@sema-agent/settings-schema 8.0.0 → 8.2.0

package/dist/fleet.js

@@ -19,6 +19,43 @@
  */
 import { z } from "zod";
 import { fnv1a64 } from "./hash.js";
+// ── The center's fleet endpoints (paths, one spelling) ─────────────────────────────────────────────────────
+/**
+ * The center's `/api/fleet/*` endpoints that are addressed from outside the center, relative to its origin. ONE spelling: whoever
+ * calls one (the engine, the executor) and whoever serves or routes it (the center, the deployment's Service / Ingress) imports it
+ * here — nobody writes the string. Membership rule: an endpoint is here iff this package types its body, or it belongs to the
+ * liveness group ({@link FLEET_LIVE_PATHS}); a center-internal route is not.
+ *  - `instances` — `POST` = the heartbeat ({@link InstanceAnnouncement}; its 2xx reply carries the center's
+ *    {@link CenterCapabilities} under {@link HEARTBEAT_REPLY_CAPABILITIES_KEY}), `DELETE` = the goodbye ({@link InstanceDeregistration}).
+ *  - `usage` — `POST` a {@link UsageReport}.
+ *  - `quotaLeases` — the quota lease ({@link QuotaLease}).
+ *  - `servingLease` — `POST` a {@link ServingLeaseRequest}, answered with a {@link ServingLeaseResponse}.
+ *  - `hostPlanner` — `GET` one host's planner record, for the executor (its body is the center's and the executor's contract, not
+ *    this package's; it is here because the deployment routes it as a member of the liveness group).
+ * Notation: a value is a path TEMPLATE — a parameter is a whole segment written `{name}` (`hostPlanner` ends in `/{host}`, filled
+ * with the URL-encoded host id); the other values have none and are the path itself. A prefix router (an Ingress rule) takes the
+ * template up to its first `{`.
+ */
+export const FLEET_PATHS = {
+    instances: "/api/fleet/instances",
+    usage: "/api/fleet/usage",
+    quotaLeases: "/api/fleet/leases",
+    servingLease: "/api/fleet/live/serving-lease",
+    hostPlanner: "/api/fleet/live/host-planner/{host}",
+};
+/**
+ * The LIVENESS group — the fleet endpoints a center answers without its readiness gate and without its config-governance gates
+ * (they read no config domain and take service credentials only), so that a center whose management face is refused never turns
+ * into a fleet that gets no answers. A deployment routes exactly these past the readiness gate (on Kubernetes: a second Service
+ * with `publishNotReadyAddresses`, and the Ingress rules for them point at it). Membership is THIS list, not a path prefix — the
+ * heartbeat predates the `/api/fleet/live/` prefix; every {@link FLEET_PATHS} entry under that prefix is a member. The
+ * quota-lease and usage endpoints are not.
+ *
+ * The same two constants ship as JSON for tooling that cannot import TypeScript (a Helm chart, a smoke script): the subpath
+ * `@sema-agent/settings-schema/fleet-paths.json` is `{ "FLEET_PATHS": …, "FLEET_LIVE_PATHS": … }`, written from these values at
+ * build time — never edited by hand.
+ */
+export const FLEET_LIVE_PATHS = [FLEET_PATHS.instances, FLEET_PATHS.servingLease, FLEET_PATHS.hostPlanner];
 // ── Domain 1: drain protocol (graceful rolling update — the ground every form stands on) ──────────────────
 /** Lifecycle of a draining instance. `running`→`draining` on the stop signal; `drained` once in-flight hits
  *  zero (clean) or the grace deadline forces the issue. Exit always follows `drained`. */
@@ -40,13 +77,60 @@ export function drainVerdict(s) {
     const grace = Math.max(DRAIN_GRACE_FLOOR_MS, s.graceMs);
     return s.nowMs - s.startedMs >= grace ? "exit_forced" : "wait";
 }
+/** A wall-clock instant as epoch milliseconds — one quantity, one rule, wherever the fleet contract carries a point in time. */
+const EpochMs = z.number().int().nonnegative();
+/**
+ * A generation is a non-negative integer written as its CANONICAL decimal string: `"0"`, `"7"`, `"10"` — no sign, no
+ * leading zero (`"07"` is not a generation), no fraction, no whitespace, ASCII digits only, and a string, never a number.
+ * One spelling per value, so equality is string equality and the order is numeric ({@link compareGeneration}) — the center's
+ * persisted generation floor and every "is this generation below the floor" judgement rest on that order. The renderer writes
+ * the value into {@link FLEET_GENERATION_ENV}; an env value that is present but not canonical is a misconfiguration to refuse
+ * loudly, not an absent generation (absence is what marks a non-member). Wherever a wire shape here carries a generation
+ * ({@link EngineSignal}`.generation`, {@link ServingLeaseRequest}, {@link DrainRequest}`.expectedGeneration`) it is judged by
+ * this one predicate.
+ */
+const CANONICAL_GENERATION = /^(?:0|[1-9][0-9]*)$/;
+export function isCanonicalGeneration(value) {
+    return typeof value === "string" && CANONICAL_GENERATION.test(value);
+}
+/** Numeric order of two canonical generations: `-1` when `a` is older than `b`, `0` when equal, `1` when newer — `"9"` is
+ *  older than `"10"`; any number of digits. Throws a `TypeError` on an input that is not canonical (a comparison that quietly
+ *  returned some number would be a fence decision made on garbage); judge untrusted input with {@link isCanonicalGeneration}
+ *  first — the wire shapes of this file already do. */
+export function compareGeneration(a, b) {
+    if (!isCanonicalGeneration(a) || !isCanonicalGeneration(b)) {
+        throw new TypeError(`compareGeneration: a generation is a canonical non-negative decimal string (got ${JSON.stringify(isCanonicalGeneration(a) ? b : a)})`);
+    }
+    if (a.length !== b.length)
+        return a.length < b.length ? -1 : 1; // canonical ⇒ no leading zeros ⇒ more digits is larger
+    return a === b ? 0 : a < b ? -1 : 1;
+}
+/** The generation field of every wire shape that carries one — a string judged by {@link isCanonicalGeneration}. */
+const Generation = z.string().refine(isCanonicalGeneration, { message: "a generation is a canonical non-negative decimal string (no sign, no leading zero)" });
+/**
+ * The serving lease as the ENGINE holds it — a CLOSED set of four words, owned here (the engine's vocabulary, word for word;
+ * a reader that switches on it exhaustively is told by the compiler when a word is added):
+ *  - `none` — the lease is not in effect: the center has not announced {@link CenterCapabilities}`.servingLease` (an older or
+ *    degraded center). The engine behaves exactly as an engine without a lease — no renewals, no fence.
+ *  - `granted` — the engine holds a lease; `leaseUntil` says until when (epoch ms, the engine's own computation from the
+ *    granted `ttlMs`, see {@link ServingLeaseResponse}).
+ *  - `expired` — the lease is in effect but no grant is valid right now (the center is unreachable, answered `unknown`, or has
+ *    not granted one yet): the engine keeps serving until its own outage allowance runs out. Not a denial.
+ *  - `denied` — the center denied this instance on positive evidence (the `denied` verdict): sticky; the engine is draining and
+ *    stops at its deadline.
+ * Only a fleet member says it: an engine without a generation has no lease and carries no `leaseState` at all (there is no
+ * fifth word for "not a member" — absence is that).
+ */
+export const LEASE_STATES = ["none", "granted", "expired", "denied"];
+export const LeaseState = z.enum(LEASE_STATES);
 /**
  * "This instance must restart to apply config" — the engine's OWN observation (S-741), defined ONCE for both exits that
  * carry it: the fleet heartbeat ({@link InstanceAnnouncement}`.restart`, typed) and GET /health (`restart`, read through
  * {@link readRestartSignal} — {@link InstanceHealth} keeps carrying it untyped, see there). One mint point, two exits —
  * never a second judgement.
  *
- * Shape = what the server already ships on /health (`restart: { reasons, version, since }`). PRESENCE is the signal:
+ * Shape = what the server already ships on /health (`restart: { reasons, version, since }`, plus the optional `withheld`
+ * qualifier below). PRESENCE is the signal:
  * present ⇔ a restart is required, absent ⇔ not; there is deliberately no `required` boolean inside (a boolean next
  * to presence is redundant, and two spellings of one fact drift).
  *  - `reasons` — which restart-to-apply slices differ from the value baked at boot (the vocabulary is the engine's;
@@ -55,35 +139,45 @@ export function drainVerdict(s) {
  *    later publishes, so a "one restart per version" dedupe bounds restarts per config version, not per reason set).
  *    Judged exactly as `readEffectiveWire` judges a config version (a finite number) — one quantity, one rule.
  *  - `since` — epoch ms when this restart first became required (stable across refreshes while `reasons` holds).
+ *  - `withheld` — optional: the ENGINE's own verdict that this beat must not be handed to a new generation ("a restart is
+ *    required, but replacing this instance right now would lose state it holds"). Absent ≡ `false` — an explicit `false`
+ *    on the wire reads the same as the key being absent, and a reader never mints the key when the producer did not send
+ *    it. It is a qualifier INSIDE the restart signal, never a signal of its own: it exists only where `restart` does.
  */
 export const RestartSignal = z.object({
     reasons: z.array(z.string().min(1)).min(1),
     version: z.number().finite(),
-    since: z.number().int().nonnegative(),
+    since: EpochMs,
+    withheld: z.boolean().optional(),
 });
 /**
- * The ONE /health reader behind every engine-owned signal ({@link readRestartSignal}, {@link readModelRefusals}): `health[key]`
- * judged against that signal's one shape. Shape mismatch, a missing key, a non-object body, even a throwing accessor ⇒
- * `undefined` — never throws (a probe must not die on one odd body).
+ * The ONE guarded body reader behind every wire-shape read in this file: the engine-owned signals on /health
+ * ({@link readRestartSignal}, {@link readModelRefusals}, {@link readEngineSignal}) and the request / reply bodies of the
+ * fleet endpoints ({@link readServingLeaseRequest}, {@link readServingLeaseResponse}, {@link readDrainRequest},
+ * {@link readDrainReceipt}). `pick(body)` — one key of the body, or the body itself — is judged against that shape's one
+ * schema. Shape mismatch, a non-object body, even a throwing accessor ⇒ `undefined` — never throws (a probe must not die
+ * on one odd body). A second hand-written guard anywhere else in this package is the defect, not a convenience.
  */
-function readHealthSignal(health, key, schema) {
+function readSignalBody(body, pick, schema) {
     try {
-        if (health === null || typeof health !== "object" || Array.isArray(health))
+        if (body === null || typeof body !== "object" || Array.isArray(body))
             return undefined;
-        const parsed = schema.safeParse(health[key]);
+        const parsed = schema.safeParse(pick(body));
         return parsed.success ? parsed.data : undefined;
     }
     catch {
         return undefined;
     }
 }
+/** `pick` for a shape whose keys sit flat on the body itself (as opposed to under one key of it). */
+const wholeBody = (body) => body;
 /**
  * The /health exit of {@link RestartSignal}: `health.restart` judged against the one shape. Shape mismatch, a missing
  * key, a non-object body, even a throwing accessor ⇒ `undefined` — never throws (a probe must not die on one odd body).
  * Presence law: only `restart` counts; the top-level `restartRequired` boolean the server also ships is not read.
  */
 export function readRestartSignal(health) {
-    return readHealthSignal(health, "restart", RestartSignal);
+    return readSignalBody(health, (h) => h.restart, RestartSignal);
 }
 /**
  * The model-refusal cause codes (S-768) — CLOSED sets, owned HERE, never a hand-copied second list. Adding a code is
@@ -177,7 +271,7 @@ const isModelPlaneRefusalCode = (c) => MODEL_PLANE_REFUSAL_CODES.includes(c);
  * at all — it answers the key only and never judges the engine's version (see {@link InstanceAnnouncement}`.modelRefusals`).
  */
 export function readModelRefusals(body) {
-    const wire = readHealthSignal(body, "modelRefusals", ModelRefusalsWire);
+    const wire = readSignalBody(body, (b) => b.modelRefusals, ModelRefusalsWire);
     if (wire === undefined)
         return undefined;
     const entries = Object.fromEntries(Object.entries(wire.entries).filter((e) => isModelEntryRefusalCode(e[1])));
@@ -205,7 +299,11 @@ export const InstanceHealth = z
     // S-768: `modelRefusals` rides the passthrough untyped for the same reason — read it with {@link readModelRefusals}.
 })
     .passthrough();
-/** Readiness = the routability predicate (k8s readiness probe, gateway health filter, shell seam switch). */
+/** Readiness = the routability predicate (k8s readiness probe, gateway health filter, shell seam switch).
+ *  Its input is the boolean-`draining` dialect of {@link InstanceHealth}. An {@link EngineSignal} types `draining` as an
+ *  object, so it does not typecheck here (on purpose: `!== true` would read an object-valued `draining` as "ready").
+ *  The next major retires the boolean pair (`draining` / `drainingSince`) and gives both this predicate and
+ *  {@link isRoutable} `EngineSignal` as their input. */
 export function isReadyForTraffic(h) {
     return h.draining !== true;
 }
@@ -219,7 +317,10 @@ export const STALE_HEARTBEAT_MULTIPLIER = 2;
 /** Register/heartbeat upsert (worker → center, D2: worker-active). ONE shape for both — registration is the
  *  first heartbeat; every heartbeat re-announces the full row (idempotent upsert, no drift between a
  *  "register" and a "renew" schema). `draining:true` is the instance SELF-removing from the routable set the
- *  moment the stop signal lands — faster than any observer. */
+ *  moment the stop signal lands — faster than any observer.
+ *  Scope: the body carries NO `scope` — this shape has no such key, and one sent anyway is stripped. The row lands in the scope
+ *  the CREDENTIAL names: under a per-worker token, the scope the token binds (a `?scope=` query parameter, when given, must equal
+ *  it); under the shared token, the `?scope=` query parameter, absent ⇒ `"global"`. */
 export const InstanceAnnouncement = z.object({
     instanceId: z.string().min(1),
     /** worker (deployment) this instance belongs to — the dispatch key */
@@ -247,6 +348,20 @@ export const InstanceAnnouncement = z.object({
      *  ABSENT (`.catch`) — it never fails the announcement, so it can never make a healthy instance unroutable (unlike
      *  `restart`, whose shape still gates the row). The key may then be present with the value `undefined`. */
     modelRefusals: ModelRefusalsWire.optional().catch(undefined),
+    /** Fleet membership and the lease reading, flat on the heartbeat body under the names and values {@link EngineSignal} gives
+     *  them (one mint point on the engine; this shape reuses that shape's schemas, not copies):
+     *  - `generation` — the canonical decimal generation ({@link isCanonicalGeneration}); present ⇔ the instance is a fleet member.
+     *  - `leaseState` — {@link LeaseState}; present ⇔ fleet member.
+     *  - `leaseUntil` — epoch ms until which the held lease runs; present ⇔ `leaseState` is `granted`.
+     *  The presence law between the three is the engine's; this shape does not judge it across keys. Every heartbeat re-announces
+     *  the full row, so a later heartbeat without a key means the engine no longer says it (the stored row is replaced, never merged).
+     *  Failure direction = meaning direction: these are evidence a center keeps, never routing input — a value that breaks its schema
+     *  drops that ONE key to ABSENT (`.catch`) and the heartbeat is still accepted, so a lease word a newer engine adds can never make
+     *  an older center refuse every heartbeat of that engine. A dropped key reads exactly like an unsaid one; the key may then be
+     *  present with the value `undefined`. */
+    generation: Generation.optional().catch(undefined),
+    leaseState: LeaseState.optional().catch(undefined),
+    leaseUntil: EpochMs.optional().catch(undefined),
 });
 /** Explicit goodbye (stop signal handler) — removes the row immediately instead of waiting out staleness. */
 export const InstanceDeregistration = z.object({
@@ -266,13 +381,272 @@ export function isInstanceStale(r, nowMs) {
     return nowMs - r.lastSeenMs > STALE_HEARTBEAT_MULTIPLIER * r.heartbeatMs;
 }
 /** Health fusion: routable ⇔ self-declared ready ∧ not draining ∧ not stale ∧ observer does not veto.
- *  Two sources merge as an AND — EITHER source's "not ready" removes the instance (fail-closed). */
+ *  Two sources merge as an AND — EITHER source's "not ready" removes the instance (fail-closed).
+ *  Its input is the stored heartbeat row (boolean `draining`); it moves to {@link EngineSignal} in the same major as
+ *  {@link isReadyForTraffic}. */
 export function isRoutable(r, nowMs) {
     return r.ready && !r.draining && r.observedReady !== false && !isInstanceStale(r, nowMs);
 }
 export function routableInstances(rs, nowMs) {
     return rs.filter((r) => isRoutable(r, nowMs));
 }
+// ── Domain 2b: the engine's own signal, the serving lease, the drain endpoint ─────────────────────────────
+/**
+ * The engine's draining fact — ONE object wherever the engine says "I am draining": inside {@link EngineSignal}`.draining`
+ * and as the body of a {@link DrainReceipt}.
+ *  - `actionId` — the action that put the engine into draining (idempotency key of the drain request).
+ *  - `since` — epoch ms when draining began; it does not move when the same action repeats.
+ *  - `deadlineAt` — epoch ms by which the engine stops on its own.
+ */
+export const EngineDraining = z.object({
+    actionId: z.string().min(1),
+    since: EpochMs,
+    deadlineAt: EpochMs,
+});
+/**
+ * Everything the ENGINE itself mints about its own state, as one object — the closed form of the engine-owned subset of the
+ * /health self-description ({@link InstanceHealth} is that self-description: an open record, `.passthrough()`, which also
+ * carries what the host adds — build, pid, port, store posture). One mint point on the engine; {@link readEngineSignal} reads
+ * this shape off a body whose keys sit flat on it (no wrapper key).
+ *
+ * Where it rides today: on NEITHER exit whole. The heartbeat ({@link InstanceAnnouncement}) and `/health` ({@link InstanceHealth})
+ * still speak the 8.0 dialect for the keys they share with this shape, in three ways:
+ *  1. `draining` is a BOOLEAN there, not the {@link EngineDraining} object. The heartbeat always carries it (`false` included);
+ *     `/health` carries `draining: true` only while draining.
+ *  2. `/health` carries `ready` only while NOT ready (`ready: false`); a ready engine's `/health` body has no `ready` key.
+ *  3. The engine writes `configTargetVersion` / `configAppliedVersion` as numbers; this shape types them as strings.
+ * So `readEngineSignal` over a heartbeat body is always `undefined` (point 1), and over a `/health` body it is `undefined` whenever
+ * any of the three applies. What does ride both exits flat, under these names and with these values: `restart`, `instanceId`
+ * and the fleet-membership keys `generation` / `leaseState` / `leaseUntil` — on the heartbeat, read them off the parsed
+ * {@link InstanceAnnouncement} (which types all five). The next major retires the boolean pair (`draining` / `drainingSince`),
+ * has both exits carry this shape whole and moves {@link isReadyForTraffic} / {@link isRoutable} onto it; until then this is
+ * the target form, and `readEngineSignal` is the reader for a body that already speaks it.
+ *
+ *  - `ready` — always said (never "absent while ready"): the engine can take new work right now.
+ *  - `draining` — present ⇔ draining ({@link EngineDraining}). NOTE the dialect: {@link InstanceHealth}`.draining` and
+ *    {@link InstanceAnnouncement}`.draining` are BOOLEANS (the 8.0 dialect, kept untouched); here it is an object. A body
+ *    whose `draining` is a boolean is therefore not an `EngineSignal` and reads as `undefined`.
+ *  - `restart` — the one {@link RestartSignal}, same schema object, no copy.
+ *  - `generation` — echo of the env the config renderer set on this instance ({@link FLEET_GENERATION_ENV}), a canonical
+ *    decimal string ({@link isCanonicalGeneration}). Absent ⇔ not a fleet member (a single-machine engine): it takes no lease
+ *    and is not fenced.
+ *  - `instanceId` — the engine's OWN process identity, minted by the engine every time the process starts (never read from
+ *    env: replicas of one Deployment share one env, and a restarted container reuses its env, so env cannot tell two
+ *    processes apart). It is present on a standalone engine too — only `generation` marks fleet membership.
+ *  - `leaseState` — the serving lease as the engine holds it ({@link LeaseState}: `none` / `granted` / `expired` / `denied`);
+ *    present ⇔ fleet member (the engine says it on every beat once it has a generation).
+ *  - `leaseUntil` — epoch ms until which the engine holds its serving lease, as the engine computed it from the last
+ *    `ttlMs` it was granted ({@link ServingLeaseResponse}); present ⇔ `leaseState` is `granted`.
+ *  - `configTargetVersion` / `configAppliedVersion` — the config-center version the engine was told to converge on, and the
+ *    one it has applied (opaque strings; equal ⇔ converged).
+ *
+ * Reading: `EngineSignal` is parsed with the default strip — a whole /health body goes in, only these keys come out. A
+ * shape violation in ANY key makes the whole signal `undefined` (it is never "the rest of it"). `undefined` means "no
+ * signal this reader can say" — an engine that predates the keys, or a malformed body — and is NEVER "ready": a caller on
+ * the routing axis treats it as not routable unless it deliberately falls back to the boolean dialect of
+ * {@link InstanceHealth}.
+ */
+export const EngineSignal = z.object({
+    ready: z.boolean(),
+    draining: EngineDraining.optional(),
+    restart: RestartSignal.optional(),
+    generation: Generation.optional(),
+    instanceId: z.string().min(1).optional(),
+    leaseState: LeaseState.optional(),
+    leaseUntil: EpochMs.optional(),
+    configTargetVersion: z.string().min(1).optional(),
+    configAppliedVersion: z.string().min(1).optional(),
+});
+/**
+ * The reader of {@link EngineSignal}: the shape's keys, flat on the given body, judged by the same guarded body reader as
+ * {@link readRestartSignal} and {@link readModelRefusals}, so the same odd input gets the same answer from all three. Shape
+ * mismatch, a missing `ready`, a non-object body, even a throwing accessor ⇒ `undefined` — never throws. See {@link EngineSignal}
+ * for what `undefined` means (not "ready") and for why today's heartbeat and `/health` bodies read as `undefined` here.
+ */
+export function readEngineSignal(health) {
+    return readSignalBody(health, wholeBody, EngineSignal);
+}
+/**
+ * The env name a fleet member's generation travels under — the config renderer sets it, the engine reads it back and echoes
+ * it as {@link EngineSignal}`.generation`. Both sides import THIS constant; neither spells the name. The value is the
+ * generation this instance belongs to (opaque string); absent from the engine's env ⇔ not a fleet member (the standalone
+ * form). There is deliberately NO env name for the instance id: an instance's identity is minted by the engine per process
+ * ({@link EngineSignal}`.instanceId`), and env cannot carry it (see there).
+ */
+export const FLEET_GENERATION_ENV = "FLEET_GENERATION";
+/**
+ * The serving lease — the ONE fence between a superseded generation and the traffic it must stop taking. A fleet-member
+ * engine renews it with the center; the center answers per the lifecycle object it holds for that instance. Three constants
+ * fix the clock, all in ms:
+ *  - {@link SERVING_LEASE_TTL_DEFAULT_MS} — the lease length when the operator sets none (10 min).
+ *  - {@link SERVING_LEASE_TTL_FLOOR_MS} — the shortest lease there is: a configured TTL below it is treated as it (1 min),
+ *    the same way {@link DRAIN_GRACE_FLOOR_MS} protects a fat-fingered grace.
+ *  - {@link SERVING_LEASE_DRIFT_MARGIN_MS} — the center's clock-skew allowance: it adds this to a lease's recorded expiry
+ *    before it counts that lease as over. It is DERIVED from {@link DEFAULT_HEARTBEAT_MS} (one cadence, one number), never a
+ *    second constant that could drift from it.
+ */
+export const SERVING_LEASE_TTL_DEFAULT_MS = 600_000;
+export const SERVING_LEASE_TTL_FLOOR_MS = 60_000;
+export const SERVING_LEASE_DRIFT_MARGIN_MS = DEFAULT_HEARTBEAT_MS;
+/**
+ * The ONE place a configured lease TTL becomes a usable one: not a number (absent, `NaN`, infinite, another type) ⇒
+ * {@link SERVING_LEASE_TTL_DEFAULT_MS}; a number below {@link SERVING_LEASE_TTL_FLOOR_MS} (zero and negatives included) ⇒ the
+ * floor; otherwise the number, truncated to whole ms, with no ceiling. It is for the ISSUING side's configuration. A reply's
+ * `ttlMs` is used exactly as granted and is never clamped upward — an engine that stretched a short grant to the floor would
+ * hold the lease past what the center recorded, which is the one thing the fence exists to prevent.
+ */
+export function clampServingLeaseTtlMs(configuredMs) {
+    if (typeof configuredMs !== "number" || !Number.isFinite(configuredMs))
+        return SERVING_LEASE_TTL_DEFAULT_MS;
+    return Math.max(SERVING_LEASE_TTL_FLOOR_MS, Math.floor(configuredMs));
+}
+/**
+ * Engine → center: "may this instance keep serving?" The identity triple names the instance exactly — a lease is never
+ * asked for by worker name alone. `generation` is the env echo ({@link FLEET_GENERATION_ENV}); `instanceId` is the engine's
+ * own per-process identity ({@link EngineSignal}`.instanceId`), so a restarted process is a NEW instance to the center.
+ * `scope` — the tenant scope the lease is asked in. A renewal is taken on a PER-WORKER token only — the credential binds
+ * (scope, worker) — so the credential decides the scope and this field can only agree: absent = the scope the token binds; present
+ * ⇒ it must equal that scope (a mismatch is refused, never rewritten either way). The shared token may not renew a lease at all
+ * (the center answers 403). Only fleet members ask: an engine without a generation (the standalone form) has no lease and sends
+ * nothing.
+ */
+export const ServingLeaseRequest = z.object({
+    worker: z.string().min(1),
+    scope: z.string().min(1).optional(),
+    generation: Generation,
+    instanceId: z.string().min(1),
+});
+/**
+ * Why a lease is refused — a CLOSED set of exactly two words, owned here:
+ *  - `superseded` — a newer generation of this worker has taken over; this instance is the old one.
+ *  - `retired` — the center has retired this instance (or the worker it belongs to).
+ * Only {@link ServingLeaseResponse}'s `denied` arm carries a reason; `unknown` has none, by shape.
+ */
+export const SERVING_LEASE_DENIED_REASONS = ["superseded", "retired"];
+export const ServingLeaseDeniedReason = z.enum(SERVING_LEASE_DENIED_REASONS);
+const ServingLeaseGranted = z.object({ verdict: z.literal("granted"), ttlMs: z.number().int().positive() });
+const ServingLeaseDenied = z.object({ verdict: z.literal("denied"), reason: ServingLeaseDeniedReason });
+const ServingLeaseUnknown = z.object({ verdict: z.literal("unknown") });
+/**
+ * Center → engine: the verdict, a CLOSED set of three words ({@link SERVING_LEASE_VERDICTS}) — the arms of one
+ * discriminated union, so a reader that switches on `verdict` is told by the compiler when a word is added.
+ *  - `granted` — keep serving; `ttlMs` is how long the lease lasts, a DURATION, never a wall-clock instant: the engine counts
+ *    it from the instant it SENT the request, on its own monotonic clock (`expiresAt = sendAt + ttlMs`), and the center keeps
+ *    its own expiry from its store time — the two sides never compare clocks, so no clock agreement is needed.
+ *  - `denied` — this instance must stop: `reason` is {@link ServingLeaseDeniedReason}. The ONLY arm that obliges an engine to
+ *    stop serving, and it is issued on POSITIVE evidence only: the center keeps, per (scope, worker), a persisted generation
+ *    floor that is never garbage-collected, and a request whose generation lies below it is `superseded`; `retired` likewise
+ *    rests on a record the center holds. A center that merely holds no such record does not deny — it answers `unknown`.
+ *  - `unknown` — the center holds no lifecycle object for this instance right now (restoring its store, migrating scopes, not
+ *    yet claimed). It says NOTHING about whether the instance should serve, so it is not a kind of `denied` and absence of the
+ *    object NEVER turns into a denial: it carries no reason, and an engine never drains on it. To the engine it is the same
+ *    case as an unreachable center.
+ * This is the law for what a center SENDS. A reader does not apply it to `reason`: {@link readServingLeaseResponse} judges by
+ * the `verdict` key and keeps a `denied` a `denied` even when its reason is outside the set ({@link ServingLeaseReading}). A
+ * reply whose `verdict` itself is outside the three words (or a `granted` with no valid `ttlMs`) is not a verdict at all and
+ * reads as `undefined` — an unreachable center, never `denied`, never `granted`.
+ */
+export const ServingLeaseResponse = z.discriminatedUnion("verdict", [ServingLeaseGranted, ServingLeaseDenied, ServingLeaseUnknown]);
+/** The reason word a READER puts in place of a `denied` reason it cannot place (outside {@link SERVING_LEASE_DENIED_REASONS},
+ *  missing, not a string). Read-face only: a producer never sends it, and the strict {@link ServingLeaseResponse} refuses it. */
+export const SERVING_LEASE_UNKNOWN_REASON = "unknown_reason";
+const isServingLeaseDeniedReason = (w) => SERVING_LEASE_DENIED_REASONS.includes(w);
+/** What a reader makes of the `denied` arm: it is judged by the `verdict` key ALONE, and `reason` is diagnostic — a reason it
+ *  can place is kept, anything else becomes {@link SERVING_LEASE_UNKNOWN_REASON}. The arm is still `denied`. */
+const ServingLeaseDeniedRead = z.object({
+    verdict: z.literal("denied"),
+    reason: z.unknown().transform((r) => (isServingLeaseDeniedReason(r) ? r : SERVING_LEASE_UNKNOWN_REASON)),
+});
+/** The read face of {@link ServingLeaseResponse} — same three arms, with the `denied` arm tolerant about `reason`. */
+const ServingLeaseReadFace = z.discriminatedUnion("verdict", [ServingLeaseGranted, ServingLeaseDeniedRead, ServingLeaseUnknown]);
+/** The verdict words as a runtime list. `satisfies` bites a word the union does not have; the converse (a union arm missing
+ *  from this list) is pinned by a test that reads the union's discriminators. */
+export const SERVING_LEASE_VERDICTS = ["granted", "denied", "unknown"];
+/** Center side: the request body of a serving-lease renewal. Shape mismatch / non-object / throwing accessor ⇒ `undefined`,
+ *  never throws (same guarded reader as every other read in this file). */
+export function readServingLeaseRequest(body) {
+    return readSignalBody(body, wholeBody, ServingLeaseRequest);
+}
+/** Engine side: the reply to a renewal, judged by its `verdict` key: `granted` needs a valid `ttlMs`, `denied` is `denied`
+ *  whatever its `reason` (see {@link ServingLeaseReading}), `unknown` is `unknown`. A non-object, a throwing accessor, a
+ *  `verdict` outside the three words or a `granted` without a valid `ttlMs` ⇒ `undefined`, never throws — and `undefined`
+ *  is read like an unreachable center, never like `denied` and never like `granted`. */
+export function readServingLeaseResponse(body) {
+    return readSignalBody(body, wholeBody, ServingLeaseReadFace);
+}
+/**
+ * What the CENTER says it can do: capability bits an engine reads before it starts using a center-side endpoint.
+ *  - `servingLease` — the center answers serving-lease renewals ({@link ServingLeaseRequest} / {@link ServingLeaseResponse}).
+ *
+ * A bit is `true` or absent — one spelling for "not supported" (there is no `false`). Absent (an older center, a body without
+ * the key, a body that cannot be read) means the center does not support the lease, and the engine then neither renews a
+ * lease nor is fenced by one: this is the compatibility gate that lets an executor ship ahead of the center without pushing
+ * running engines into lease expiry. It is a gate, not a verdict — nothing in this shape says "the center refuses leases".
+ * A reader asks `readCenterCapabilities(body)?.servingLease === true` and starts the lease client only on that.
+ * Unknown bits are stripped (a newer center's extra bits never break an older reader); a known bit whose value is not `true`
+ * makes the whole read `undefined`, which reads exactly as absent.
+ * It rides in ONE place: the heartbeat's 2xx reply ({@link FLEET_PATHS}`.instances`), under {@link HEARTBEAT_REPLY_CAPABILITIES_KEY}.
+ * The center answers the bits per CALLER CREDENTIAL: under a per-worker token, by what the center supports; under the shared token
+ * `servingLease` is always absent (the serving-lease endpoint takes per-worker tokens only, so announcing it there would only push
+ * that caller into the unreachable arm).
+ */
+export const CenterCapabilities = z.object({
+    servingLease: z.literal(true).optional(),
+});
+/**
+ * The key of the heartbeat's 2xx reply body under which the center puts its {@link CenterCapabilities} — the object's only carrier.
+ * The center writes `{ …, [HEARTBEAT_REPLY_CAPABILITIES_KEY]: caps }`; the engine reads
+ * `readCenterCapabilities(reply[HEARTBEAT_REPLY_CAPABILITIES_KEY])`, and only on a 2xx (a failed heartbeat says nothing about the
+ * bits). Nested, not flat: the reply's own keys and the capability bits never share a namespace. A reply without the key is an
+ * older center — no capability said.
+ */
+export const HEARTBEAT_REPLY_CAPABILITIES_KEY = "capabilities";
+/** Engine side: the center's capability object. Shape mismatch / non-object / throwing accessor ⇒ `undefined`, never throws
+ *  (and `undefined` means "no capability said" — the same as every bit absent). */
+export function readCenterCapabilities(body) {
+    return readSignalBody(body, wholeBody, CenterCapabilities);
+}
+/**
+ * The drain endpoint's request: "put this instance into draining, by this deadline". One persisted action, one validation,
+ * whether the center calls directly or an executor retries it. Two lanes, one shape: on the Docker lane (and for a direct
+ * call from the center) this HTTP request is how an instance is drained; on the Kubernetes lane no per-pod HTTP call is made
+ * (per-pod addressing and RBAC make it the wrong tool) — an instance is drained by its serving lease being denied
+ * ({@link ServingLeaseResponse}), after which the engine puts itself into draining.
+ *  - `actionId` — idempotency key: the same id again echoes the first answer ({@link DrainReceipt}`.state` =
+ *    `already_draining`) and changes nothing.
+ *  - the identity — `scope?` / `worker` / `expectedGeneration?` / `instanceId?` — names WHICH instance the action is for. The
+ *    engine compares it field by field against its own, absent against absent: an engine that is not a fleet member has no
+ *    generation, so a request with no `expectedGeneration` is the standalone form, not a wildcard; `instanceId`, when given,
+ *    is the engine's own per-process identity ({@link EngineSignal}`.instanceId`). A mismatch is the endpoint's refusal, not
+ *    this shape's: this schema only says what a well-formed request looks like.
+ *  - `deadlineAt` — epoch ms by which the engine stops on its own.
+ *  - `term` — the claim term the sending executor holds for this action (center-issued, opaque); absent where no executor
+ *    sits in between (a direct call, a hand-issued action).
+ */
+export const DrainRequest = z.object({
+    actionId: z.string().min(1),
+    scope: z.string().min(1).optional(),
+    worker: z.string().min(1),
+    expectedGeneration: Generation.optional(),
+    instanceId: z.string().min(1).optional(),
+    deadlineAt: EpochMs,
+    term: z.string().min(1).optional(),
+});
+/** What a drain request leaves the engine in: `draining` — this call put it into draining; `already_draining` — it already was
+ *  (the same action repeated), and the receipt reports the first call's facts. */
+export const DRAIN_RECEIPT_STATES = ["draining", "already_draining"];
+export const DrainReceiptState = z.enum(DRAIN_RECEIPT_STATES);
+/** The drain endpoint's answer: the engine's draining fact ({@link EngineDraining} — the same object {@link EngineSignal}
+ *  carries as `draining`, extended, not copied) plus how this call found the engine. */
+export const DrainReceipt = EngineDraining.extend({ state: DrainReceiptState });
+/** Engine side: the request body of the drain endpoint. Shape mismatch / non-object / throwing accessor ⇒ `undefined`, never throws. */
+export function readDrainRequest(body) {
+    return readSignalBody(body, wholeBody, DrainRequest);
+}
+/** Caller side: the drain endpoint's answer. Shape mismatch / non-object / throwing accessor ⇒ `undefined`, never throws. */
+export function readDrainReceipt(body) {
+    return readSignalBody(body, wholeBody, DrainReceipt);
+}
 // ── Domain 3: dispatch policy (traffic + failover + LB — three domains, one gateway) ──────────────────────
 export const DISPATCH_STRATEGIES = ["round-robin", "least-inflight", "consistent-hash"];
 /** Per-worker dispatch policy (center-configured; the gateway is OPTIONAL — D3: TOC/self-maintained TOB go

package/dist/issue-text.d.ts

@@ -0,0 +1,10 @@
+/**
+ * The ONE rendering of a zod issue into a sentence that may leave in a report which promises to name fields, never values (the
+ * workers migration's `refused[].reason`, the `migrate-workers` CLI report). Internal — not on any package subpath.
+ *
+ * zod's own messages name the expected shape, not the input, with one exception: the default `invalid_enum_value` message ends in
+ * `, received '<the value>'`. That issue is re-worded from its options alone (the closed set it expected); every other issue keeps
+ * its message as is. The result still goes through the usual secret redaction where the caller applies it.
+ */
+import type { z } from "zod";
+export declare function issueText(issue: z.ZodIssue): string;

package/dist/issue-text.js

@@ -0,0 +1,8 @@
+export function issueText(issue) {
+    switch (issue.code) {
+        case "invalid_enum_value":
+            return `Invalid enum value. Expected ${issue.options.map((o) => `'${String(o)}'`).join(" | ")}`;
+        default:
+            return issue.message;
+    }
+}

package/dist/migrate-workers.d.ts

@@ -21,15 +21,22 @@
  *    (无 host、无 `DB_BACKEND`、无 `tidb` 词)⇒ 不写店,旧字段 dropped。
  *  · **表达不了 ⇒ refused**:值写错了栏(密钥以字面值写在 env、坐标来自宿主密钥)、不认识的词、新旧两形并存、`DB_BACKEND=pg`
  *    配 MySQL 族坐标 —— 迁移不搬值进密钥位、不读宿主密钥、不替运维挑赢家、不换库。
- *  · **终判 = 7.0.0 schema**:迁出来的每只 worker 都过 `WorkerSpec.safeParse`;不过 ⇒ refused,拒因是 schema 自己的 issue
- *    (例:多租户 + host 车道、点了车道却缺必需坐标)。迁移不复述任何一条写闸规则。
+ *
+ * ## 终判(逐行:迁过的行与没动的行同一只)
+ * 每一只**认得出名字**的 worker —— 迁过的、没动的一样 —— 都过读侧自己的判据:**只含这一行的 workers 域**读不读得进
+ * (`WorkersConfig`,就是 `parseDomain("workers")` 用的那一只 schema)。读不进 ⇒ refused,拒因是 schema 自己的 issue(例:多租户 + host
+ * 车道、点了车道却缺必需坐标、`env` 里设了保留名、`replicas` 与 `autoscaling` 并存)。迁移不复述任何一条写闸规则,也不另抄保留名表:
+ * 判据只有读侧那一只。所以 `doc` 里每一只认得出名字的 worker 单独都读得进。
+ *
+ * 整域读侧仍是**最后围栏**,只剩两类归它:认不出名字的条目(不是对象 / 没有字符串名字 —— 迁移不判形,原样留在 `doc`)与跨行规则
+ * (名字 / 路由前缀唯一 —— 两行单独都读得进,合起来才不行,迁移不替运维挑留哪一行)。
  *
  * refused 的 worker **不进**输出 `doc`(中心不加载它、在列表标红点名 `field`;CLI 有 refused 就一字不写),但随 `refused[].original`
  * 逐字带回:`doc` ∪ `refused[].original` 覆盖输入的全部 worker,中心写回前按 `index` 放回(或另存),运维的 spec 不会随迁移消失。
  * 拒因 / dropped 只点名字段,不回显值。
  *
  * ## 幂等
- * 已迁形(没有任何旧键、该有的块都在)⇒ 原样(同一引用)返回、`changed = []`。所以再跑一次 ⇒ 零变化、`doc` 字节相等。
+ * 已迁形且逐行读得进(没有任何旧键、该有的块都在)⇒ 原样(同一引用)返回、`changed = []`。所以再跑一次 ⇒ 零变化、`doc` 字节相等。
  */
 import { type ConfigPath } from "./config-fns.js";
 /** 一个被丢掉的旧字段(引擎本就不读它 —— 通知一行,不是错误)。`field` 相对该 worker 条目;`index` = 它在输入 `workers` 里的下标。 */
@@ -38,7 +45,8 @@ export interface WorkersMigrationDrop {
     readonly index: number;
     readonly field: ConfigPath;
 }
-/** 一只迁不了的 worker(不进输出 `doc`)。`field` 指到要人改的那一格(相对该 worker 条目;终判失败时是 7.0.0 形里的路径),
+/** 一只迁不了的 worker(不进输出 `doc`)。`field` 指到要人改的那一格(相对该 worker 条目;终判拒时是读侧 schema issue 的路径 ——
+ *  迁过的行指迁出形里的格,没动的行指存下来那一行的格),
  *  `reason` 只点名字段、不回显值。`original` = 输入里那一行**逐字**(同一个值,未拷贝未改写)——
  *  🔴 **写回 `doc` 之前必须把每个 `refused[].original` 按 `index` 放回(或另存)**,否则这只 worker 的 spec 随写回从存储里消失,
  *  运维看到的是「worker 不见了」而不是「worker 被标红」。它是调用方自己的数据,原样带回;要记日志,按调用方记那一行的规矩记。 */