@@ -0,0 +1,28 @@
+---
+'@objectstack/spec': minor
+---
+
+fix(spec)!: `defineConnector()` refuses a top-level key the connector does not declare, as every other connector door does
+
+Clause-②: no (narrowing)
+Metadata-protocol: narrowed
+
+<!-- adr-0087: not-required (already-registered connector-entry-undeclared-key-refused) the same narrowing as that entry, reached through one more door; its surface now names defineConnector() -->
+
+**BREAKING** accept-set narrowing on `defineConnector()` (`@objectstack/spec` and `@objectstack/spec/integration`).
+
+- **Before.** The helper parsed the open `ConnectorSchema`, so a top-level key the connector does not declare was dropped without a word. Because the helper parses first, the closed authored entry behind `defineStack({ connectors })`, `os validate` / `os compile`, the artifact load and the metadata save door never saw the key either: the one helper every documented `connectors:` entry is wrapped in was the one door that stayed silent. TypeScript's excess-property check catches the key only in an object literal, so the gap was reached through a spread, a variable or a cast.
+- **Now.** The helper parses the closed connector carrier, behind the same retired-default residue stage as `ConnectorSchema`. Such a key throws a `ZodError` naming it (`unrecognized_keys` at the root), with the message the authored entry gives: a credential-shaped key (`apiKey`, `token`, `secret`, `password`, …) meets the `auth.credentialRef` prescription, a provider setting written at the top level (`baseUrl`, `spec`, `transport`, `headers`, …) is pointed at `providerConfig`, and `timeout` / `timeoutMs` are pointed at `requestTimeoutMs`. The ADR-0010 protection envelope stays declared and a retired key's emitted default (`status: 'inactive'`) stays accepted as residue.
+- **Unchanged.** The return type (`ConnectorParsed`). `ConnectorSchema`, the def a plugin hands to `registerConnector`, keeps its open posture. The stack-only rules of an authored entry (no inline `authentication`, `providerConfig` / `auth` need a `provider`, no `actions` on a provider-bound instance) stay at the stack doors, which still apply them to the value the helper returns.
+
+## FROM → TO
+
+```ts
+// before: returned without `timeout`; the request timeout stayed the 30 s default
+defineConnector({ ...billingApi, timeout: 5000 });
+
+// after: `timeout` is refused by name and pointed at the declared key
+defineConnector({ ...billingApi, requestTimeoutMs: 5000 });
+```
+
+Move a provider setting under `providerConfig`, put a secret into the secrets layer under the name `auth.credentialRef` gives, and delete any other undeclared key. The upgrade guide entry is `connector-entry-undeclared-key-refused`.
@@ -13,7 +13,7 @@ Metadata-protocol: narrowed
 
 - **Before.** The entry was a plain object: a top-level key it does not declare parsed green and meant nothing to the runtime.
 - **Now.** The entry is closed. Such a key is refused by name with a located error (`unrecognized_keys` at the entry; at the save door `422 INVALID_METADATA`). A credential-shaped key (`apiKey`, `token`, `secret`, `password`, …) meets the `auth.credentialRef` prescription, and a provider setting written at the top level (`baseUrl`, `spec`, `transport`, `headers`, …) is pointed at `providerConfig`. The ADR-0010 protection envelope stays declared, so a package-stamped entry still parses. An artifact `os build` wrote carries no undeclared key (it serializes the parsed stack), so only a hand-assembled artifact can meet the refusal at boot.
-- **Unchanged.** `ConnectorSchema` — the def a plugin hands to `registerConnector`, and the shape `defineConnector()` parses — keeps its posture. Nothing in the runtime ever read an undeclared entry key, so no connector's behaviour moves.
+- **Unchanged.** `ConnectorSchema` — the def a plugin hands to `registerConnector` — keeps its posture. Nothing in the runtime ever read an undeclared entry key, so no connector's behaviour moves.
 - **Read half.** The built-in `connector` redactor also withholds, on every read exit that serves a stored body through the metadata-type redactor registry: the userinfo and the credential query parameters of every URL under `providerConfig` (`baseUrl`, `transport.url`, a URL `spec`, and any other URL a provider keeps at object depth), the rest of each URL served byte for byte; and an `auth` or `authentication` value that is not an object, whole. A save of the served form keeps the stored value (the metadata protocol's carry-forward), and the runtime keeps reading the unredacted execution view.
 - `redactUrlCredentialQueryParams` (`@objectstack/spec/data`) takes an optional parameter-name list; its default, and every existing caller, is unchanged.
 
 
@@ -1376,7 +1376,7 @@ rest at #5107.
 | `kernel/` | **mixed · `manifest.zod.ts` authorable, the rest wire** | ⚠️ **Split at #14192 — the flat `wire` verdict this row carried was right for the directory and wrong for one file in it, the `api/` row's finding one directory over.** `kernel/manifest.zod.ts` is `manifest:` — the hand-authored identity block of every `objectstack.config.ts`, every `os init` template, every example app, the Studio package form and the `objectstack.plugin.json` that `os plugin build` reads — and it was a plain open `z.object` under a cell that read "code-to-code". Measured first (2026-09-02 at `bd4aa4e49`, from `src` and through the built `dist`, identical readings): an unknown key parsed green and was DROPPED at all seven doors that reach `ManifestSchema` — the stack `manifest:` member (`defineStack` / `os validate` / `os compile`), `devPlugins[]`, the artifact `packages[]` entry in both its authoring and assembled forms, `os plugin build`, the `InstalledPackage` row schema, and the six package request/snapshot wire shapes that embed it. A transposed `namesapce` left `manifest.namespace` undefined at every one of them with exit 0 — and that key decides table names, REST paths and the install-time namespace gate (ADR-0129 D1–D2, ADR-0048 §3.2, ADR-0130 D1/D3). The same silent drop held one level down for `contributes` (`kind:` for `kinds:`), `contributes.kinds[]` and `engines` (`protocl:` for `protocol:`, which switches the load-time protocol handshake off). **The order the `api/` row records was kept: measurement, then the close.** No stored-row caller feeds this schema — `registry.validate('package' \| 'plugin')` has no live caller (`installPackage` stores the caller's object verbatim, `registerPlugin` is uncalled), the durable `sys_packages` row is re-registered through `registerApp` without a parse, and no bookkeeping key (`packageId` / `state` / `published*` / `package`) reaches any door — so the `peelStoredEnvelope` debt the `api/` row had to pay first does not exist here, and no bookkeeping key was taught to the authoring schema. Exactly ONE undeclared key was found at a real door, and it was DECLARED rather than curated: `main`, which `os plugin build` reads off the source `objectstack.plugin.json` to pick its entry and writes back into the compiled manifest as `dist/index.mjs`; three CLI fixtures author it, and a naked `strictObject` would have refused every plugin that names its entry — the shape this row would otherwise have recorded as refused. `ManifestSchema`, `contributes`, `contributes.kinds[]`, `engine` and `PluginEnginesSchema` are `strictObject` now: an undeclared key is a named rejection carrying the surface, the key and a rename (`namesapce` → `namespace`, `protocl` → `protocol`); the retired keys keep their `retiredKey()` tombstones (a tombstone types the key `never` and carries the upgrade text, which a bare refusal would not, and `acceptsNothing` keeps them out of the rename candidates); one curated wrong-layer pointer ships, `specVersion` (the retired CLI advisory axis — the live one is `engines.protocol`). `AssembledPackageBodySchema` (`stack.zod.ts`) inherits the closed posture through `.extend()`, so the load gate refuses an undeclared key on an assembled body too; that file's docblock sentence "NOT `strictObject`: `ManifestSchema` is an open object" is stale as of this change and is reported for its owner rather than edited here. Blast radius, measured with a strict preview before the close: 0 undeclared keys across the four example apps, the three `os init` templates, the `create-objectstack` blank template, the downstream-contract stack, the empty-kernel host and the i18n service manifest; the only shipped-block failure — `packages/cli/src/commands/create.ts`'s template manifest — fails the OPEN schema too (it lacks `id` and `type`) and is reported separately. Cloud is NOT MEASURED for this file (no checkout in the container, code search refused); if cloud parses a published `.osplugin` manifest through this schema, the compiled manifest it receives carries only declared keys (`main` and `integrity` included) by construction of `os plugin build`. The rest of `kernel/` is unchanged: plugin/kernel contracts, code-to-code |
 | `cloud/` | wire | multi-tenant runtime |
 | `ai/` | mixed | agent/tool/skill definitions authored (partially strict already); model/provider payloads wire |
-| `integration/` | **mixed · `connector.zod.ts`'s declarative entry authorable, the rest wire** | ⚠️ **Split at the connector-entry close — the flat `wire` verdict this row carried was right for the payloads and wrong for one shape, the `api/` and `kernel/` rows' finding again.** `DeclarativeConnectorEntrySchema` is the `connectors:` stack collection and the `connector` row the metadata save door keeps (`PUT /api/v1/meta/connector/:name`, bound in `UNREGISTERED_KIND_SCHEMAS`, which stores the request body for every type but `view` — ADR-0005 appendix (c), ruling B): an AUTHORED, STORED, SERVED type, not an upstream payload, yet it was a plain `z.object`, so an undeclared top-level key parsed green at every door that reads it. It is closed through a dedicated `strictObject` carrier (`DeclarativeConnectorEntryBaseSchema`) built from the same shape factory as the open one, each with its own field instances so `computeGuidanceRoutes()` never pairs the open `Connector` def with the closed declaration's `guidance`. Every door that parses the entry — `defineStack({ connectors })`, `os validate` / `os compile`, the artifact load at boot and reload, and the save door (`422 INVALID_METADATA`) — refuses the key by name, located at it; two curated families ride the refusal: credential-shaped keys → `auth.credentialRef`, provider settings → `providerConfig`. The ADR-0010 envelope was already declared on the shape (commit b5404f496), so no stamped entry is refused. Governing texts read before the close: ADR-0097, ADR-0143, ADR-0104 and the type-schema suite's #2657 fence — none keeps the authored entry open; the `ConnectorSchema is NOT .strict()` sentences across `connector.zod.ts` state the fact that made each retirement a `retiredKey()` tombstone, not a decision to stay open. ⛔ Deliberately NOT closed: `ConnectorSchema`, the def a plugin hands to `registerConnector` (code-to-code — the wire half of this row) and the shape `defineConnector()` parses, so `defineConnector({ … })` still drops an undeclared key before the entry sees it; closing that carrier is its own decision. The rest of `integration/` is unchanged: connector payloads, upstream adds fields freely |
+| `integration/` | **mixed · `connector.zod.ts`'s declarative entry authorable, the rest wire** | ⚠️ **Split at the connector-entry close — the flat `wire` verdict this row carried was right for the payloads and wrong for one shape, the `api/` and `kernel/` rows' finding again.** `DeclarativeConnectorEntrySchema` is the `connectors:` stack collection and the `connector` row the metadata save door keeps (`PUT /api/v1/meta/connector/:name`, bound in `UNREGISTERED_KIND_SCHEMAS`, which stores the request body for every type but `view` — ADR-0005 appendix (c), ruling B): an AUTHORED, STORED, SERVED type, not an upstream payload, yet it was a plain `z.object`, so an undeclared top-level key parsed green at every door that reads it. It is closed through a dedicated `strictObject` carrier (`DeclarativeConnectorEntryBaseSchema`) built from the same shape factory as the open one, each with its own field instances so `computeGuidanceRoutes()` never pairs the open `Connector` def with the closed declaration's `guidance`. Every door that parses the entry — `defineStack({ connectors })`, `os validate` / `os compile`, the artifact load at boot and reload, and the save door (`422 INVALID_METADATA`) — refuses the key by name, located at it; two curated families ride the refusal: credential-shaped keys → `auth.credentialRef`, provider settings → `providerConfig`. The ADR-0010 envelope was already declared on the shape (commit b5404f496), so no stamped entry is refused. Governing texts read before the close: ADR-0097, ADR-0143, ADR-0104 and the type-schema suite's #2657 fence — none keeps the authored entry open; the `ConnectorSchema is NOT .strict()` sentences across `connector.zod.ts` state the fact that made each retirement a `retiredKey()` tombstone, not a decision to stay open. ⛔ Deliberately NOT closed: `ConnectorSchema`, the def a plugin hands to `registerConnector` (code-to-code — the wire half of this row); closing that carrier is its own decision. `defineConnector()`, the helper an authored entry is wrapped in, used to parse it too, so the helper dropped an undeclared key before the entry saw it; it now parses the closed carrier behind the same retired-default residue stage and refuses the key with the entry's own message. The rest of `integration/` is unchanged: connector payloads, upstream adds fields freely |
 | `identity/` | mixed | position/user shapes authored (`PositionSchema` **strict as of #4001 step 2**, with the ADR-0010 envelope declared); auth payloads wire. **34 → 33 in #4641**: `identity.zod.ts` lost its `SessionSchema` site — a second, importerless declaration of a name `api/auth.zod.ts` already owned (the #4411 dual-source trap), deleted rather than reclassified |
 | `shared/` | **mixed · `protection.zod.ts` and `http.zod.ts`'s rate-limit budget authorable, the rest as written** | ⚠️ **Annotated again at #18578 — a FOURTH instance of the same shape, and this one was invisible to a sweep that went looking for it.** `shared/http.zod.ts`'s `RateLimitConfigSchema` is a building block with two mounts, and this row's rationale — *strictness decided at the consuming schema* — held for exactly one of them: `system/stack-server.zod.ts` re-postured it closed, and it did so by building `strictObject(…, RateLimitConfigSchema.shape)` **from this shape object**, so ONE declaration answered for TWO emitted defs with OPPOSITE doors. `api/endpoint.zod.ts` mounts the same schema BARE on `apis[].rateLimit` — a registered metadata type since #5312, authored through `defineStack({ apis })`, the Studio form and `PUT /meta/api/:name` — where nothing re-postures it, so the two `guidance` entries (`keyBy`, `store`) prescribed to nobody and a misspelled budget was worse: `windowSeconds: 60` parsed green and metered the 60000 ms default, a thousandfold miss reported as success. ⚠️ **The sweep that should have caught it could not.** A `CONTRACT_REVIEW_TIER` review swept this exact class with live controls (5 `.strip()` sites, 0 `z.object(XSchema.shape…)`, 0 `z.object(bareIdentifier)`) and found nothing, because the sharing runs the other way round here: it hunted an OPEN clone built from a STRICT schema's shape, and this is the STRICT one built from the OPEN one's shape — every grep shape in that sweep is blind to that direction by construction. It was found instead by driving the gate's own instrument (`computeGuidanceRoutes()` in `scripts/build-schemas.ts`) over every emitted def: match each def to its declaration, then ask the def what it actually does with the key. Census on `42f8df1723`: 1527 emitted defs, 258 resolving to exactly one declaration, 779 keys promised, **770 delivered, 9 not** — 2 of them this live silent strip, the other 7 union defs whose discriminator the probe's one-key document cannot supply (they DO deliver to an author who writes a whole document). The close moves the strictness and both tables onto the shared schema, leaving ONE declaration and ONE door for both defs: 772 delivered, 7 not. ⚠️ The residual 7 are a PROBE boundary, ⛔ not a clean zero and ⛔ not a finding. ⚠️ **Annotated at #16845 — the flat `n/a` verdict this row carried was right for the directory and wrong for one file in it, the `api/` and `kernel/` rows' finding a third time.** — the flat `n/a` verdict this row carried was right for the directory and wrong for one file in it, the `api/` and `kernel/` rows' finding a third time.** ⛔ **This directory is still UNTRIAGED and this is not a per-file row** — `shared/` has never had per-file rows, so `shared/protection.zod.ts` was **never enumerated** by this campaign; it was not deliberately accepted, because no verdict was ever taken on it. Two measurements say why the silence carried no information. **①** This row's own rationale — *strictness decided at the consuming schema* — is false for this file: all **16** `protection: ProtectionSchema` mounts across **14** files are the bare `ProtectionSchema.optional()`, not one `.extend()` / `.merge()` / `.omit()` / re-posture among them, so both the strictness and the MESSAGE are decided here in `shared/` and inherited verbatim by objects, views, dashboards, datasets, reports, apps, flows, webhooks, permissions, positions, email templates, agents, tools and skills — very nearly every authorable metadata type in the platform. A row is read as licence, which is what this ledger's own gate exists to prevent. **②** Even a per-file row would not have surfaced the defect, and this is the part worth keeping: `ProtectionSchema` has been `.strict()` since it was introduced, so it counts in the `strict` column and could never carry a remaining-strip row. **This ratchet's axis is CLOSURE; the defect was MESSAGE QUALITY** — a closed shape with no error map, refusing `lockk` with zod's bare `Unrecognized key: "lockk"`: no surface, no declared-key list, no rename, on every one of those mounts. `strictObject` at #16845 (the `PluginPermissionsSchema` conversion at #16328 one directory over is the precedent). ⛔ The population of *closed shapes still carrying zod's bare message* is **NOT MEASURED** here and is not this row's claim — #14722's rule stands that a sweep needs its own card with its own measured count. The rest of `shared/` is unchanged: utilities and building blocks whose strictness really is decided at the consuming schema |
 | `qa/` | n/a | test fixtures |