed is a **pool** — the lock is released the moment
 that connection goes back to it, so every node reads itself as leader. The lease is a row with an
 expiry and needs no connection affinity. `acquire()` is also the renewal, called every round, which
@@ -850,18 +878,18 @@ hourly task fire 24 catch-ups a second apart.
 
 ### A `PgExecutor`
 
-`PgExecutor` is one method — `query(text, values)` — and the boot supplies it (`@ultimat3/cli`'s
-`pgExecutorFor(client)`). Outside the boot — a test, a script — build it over `@ultimat3/db`'s
-client, which already speaks `(text, values)` and decodes `jsonb`:
+`PgExecutor` is one method — `query(text, values)` — and there is ONE builder for it:
+`@ultimat3/db`'s `dbExecutor()`, which the boot uses too (`dbExecutor(() => client)`). It resolves
+its client per statement — by default the installed one, which inside `withTransaction` is the
+transaction's own connection — and that client already speaks `(text, values)` and decodes `jsonb`.
+Outside the boot — a test, a script — hand it the client to stay on:
 
 ```ts
-import { createPostgresClient } from '@ultimat3/db';
+import { dbExecutor, postgresClient } from '@ultimat3/db';
 import type { PgExecutor } from '@ultimat3/jobs';
 
-const client = createPostgresClient({ url: 'postgres://localhost:5432/app_test' });
-export const executor: PgExecutor = {
-  query: <R>(text: string, values: readonly unknown[]) => client.query<R>({ text, values }),
-};
+const client = postgresClient({ url: 'postgres://localhost:5432/app_test' });
+export const executor: PgExecutor = dbExecutor(() => client);
 ```
 
 | Not this | Because |
@@ -886,11 +914,11 @@ A queue with nothing to do costs almost nothing, and a job starts when it is com
 `startQueueWake({ listener, executor })` holds ONE `LISTEN` session per worker pod and turns "another process committed" into the signal the idle loops already hear. The boot starts it for the `worker` role.
 
 ```ts
-import { createPostgresClient } from '@ultimat3/db';
+import { postgresClient } from '@ultimat3/db';
 import type { PgExecutor } from '@ultimat3/jobs';
 import { startQueueWake } from '@ultimat3/jobs';
 
-const client = createPostgresClient({ url: 'postgres://localhost:5432/app_test' });
+const client = postgresClient({ url: 'postgres://localhost:5432/app_test' });
 const executor: PgExecutor = {
   query: <R>(text: string, values: readonly unknown[]) => client.query<R>({ text, values }),
 };
@@ -959,7 +987,7 @@ exactly as it had before.
 | Thrown | What the queue does |
 |---|---|
 | a `terminal` code (`X_SCRAPE_AUTH_FAILED`, a validation fault, a permission denial) | dead-lettered on the attempt it happened, `attempt` recorded, remaining attempts unspent — a rotated password retried five times is five more wrong passwords at a site that locks the account after three |
-| a `retry-after` code (`X_RATE_LIMITED`, `X_OVERLOADED`) | retried at the time the responder NAMED — `meta.retryAfterSeconds`, clamped by the policy's `maxDelay` — instead of the backoff. Still an attempt, still under the ceiling |
+| a `retry-after` code (`X_RATE_LIMITED`, `X_OVERLOADED`) | retried at the time the responder NAMED — `meta.retryAfterSeconds`, clamped by the policy's `maxDelay`, plus core's `jitterStatedDelay` spread unless `jitter: false` — instead of the backoff. Still an attempt, still under the ceiling |
 | a `retryable` code (`X_TIMEOUT`, `X_DRAINING`) | the backoff schedule above, unchanged |
 | an **unclassified** code, or anything that is not an `UltimateError` | the backoff schedule above, unchanged. Most codes are unclassified and `retryFor` answers `terminal` for all of them, so reading that would have stopped every transient retry in every app |
 
@@ -990,7 +1018,7 @@ contractual rate.
 `job.concurrency` is the one that is fleet-wide, and it is enforced by a row every replica can
 see — one per held slot, keyed `job:<name>`, renewed by the same heartbeat that renews the
 visibility lease and reclaimed by TTL when a worker is SIGKILLed. A driver with no lease store
-cannot hold the cap, so `createWorker().start()` **refuses to boot**
+cannot hold the cap, so `jobWorker().start()` **refuses to boot**
 (`X_JOB_CONCURRENCY_UNENFORCEABLE`) rather than let a documented guarantee do nothing.
 
 Over any cap the claim is handed straight back without burning an attempt — one org's 50k-row
@@ -1028,7 +1056,7 @@ export const syncAccount = job({
 |---|---|---|
 | a cap of `0`, negative, fractional, `NaN` or `Infinity` — `concurrency: 0` and `limit: 0` alike; a `key` that is not a function; a `whenBusy` outside the two | where the job is declared | `X_JOB_DECLARATION_INVALID` |
 | `key(input)` answering `''`, a non-string, or more than 200 characters | at that **enqueue** — the facade and the scheduler both ask | `X_JOB_DECLARATION_INVALID` |
-| a driver with no lease store, for any `concurrency` | `createWorker().start()` | `X_JOB_CONCURRENCY_UNENFORCEABLE` |
+| a driver with no lease store, for any `concurrency` | `jobWorker().start()` | `X_JOB_CONCURRENCY_UNENFORCEABLE` |
 | a `LeaseStore` with no `holders(key)` | the build — the member is required | `TS2741` |
 
 What `'fail'` decides, exactly:
@@ -1116,7 +1144,6 @@ the pg and the memory driver alike. `x jobs`, `/_x` and a dashboard read nothing
 | the counter moves in the statement that settles the row | a count that can disagree with the rows is worse than none — and no second round trip per job |
 | a shed, a suspension and a drained attempt add nothing | they are handed back uncounted; counted, every `step.sleep` would read as a failure |
 | `ack` / `nack` / `heartbeat` / `recordProgress` are fenced on the CLAIM | `{ workerId, claim }`: a body whose lease lapsed must not settle, renew or report on the run that replaced it — claimed by another worker, or by the SAME one, whose id did not change. A miss answers `false` and logs `jobs.settle.unowned` |
-| `ack(id, { …, counted: false })` adds nothing to the counters | `x jobs drain` settles the row it moved: `done` here, and not a completed run |
 | a pause is a row the claim reads | never a column on every queued row: pausing a million-row queue takes effect within one poll |
 | an occurrence fires in one statement | the watermark and its jobs move together (`SchedulerState.fire`), so a crash between them cannot fire it twice |
 
@@ -1235,7 +1262,7 @@ FOR a user takes that user's id in its input and re-authorises it in the body.
 | `X_JOB_NOT_PROMOTABLE` | `promote` reached a job not waiting on its run time |
 | `X_JOB_PAGE_INVALID` | `list()` was asked for more than `MAX_JOB_PAGE` rows, or handed a cursor no page produced. The cause names which cursor (`after` / `before`). Fix: `x jobs ls --limit 200 --json` |
 | `X_JOB_ON_SETTLED_FAILED` | a declared `onSettled` threw on every one of its tries; logged and reported, never thrown |
-| `X_NOT_IMPLEMENTED` | redis / nats driver |
+| `X_NOT_IMPLEMENTED` | introspection or the operator surface on a driver with no `introspect` (a hand-rolled one) |
 
 ### Error classes
 
@@ -1278,6 +1305,7 @@ a job boundary the class is gone and the `code` is what survives — match on th
 | `JobRowStatusUnknownError` | `X_JOB_ROW_STATUS_UNKNOWN` | `src/errors.ts` |
 | `JobSlotLostError` | `X_JOB_SLOT_LOST` | `src/errors.ts` |
 | `JobTenantRequiredError` | `X_JOB_TENANT_REQUIRED` | `src/errors.ts` |
+| `JobTenantMismatchError` | `X_JOB_TENANT_MISMATCH` | `src/errors-tenant.ts` |
 | `JobTimeoutError` | `X_JOB_TIMEOUT` | `src/errors.ts` |
 | `LeaseLostError` | `X_JOB_LEASE_LOST` | `src/errors.ts` |
 | `OutboxNoTxError` | `X_OUTBOX_NO_TX` | `src/errors.ts` |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ultimat3/jobs",
-  "version": "24.0.0",
+  "version": "25.1.0",
   "description": "Durable background work: steps, transactional outbox, cron tasks, one driver interface",
   "license": "MIT",
   "type": "module",
@@ -25,17 +25,17 @@
     "LICENSE"
   ],
   "engines": {
-    "bun": ">=1.4.0"
+    "bun": ">=1.4.2"
   },
   "scripts": {
     "typecheck": "tsc --noEmit -p tsconfig.json",
     "test": "bun test"
   },
   "dependencies": {
-    "@ultimat3/core": "24.0.0",
-    "@ultimat3/db": "24.0.0",
-    "@ultimat3/entity": "24.0.0",
-    "@ultimat3/schema": "24.0.0",
-    "@ultimat3/time": "24.0.0"
+    "@ultimat3/core": "25.1.0",
+    "@ultimat3/db": "25.1.0",
+    "@ultimat3/entity": "25.1.0",
+    "@ultimat3/schema": "25.1.0",
+    "@ultimat3/time": "25.1.0"
   }
 }

package/src/backfill-errors.ts

@@ -5,7 +5,7 @@
 // declared in ONE place; only the classes that throw them live here, beside `backfill-ledger.ts`,
 // `backfill-pending.ts` and `backfill-registry.ts`.
 
-import { UltimateError } from '@ultimat3/core';
+import { renderFixShellArg, UltimateError } from '@ultimat3/core';
 
 /**
  * The seven backfill codes below all answer one question — "why is this sweep not running?" — and
@@ -64,7 +64,8 @@ export class BackfillEnvironmentError extends UltimateError {
       fix:
         target === undefined
           ? 'x db backfill --pending --json'
-          : `ULTIMATE_ENV=${target} x db backfill ${input.backfill} --write --json`,
+          : // Both are the declaration's own strings and the class is public: screened (sweep 1c).
+            `ULTIMATE_ENV=${renderFixShellArg(target, "'<environment>'")} x db backfill ${renderFixShellArg(input.backfill, "'<backfill>'")} --write --json`,
     });
   }
 }

package/src/backfill-ledger.ts

@@ -153,7 +153,7 @@ export function decideBackfill(
   return { run: force, previous: completed, changed: completed.checksum !== checksum };
 }
 
-export function createMemoryBackfillLedger(clock: Clock = systemClock): BackfillLedger {
+export function memoryBackfillLedger(clock: Clock = systemClock): BackfillLedger {
   const runs = new Map<string, BackfillRun>();
   const patch = (runId: string, fields: Partial<BackfillRun>): void => {
     const existing = runs.get(runId);

package/src/backfill-rate.ts

@@ -69,14 +69,14 @@ function timerSleep(ms: number, signal: AbortSignal): Promise<void> {
  * rate is a property of the table being swept and the pool it is swept through, not of whichever
  * attempt happens to hold the run.
  */
-export function createPacer(options: PacerOptions): Pacer {
+export function backfillPacer(options: PacerOptions): Pacer {
   // Refused HERE and not only at `backfill()`: `rate: 0` makes `intervalMs` Infinity, which the
   // timer clamps to about a millisecond — so an unvalidated zero reads as "no throttle at all",
   // which is the one setting this module exists to make unreachable. A negative rate is the same
   // bug with a negative wait.
   assert(
     Number.isFinite(options.rate) && options.rate > 0,
-    `createPacer({ rate: ${String(options.rate)} }) for "${options.job}" — a rate is batches per second, greater than zero`,
+    `backfillPacer({ rate: ${String(options.rate)} }) for "${options.job}" — a rate is batches per second, greater than zero`,
     `pass rate: ${DEFAULT_BACKFILL_RATE} — to sweep faster raise the number, there is no unthrottled mode`,
   );
   const clock = options.clock ?? systemClock;

package/src/backfill.ts

@@ -15,7 +15,7 @@ import type { ReadBuilder } from '@ultimat3/entity';
 import { t } from '@ultimat3/schema';
 import { backfillChecksum } from './backfill-ledger';
 import { backfillPass } from './backfill-pass';
-import { createPacer, DEFAULT_BACKFILL_RATE } from './backfill-rate';
+import { backfillPacer, DEFAULT_BACKFILL_RATE } from './backfill-rate';
 import type { BackfillCount } from './backfill-registry';
 import { stampBackfill } from './backfill-registry';
 import type { DurationInput } from './clock';
@@ -176,7 +176,7 @@ export function backfill<Row>(definition: BackfillDefinition<Row>): JobHandle<Ba
   const checksum = backfillChecksum(definition.source, definition.handle);
   // Built here rather than per attempt: the interval belongs to the table and the pool, not to
   // whichever attempt holds the run, so a retrying pass keeps the pace it was declared with.
-  const pace = createPacer({ rate, job: definition.name });
+  const pace = backfillPacer({ rate, job: definition.name });
 
   // Bound to the definition rather than passed bare: `count` is declared as a method, so a
   // reference torn off the object literal would run with `this` undefined the first time an

package/src/counters.ts

@@ -45,7 +45,7 @@ export interface MemoryCounters {
 }
 
 /** The memory driver's counters. Same buckets, same tiers, same fold as `x_job_counters`. */
-export function createMemoryCounters(): MemoryCounters {
+export function memoryCounters(): MemoryCounters {
   const buckets = new Map<string, JobCounter>();
   const keyOf = (job: string, bucketMs: number, bucketStart: number): string =>
     `${bucketMs}\u0000${bucketStart}\u0000${job}`;

package/src/driver-memory-operator.ts

@@ -7,7 +7,7 @@ import type { Clock } from '@ultimat3/core';
 import { assert, finiteOption } from '@ultimat3/core';
 import { nowMs } from './clock';
 import type { MemoryCounters } from './counters';
-import { createMemoryCounters } from './counters';
+import { memoryCounters } from './counters';
 import type { JobRecord } from './driver';
 import { REQUEUEABLE_STATES } from './driver';
 import { signalEnqueued } from './enqueue-signal';
@@ -92,9 +92,9 @@ function pauseSet(clock: Clock): {
   };
 }
 
-export function createMemoryOperator(state: MemoryQueueState): MemoryOperator {
+export function memoryOperator(state: MemoryQueueState): MemoryOperator {
   const { jobs, clock } = state;
-  const counters = createMemoryCounters();
+  const counters = memoryCounters();
   const queues = pauseSet(clock);
   const tasks = pauseSet(clock);
   const workers = new Map<string, WorkerRecord & { readonly expiresAt: number }>();