@sema-agent/sdk 16.0.1 → 16.2.0

package/openapi.yaml

@@ -414,9 +414,10 @@ paths:
         Synchronous run-to-completion. Auto `Idempotency-Key` (→ retry-safe). Supports `verify`/`cascade`.
         For anything that may take minutes or hit a HITL gate, use `/v1/runs` instead (this call blocks).
         🔴 PREPARE-TIME REFUSALS ARE TRIAGED ON WORK DONE (server >= 7.104.0 / S-271, one rule for the whole table): a
-        prepare-time refusal code that HAS a status in the server's per-code triage table (`resume_at.*`, governance codes,
+        prepare-time refusal code that HAS a status in the server's per-code triage table (`resume_at.*` — `resume_at.not_found` is 404, the rest 422 —, governance codes,
         `rewind.store_unconfigured` / `rewind.capture_disabled` / `rewind.child_scope_unsupported` / `rewind_snapshot.unresolvable`, the
-        registered `config.*` codes incl. the three roster-bound ones, `corrupt_session`; codes outside the table, e.g. `rewind.invalid_spec`, stay
+        registered `config.*` codes incl. the three roster-bound ones and — server >= 7.116.0 — `config.invalid_checkpoint_store` (400) and
+        `config.user_invoked_skill_unknown` (400: top-level `userInvokedSkills` named a skill this run does not carry), `corrupt_session`; codes outside the table, e.g. `rewind.invalid_spec`, stay
         200 with a failed body) answers its 4xx / 5xx ERROR BODY only when the whole submission did ZERO WORK (cumulative
         `stats.turns === 0` AND `stats.tokens === 0` — the common case: nothing billed, not idempotency-cached). When a
         `verify` / `cascade` run's earlier tier already ran turns and only the last tier is refused, the SAME code arrives
@@ -442,6 +443,16 @@ paths:
         '400': { $ref: '#/components/responses/BadRequest' }
         '401': { $ref: '#/components/responses/Unauthorized' }
         '403': { $ref: '#/components/responses/Forbidden' } # (declared 2026-08-01) 带 `sessionId` 复用他人会话:归属不匹配 ⇒ 403(自公开快照起点即有,spec 此前漏登记)。server 3.15.0 起多一个触发条件:多租部署上 session store 无归属判别能力时,复用**任何** caller 自报的 sessionId 都 403(含本 worker 自己刚铸的 —— 无 register seam 时归属从未被记下)。core 2.11.0 起默认内存店自带该能力 ⇒ 该触发条件在默认部署上不再出现。 ⚠️ (declared 2026-08-05,server >=7.0.0)`memory.admission_denied` 也走本状态 —— 本状态的 producer 全清单与分支判据写在 `Forbidden` 组件的 description 里(**那段是被解析的**,本行注释只是指路,不复述以免两处漂移)。
+        '404':
+          description: >-
+            Two codes. `resume.session_not_found` (server >= 7.115.0 / S-1038): the body carried `requireExistingSession: true` and its
+            `sessionId` does not exist in this deployment. `resume_at.not_found` (server `dist/runs.js` `resumeAtHttpStatus`): a `resumeAt`
+            anchor that is genuinely absent (compacted away) — the ONLY `resume_at.*` code that is a 404 (the rest are 422 below); like
+            every prepare-time refusal in that table it answers its error body only when the submission did ZERO WORK (turns 0, tokens 0),
+            otherwise 200 + a failed body carrying the code in `terminal.code`.
+          content:
+            application/json:
+              schema: { $ref: '#/components/schemas/ErrorResponse' }
         '409':
           description: >-
             Conflict (ConflictError). 409 — session already has an active run (`conflict.session_active_run`, `activeTaskId`,
@@ -460,7 +471,10 @@ paths:
             Semantically unprocessable. K-24 (server >= 7.104.0 / S-724): `rewind.capture_disabled` — the run turned file
             history off (`fileHistory: "disabled"`) and asks to restore in the same breath; this server's request face
             refuses that combination earlier (400 `request.field_conflict`), so only a host building a TaskSpec directly can
-            reach this code. `rewind.child_scope_unsupported` / `resume_at.*` also land here.
+            reach this code. `rewind.child_scope_unsupported` and every `resume_at.*` code EXCEPT `resume_at.not_found` (that one is
+            a 404 above) also land here — e.g. `resume_at.before_target_not_user` / `resume_at.before_root_unsupported` (`resumeAtMode:
+            "before"`). Also `request.field_conflict` (server >= 7.115.0 / S-1038): `requireExistingSession: true` without a `sessionId`
+            (the only 422 this code carries; the request contradicts itself).
             `rewind_snapshot.unresolvable` (server 7.114.0 `dist/runs.js` `resumeAtHttpStatus`: a `resumeAt` file restore —
             `restoreFiles` — that finds no file-history boundary at / above the branch point) is in the same per-code table and lands
             here too, on the same ZERO WORK condition (turns 0, tokens 0: nothing ran, nothing billed); a submission that already ran
@@ -574,6 +588,20 @@ paths:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
         '401': { $ref: '#/components/responses/Unauthorized' }
+        '404':
+          description: >-
+            `resume.session_not_found` (server >= 7.115.0 / S-1038): the body carried `requireExistingSession: true` and its `sessionId` does not
+            exist in this deployment (the previous status-derived coarse code `not_found.resource` is gone). Dispatch on `errorCode`.
+          content:
+            application/json:
+              schema: { $ref: '#/components/schemas/ErrorResponse' }
+        '422':
+          description: >-
+            `request.field_conflict` (server >= 7.115.0 / S-1038): the body carried `requireExistingSession: true` without a `sessionId` —
+            the request contradicts itself (the previous status-derived coarse code was `request.unprocessable`). The only 422 this code carries.
+          content:
+            application/json:
+              schema: { $ref: '#/components/schemas/ErrorResponse' }
         '429': { $ref: '#/components/responses/RateLimited' }
         '503': { $ref: '#/components/responses/Unauthorized' } # (declared 2026-07-31) this path is in server.ts's isBillableSubmitPath set — same three 503 doors as POST /v1/tasks and /v1/runs (no service token / draining / model-roster-pending)
 
@@ -603,7 +631,21 @@ paths:
               schema: { $ref: '#/components/schemas/RunReceipt' }
         '400': { $ref: '#/components/responses/BadRequest' }
         '401': { $ref: '#/components/responses/Unauthorized' }
+        '404':
+          description: >-
+            `resume.session_not_found` (server >= 7.115.0 / S-1038): the body carried `requireExistingSession: true` and its `sessionId` does not
+            exist in this deployment (the previous status-derived coarse code `not_found.resource` is gone). Dispatch on `errorCode`.
+          content:
+            application/json:
+              schema: { $ref: '#/components/schemas/ErrorResponse' }
         '409': { $ref: '#/components/responses/Conflict' }
+        '422':
+          description: >-
+            `request.field_conflict` (server >= 7.115.0 / S-1038): the body carried `requireExistingSession: true` without a `sessionId` —
+            the request contradicts itself (the previous status-derived coarse code was `request.unprocessable`). The only 422 this code carries.
+          content:
+            application/json:
+              schema: { $ref: '#/components/schemas/ErrorResponse' }
         '429': { $ref: '#/components/responses/RateLimited' }
         '501': { $ref: '#/components/responses/NotImplemented' }
         '503': { $ref: '#/components/responses/Unauthorized' }
@@ -919,7 +961,8 @@ paths:
         un-started ones settle as interrupted pairs, in-flight tools are NOT collateral. TWO shapes,
         discriminated by `text` presence.
         WITH text = cut + steer: the in-flight turn is cut and the text goes to the FRONT of the queue — the
-        `"now"` tier is the VERB's semantics, not a body field (the steer op's `priority` stays advisory) —
+        `"now"` tier is the VERB's semantics, not a body field (the steer op's own `priority` is a separate
+        input: it takes effect only on a server whose `Capabilities.fleet.steerPriority` reads `"engine"`) —
         and the run CONTINUES. 202 `{taskId, status, delivery:"queued-immediate", messageId, note}`;
         `messageId` ≡ the engine inputId, and a real cut is proven ONLY by a `task.turn_interrupted` event on
         the run stream whose `detail.inputId` matches it (core: no false interrupt claims — every real cut
@@ -2048,7 +2091,11 @@ paths:
           # 亲读真码:wake 的成功腿是 `driveResumeIntoRunLog` 的返回(`server.ts`,成功腿与取消臂两处铸造点),
           # **恒为 200**(wake 是同步驱动到终局/再挂起,不是 accepted 回执),且 `taskId` 有条件
           # (无活跃行即省略——ApprovalDecisionResult 同一铸造点的同一注)。旧 202+required taskId 双谎。
-          description: Woken — the resumed leg ran to its next settle (terminal, re-suspended, or needs_review).
+          description: >-
+            Woken — the resumed leg ran to its next settle (terminal, re-suspended, or needs_review). 🔴 A message-carrying wake that is CANCELLED
+            (`POST /v1/runs/{taskId}/cancel`) while the deployment's `userPromptSubmit` gate is still answering lands HERE, not as a 409 (server
+            >= 7.115.0 / core 7.40.1): `{ status: "failed", errorCode: "cancelled", bindingEnforced: true }` — RETURNED, branch on `errorCode`; the
+            park is closed with the cancel, so a second wake is 404 `not_found.parked_checkpoint` (continue the session with a new submit).
           content:
             application/json:
               schema:
@@ -2070,12 +2117,17 @@ paths:
                   retriable: { type: boolean, description: 'true = the park is STILL pending (re-parked); refetch and retry. Synchronous form only.' }
         '400': { $ref: '#/components/responses/BadRequest' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '404': { description: 'No parked checkpoint for this session (nothing to wake), or session not visible to the caller.' }
+        '404': { description: 'No parked checkpoint for this session (nothing to wake; `not_found.parked_checkpoint`), or session not visible to the caller. Also what a SECOND wake gets after a message-carrying wake was cancelled (server >= 7.115.0: that park was closed with the cancel — continue the session with a new submit).' }
         '409':
           description: >
             Pending gate (`wake.gate_pending` — decide it through its own entry) or resume context missing; also the resume-leg refusals core
             raises before the claim (`steering.blocked_by_hook` when the wake carried a `message` and the deployment's `userPromptSubmit`
-            hook crashed / timed out / refused — server >= 7.113.0 adds `retriable: true` there; `checkpoint.config_refused`). Value change on
+            hook crashed / timed out / refused — server >= 7.113.0 adds `retriable: true` there; since server >= 7.115.0 that is the ONLY thing it
+            means on this door — a message-carrying wake CANCELLED while the gate was still answering (`POST /v1/runs/{taskId}/cancel`) is no longer a
+            409 but a 200 `{ status: "failed", errorCode: "cancelled" }` (see 200; <= 7.114.x answered it 409 `steering.blocked_by_hook` and left the park
+            pending — the wrong code's side effect); `checkpoint.unsupported_version` (server >= 7.115.0, `retriable: true` = the card is still pending,
+            NOT "a verbatim retry will succeed": a task parked by <= 7.114.x whose submit body carried a non-empty `settings.permissions.allow` is not replayed
+            under the new reading — resubmit it as a new task; no `taskId` in the body); `checkpoint.config_refused`). Value change on
             the run row the wake minted for the refused attempt (server >= 7.113.0): it now ends `failed` with a structured terminal carrying
             `terminal.code: "steering.blocked_by_hook"` and holds no session lock (before 7.113.0 it ended with a code-less terminal and
             `result: null` — a zero-execution refusal recorded as an ordinary failure); the card itself stays pending.
@@ -2369,9 +2421,10 @@ paths:
             written. DETERMINISTIC: a retry cannot change it (the SDK does not auto-retry this code; it arrives as a bare `APIError`
             with `errorCode: "corrupt"`); the repair is the operator's — fix the file or delete it (deleting = an explicit "no
             rules"). For a damaged rules row `error` names the session, the damage grade and both exits, with NO on-disk path.
-            ⚠️ The same code also comes from the write path's high-water-mark sidecar (`.hwm.json`) being unreadable, and that one
-            sentence STILL names the sidecar's on-disk path (server 7.114.0 discloses it as a known gap: core #1307 / #1309, core
-            7.41.0). Also `internal.error` (unclassified).
+            ⚠️ The same code also comes from the write path's high-water-mark sidecar (`.hwm.json`) being unreadable: the sentence names the
+            object, the damage and both exits (fix the mark file, or delete it — deleting gives up the number it was holding). server >= 7.116.0
+            does NOT name the on-disk path any more (the location goes to the operator log `file_store_corrupt_read` only); server <= 7.115.x
+            still did. Also `internal.error` (unclassified).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -2989,14 +3042,13 @@ paths:
         2c session-sync PUSH Phase A — a SMALL metadata body (`entryIds, snapshots, policy, anchors, resolution?`); the
         entries stream in Phase B. The cloud classifies (§7), pre-checks blob presence (a missing referenced hash →
         422 `missing_blob` — PUT it first), guards the import lease + any active run (409), then mints a stagingId.
-        ⚠️ S-15 EPOCH DEBT (registered 2026-08-30, codex adversarial review; migration is a SEPARATE batch):
-        server ≥7.52's Phase A actually consumes `{entryIds, fileHistory?, policy, anchors, resolution?,
-        logDigest?}` (routes/session-sync.ts) — the `snapshots` key below is SILENTLY IGNORED there (an
-        unknown body key), so on ≥7.52 a push lands entries/policy/anchors and the session itself but NO
-        file snapshots/history; the snapshot-epoch shape below is what ≤7.51 servers consume. The full
-        migration (SessionManifest/SessionBundle/push-pull orchestration + `fileHistory: FileHistoryExport |
-        null` + epoch negotiation) is tracked as its own debt — this op's schema deliberately stays the
-        ≤7.51 truth until that batch lands rather than half-changing.
+        ⚠️ S-15 EPOCH: server ≥7.52's Phase A consumes `{entryIds, fileHistory?, policy, anchors, resolution?,
+        logDigest?}` (routes/session-sync.ts) — the `snapshots` key is SILENTLY IGNORED there (an unknown body key); the
+        file history rides `fileHistory` (a `FileHistoryExport` envelope, `null` / absent = none) and every blob it references must have been
+        `PUT …/sync/blobs/{hash}` first. ≤7.51 servers consume `snapshots` and do not know `fileHistory`. SDK 16.2.0 carries
+        `fileHistory` in `pushSessionBundle` / `importSessionBundle` (and fills `snapshots: []` on the pull side when the manifest omits it); a hand-rolled
+        push must send `fileHistory` itself, and only to a peer whose `capabilities.sessionSyncFileHistory` is not false (server >= 7.116.0 — else the
+        commit 422s `missing_blob`).
         `identical` → `{ relation:"identical", basis, payloadVerified }` with NO stagingId (skip Phase B);
         `basis` is `"entry-ids+digest"` when the caller supplied a comparable digest and it matched, else
         `"entry-ids"` (id-set equality only) — see the `ImportStaged` schema, which has carried these two
@@ -3013,6 +3065,11 @@ paths:
               properties:
                 entryIds: { type: array, items: { type: string } }
                 snapshots: { type: array, items: { $ref: '#/components/schemas/SyncSnapshot' } }
+                fileHistory:
+                  oneOf:
+                    - { $ref: '#/components/schemas/FileHistoryExport' }
+                    - { type: 'null' }
+                  description: 'server >= 7.52: the file-history envelope (replaces `snapshots`); `null` / absent = none. Every blob it references must already be PUT.'
                 policy: { type: array, items: { $ref: '#/components/schemas/SessionRulesRecord' } }
                 anchors: { type: array, items: { $ref: '#/components/schemas/SyncAnchor' } }
                 resolution: { type: string, enum: [overwrite-dst], description: Override a fork/stale loss-of-history conflict. }
@@ -4589,10 +4646,11 @@ paths:
         `LEADER_ENABLED` (default OFF) + `REMOTE_EXEC=e2b`. Mode is a SERVER deploy flag, not a client choice:
         `LEADER_FANOUT_ENABLED=true` (default) lets the router fan out to N isolated workers (= the value-HOLD
         correctness bet); `=false` pins a single worker. Either way it runs the E2B+git pipeline. Door B's brain
-        is the strong single agent via `/v1/tasks`+`/v1/runs`+`scenario`. When disabled (`LEADER_ENABLED` off)
-        the route is simply NOT REGISTERED → the generic **404** `not_found.route`, not 501.
-        (Corrected 2026-07-31: "When disabled → 501" was never true — no code path emits 501 here; a consumer
-        branching on 501 to detect "leader unavailable" never fires.)
+        is the strong single agent via `/v1/tasks`+`/v1/runs`+`scenario`. When there is no leader face on the deployment
+        (`LEADER_ENABLED` off) the answer depends on the server: server >= 7.116.0 mounts the route unconditionally and answers
+        **501 `capability.leader_endpoint_required`** (new code; under multi-tenant the identity gate's 401 still comes first);
+        <= 7.115.x did not register the route at all → the generic **404** `not_found.route`. Detect "leader unavailable" by
+        `errorCode` (or the `capabilities.leader` bit, which reads the same fact as the gate), not by the status alone.
 
 
         🔴 IDEMPOTENCY (server >= 7.24.0): this POST now consumes the `Idempotency-Key` header — the header is
@@ -4733,7 +4791,8 @@ paths:
           description: >-
             (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate (not the bare
             isOperator, whose empty-OPERATOR_PRINCIPALS "true-for-all" would make this index-mutating door
-            world-writable).
+            world-writable). With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501
+            `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -4787,7 +4846,7 @@ paths:
         '400': { $ref: '#/components/responses/BadRequest' }
         '401': { $ref: '#/components/responses/Unauthorized' }
         '403':
-          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate (§P2.4a).
+          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate (§P2.4a). With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -4841,7 +4900,7 @@ paths:
       responses:
         '200': { description: '{ bake }.', content: { application/json: { schema: { type: object, required: [bake], additionalProperties: false, properties: { bake: { $ref: '#/components/schemas/BakeRecordView' } } } } } }
         '403':
-          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate.
+          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -4859,7 +4918,7 @@ paths:
       responses:
         '202': { description: '{ bakeId, cancelRequested, note }.', content: { application/json: { schema: { $ref: '#/components/schemas/BakeCancelAck' } } } }
         '403':
-          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate.
+          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -4921,7 +4980,7 @@ paths:
       responses:
         '200': { description: 'SSE stream.', content: { text/event-stream: { schema: { type: string } } } }
         '403':
-          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate (this summary previously did not mention the restriction at all).
+          description: (declared 2026-07-31) errorCode "auth.operator_only" — EXPLICIT operator gate (this summary previously did not mention the restriction at all). With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).
           content:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -5133,7 +5192,7 @@ paths:
               schema: { $ref: '#/components/schemas/EntryProvenanceAccount' }
         '400': { description: 'errorCode "request.id_invalid" — the entry id could not be decoded.' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'errorCode "auth.operator_only" — provenance and erasure are operator-only deployment actions.' }
+        '403': { description: 'errorCode "auth.operator_only" — provenance and erasure are operator-only deployment actions. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '500':
           description: >
             errorCode "internal.memory_control_plane_corrupt" — core's FAIL-CLOSED refusal: the control plane
@@ -5203,7 +5262,7 @@ paths:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'errorCode "auth.operator_only" — provenance and erasure are operator-only deployment actions.' }
+        '403': { description: 'errorCode "auth.operator_only" — provenance and erasure are operator-only deployment actions. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '409':
           description: >
             Three core-minted codes, passed through verbatim; branch on `errorCode` (the status cannot tell them
@@ -5282,7 +5341,7 @@ paths:
               schema: { $ref: '#/components/schemas/MemoryOriginExternalResult' }
         '400': { description: 'errorCode "request.query_invalid" — `scopes` is absent or normalizes to an empty list. The refusal text also names where scope keys come from and repeats that an empty answer is not a clean store.' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions.' }
+        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '500':
           description: 'errorCode "internal.memory_control_plane_corrupt" (meaning (1) only on this read face) or "internal.error" (unclassified, text not echoed).'
           content:
@@ -5332,7 +5391,7 @@ paths:
             application/json:
               schema: { $ref: '#/components/schemas/MemoryOriginClearancesResult' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions.' }
+        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '500':
           description: 'errorCode "internal.memory_control_plane_corrupt" (the ledger cannot be read soundly) or "internal.error".'
           content:
@@ -5396,7 +5455,7 @@ paths:
             application/json:
               schema: { $ref: '#/components/schemas/ErrorResponse' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions.' }
+        '403': { description: 'errorCode "auth.operator_only" — origin marking and clearance are operator-only deployment actions. With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '409':
           description: >
             Six core-minted codes, passed through verbatim; BRANCH ON `errorCode` — the six operator actions all
@@ -5519,7 +5578,7 @@ paths:
             application/json:
               schema: { $ref: '#/components/schemas/WiringDiagnostics' }
         '401': { $ref: '#/components/responses/Unauthorized' }
-        '403': { description: 'Multi-tenant worker: wiring diagnostics are operator-only (`auth.operator_only`).' }
+        '403': { description: 'Multi-tenant worker: wiring diagnostics are operator-only (`auth.operator_only`). With an EMPTY `OPERATOR_PRINCIPALS` the answer is instead 501 `capability.operator_principals_required` (server >= 7.116.0; any identity, ahead of authorization — branch on `errorCode`, not the status).' }
         '404': { description: 'This worker serves no wiring diagnostics (older server, or a process not assembled by the composition root).' }
 
   /v1/sendfile-links:
@@ -5849,7 +5908,9 @@ paths:
           description: >
             OPERATOR-ONLY cross-tenant read. Absent (or equal to the caller's own principal) = read your own
             rules. Anything else requires explicit OPERATOR_PRINCIPALS membership ⇒ otherwise 403
-            `auth.operator_only`. Rule text contains command shapes, so third-party reads are an information
+            `auth.operator_only` (server >= 7.116.0: with an EMPTY list the answer is 501
+            `capability.operator_principals_required` instead — any identity, ahead of authorization; your own rules never
+            go through the operator gate). Rule text contains command shapes, so third-party reads are an information
             disclosure and are deliberately not opened to non-operators.
         - name: scope
           in: query
@@ -6594,7 +6655,14 @@ components:
         application/json:
           schema: { $ref: '#/components/schemas/QuotaError' }
     NotImplemented:
-      description: 501 — capability not available (e.g. no TiDB run store; leader gated off; `wake` unsupported).
+      description: >
+        501 — "this deployment cannot answer this" (e.g. no TiDB run store; `wake` unsupported). server >= 7.116.0: HTTP has exactly ONE status for
+        "unavailable on this deployment" — 501 — and the CAUSE is the code: `capability.*` = change the deployment shape / wire the facility
+        (incl. the new `capability.leader_endpoint_required` for `/v1/leader*` and `capability.shared_memory_required` for `/v1/shared-memory/*`),
+        `feature.*` = turn a knob on (incl. the new `feature.memory_consolidation_disabled` and `feature.config_catalog_disabled`), and
+        `capability.operator_principals_required` = configure `OPERATOR_PRINCIPALS` (every operator-only endpoint answers it, for any identity,
+        when the list is empty; a non-empty list the caller is not on is still 403 `auth.operator_only`). Branch on `errorCode`, not the status
+        (these families answered 404 / 403 on <= 7.115.x). The one registered exception is `a2aServe`'s two routes (404, anti-fingerprint).
       content:
         application/json:
           schema: { $ref: '#/components/schemas/ErrorResponse' }
@@ -6774,7 +6842,18 @@ components:
               name: { type: string }
               description: { type: string }
               content: { type: string }
-              manifest: { type: object, additionalProperties: true }
+              manifest:
+                type: object
+                additionalProperties: true
+                deprecated: true
+                description: >
+                  RETIRED — server >= 7.116.0 rejects the WHOLE skill when this key is present on a delegated agent's skill (unknown key:
+                  `agent.skills must be …`; a top-level skill answers 400 `request.field_invalid` "skill.manifest was retired in core 7.41.0 — …").
+                  core 7.41.0 retired the skill manifest (hard break, no alias). Rewrite `manifest.allowTools` to the skill's
+                  `allowedTools` (an allow-rule source, not a fence); `manifest.allowPaths` has no replacement (use the session rules'
+                  `allowDirs`). Older servers (<= 7.115.x) still accept it; the key stays declared here until the next major.
+              allowedTools: { type: array, items: { type: string }, description: 'server >= 7.116.0 — the skill''s allow-rule source (see `SkillSpec.allowedTools`); <= 7.115.x rejects the key (unknown key).' }
+              disallowedTools: { type: array, items: { type: string }, description: 'server >= 7.116.0 — the skill''s deny-rule source (see `SkillSpec.disallowedTools`); <= 7.115.x rejects the key (unknown key).' }
               files:
                 type: array
                 items:
@@ -6837,6 +6916,13 @@ components:
             instead of silently starting a fresh empty session ("looks warm, actually fresh"). Sending `true`
             with NO sessionId also fails loud (nothing to resume). Absent/`false` ⇒ the historical create-on-miss.
             Rides the persisted body onto resume legs.
+            🔴 The two refusals carry machine codes (server >= 7.115.0 / S-1038; before that both answered the status-derived coarse
+            codes `not_found.resource` / `request.unprocessable` and the real code lived only in the sentence's trailing
+            parenthesis): `sessionId` not found in this deployment ⇒ **404 `resume.session_not_found`** (premise: the session store
+            can answer ownership — SQL, local and the engine's default in-memory store all can); no `sessionId` at all ⇒ **422
+            `request.field_conflict`** (the request contradicts itself — `sessionId` is its precondition; NOT "session not found",
+            and the only 422 this code carries). Same body on `POST /v1/tasks`, `/v1/tasks/stream` and `/v1/runs`; authorization
+            happens before the SSE head, so the stream door answers the real status too. Dispatch on `errorCode`.
         projectId:
           type: string
           description: >
@@ -6876,6 +6962,18 @@ components:
             LISTING RENDERER, not to this gate: turn it down with `settings.skillListingBudgetFraction` /
             `settings.skillListingMaxDescChars`.
           items: { $ref: '#/components/schemas/SkillSpec' }
+        userInvokedSkills:
+          type: array
+          items: { type: string, minLength: 1 }
+          description: >
+            server >= 7.116.0 (core 7.41.0 #1303). Skills the HUMAN called by name (the shell parses the typed `/name`; by `SkillSpec.name`).
+            Their `allowedTools` / `disallowedTools` take effect from the start of the run and NO `Skill` card is raised (the human naming
+            it is the statement); it governs this one run only (a steer does not end it; the next submit does not carry it). Every name must be
+            a skill the run carries (scenario factory ∪ this request's `skills`), else the engine refuses to start: 400
+            `config.user_invoked_skill_unknown` (sync leg `POST /v1/tasks`; the async / live-stream legs answer 2xx and the same code lands on the
+            terminal run row; `disableSkills: true` makes any name this code). A bad value shape (bare string / empty-string member / non-string /
+            object / null) is a 400 `request.field_invalid`. Does not deliver the skill body. PROBE `capabilities.userInvokedSkills` (constant true);
+            absent = an older server that answers 400 `request.body_shape` listing the key in `unknownKeys` — do not send it.
         reasoningEffort:
           type: string
           enum: [off, minimal, low, medium, high, xhigh, max]
@@ -6936,7 +7034,8 @@ components:
           type: string
           description: >
             CC Rewind parity (E18). Fork the conversation FROM this user-message SessionTreeEntry.id (non-destructive
-            branch via setLeafId). With rewindFiles=true ⇒ "both" (also restore the working tree). Alone ⇒
+            branch via setLeafId). With `restoreFiles: true` ⇒ "both" (also restore the working tree — the retired spelling
+            `rewindFiles` still rides the wire but its restore sense is core's typed migration rejection naming `restoreFiles`). Alone ⇒
             "conversation". HONORED only where the deployment wired a resume-anchor store + getLeafId (capabilities.resumeAt);
             unknown anchor ⇒ 4xx, capability-off ⇒ 501. Cannot combine with a durable resume.
         resumeAtMode:
@@ -6949,7 +7048,8 @@ components:
             everything after it"). core enforces the edges and the service passes its rejection codes through
             UNCHANGED for the shell to render: `resume_at.before_target_not_user` (plain user-message targets
             only), `resume_at.before_root_unsupported` (cannot rewind past the session root — start a new
-            session), `rewind_snapshot.unresolvable` (with rewindFiles: no snapshot at/above the branch point).
+            session), `rewind_snapshot.unresolvable` (with a file restore, `restoreFiles`: the target has no file-history boundary of its
+            own — a "before" restore only trusts the target's OWN boundary and never crosses into an earlier turn).
             Only meaningful WITH `resumeAt` — sent alone it is a 400 (fail-loud, not a silent no-op).
         rewindFiles:
           type: boolean
@@ -7024,8 +7124,8 @@ components:
             `acceptEdits` (in-workspace writes do not ask) or `bypassPermissions` (422 `request.host_posture_refused` on hosted
             deployments) for the old no-ask posture. `auto` arms iff `permissionMode === "auto"` ∧ a classifier seat is mounted ∧
             `caps.autoMode !== false` (one polarity); when the requested mode does not take effect the stream gets `engine_notice`
-            `config.permission_mode_unavailable`. `bypassPermissions` RELEASES the nine releasable ask classes and DISCLOSES each
-            (`tool_end.gate.disposition.released` + one `engine_notice` `permission.ask_released_by_mode` per (mode, class) per run);
+            `config.permission_mode_unavailable`. `bypassPermissions` RELEASES the ten releasable ask classes (server >= 7.115.0: the tenth is `unstated`, a server-tool call nobody stated)
+            and DISCLOSES each (`tool_end.gate.disposition.released` + one `engine_notice` `permission.ask_released_by_mode` per (mode, class) per run);
             immune classes (deployment-authored, ask / org rules, hooks, ancestors, questions …) still ask; a write whose protection
             cannot be judged is refused (`deniedBy: mode`). Request vocabulary: FIVE words — `dontAsk` on a fresh submit is 400
             `request.field_invalid` (S-902). The three sentences below — "omitting both carriers means no mode-derived gate", "`auto`
@@ -7230,6 +7330,26 @@ components:
             the delivery lane, so raising it only helps a model whose declared window is below 200 000 tokens.
             The engine's own twin code `config.skill_listing_budget_invalid` (400) is NOT reachable through this
             submit leg today — it belongs to callers that build a `TaskSpec` directly.
+            🔴 `permissions.allow` IS A STATEMENT, NOT A WHITELIST (server >= 7.115.0 / S-654; probe
+            `capabilities.settings.permissions.allowGrant === true` — an absent key is an older server that reads the bucket as a
+            list, so put nothing in it there). The bucket is compiled by the SAME rule compiler as `deny` / `ask`: a hit is a
+            reasoned allow = "somebody stated it" (it answers an MCP / A2A server-tool call nobody stated; without it an
+            ask-class mode raises a card, and with no approval surface the call is refused); a miss states nothing and the call is
+            judged as usual — a tool off the list is NOT refused any more (<= 7.114.x refused it). It does NOT skip the question
+            on built-in tools: the engine's own write gate and shell checks still ask in `default` mode, and deny / ask win
+            (unlike the reference implementation, where `allow: ["Edit"]` skips the edit confirmation; use `permissionMode`
+            for that). For "only these tools" use the real knobs: the session rule `toolAllow`
+            (`PUT /v1/sessions/{sessionId}/policy`), per-request `excludeTools` / `excludeAllTools`, or the deployment's scenario
+            tool surface. Entry forms: a tool-name rule (exact name, `mcp__<server>__*`, `a2a__<peer>__*`; `Bash(*)` is accepted
+            and compiled as a whole-tool rule; server >= 7.116.0 also accepts the two-segment covering form `mcp__<server>` / `a2a__<peer>`,
+            read as the whole server — same meaning as `mcp__<server>__*`); a retired name, a short name with no protocol prefix, a missing-segment
+            name (`mcp__` / `mcp__<server>__`), a protocol name whose server segment the engine cannot have minted (e.g. `mcp__github.com__*` —
+            write `mcp__github_com__*`; server >= 7.116.0 refuses it with a 422 instead of accepting a rule that can never match), a backslash,
+            more than 512 characters, or a CONTENT form
+            (`Bash(npm:*)`, `Read(./x)`, `WebFetch(domain:...)`) is a whole-request 422 (permanent content-form allows live in the
+            persistent rule store: `/v1/rules/cc-import`, or answer yes on a card). The same applies to a PreToolUse hook: an
+            EXPLICIT `permissionDecision: "allow"` states it (and binds only the arguments the hook saw); a hook that only adds
+            `additionalContext` / only rewrites `updatedInput` states nothing.
           additionalProperties: true
         cwd: { type: string, description: Working directory for the execution env. }
         deviceId:
@@ -7452,6 +7572,12 @@ components:
             to turn them off, or `{at: [r1, r2]}` with fractions in (0, 1], r1 <= r2 to tune thresholds
             (bad shapes are a 400). Budget ceilings stay TOP-LEVEL body keys
             (`maxCostUsd`/`maxTokens`) — the server folds them into the engine's limits internally.
+            🔴 The key set is CLOSED (the same four keys as the server's published `TaskRequestBody.limits`):
+            `limits.brainCallGuardrailMs` (the engine's wall on a SINGLE brain call, default one hour, `false` / `0` off) is NOT
+            one of them — server >= 7.115.0 answers it with 400 `request.field_invalid` (a millisecond number, `false` and `0`
+            alike; the sentence names the key; <= 7.114.x accepted it but it took no effect and the wall stayed at one hour).
+            This server has no knob for a caller to set that wall. `budgetStreamCancel` and `degrade` are the same kind of
+            "not caller-settable" keys.
           properties:
             maxWalltimeMs: { type: integer }
             maxOutputTokens: { type: integer }
@@ -8136,6 +8262,16 @@ components:
             is unchanged at 7.64.0 — only its source moved (projected from `result.terminal`, or read straight
             off a legacy flat blob). ⚠️ K-24 / S-173 (server >= 7.104.0): on a `needs_review` PARK row it is core's canonical
             `review.pending` (absent before) — never read "errorCode present" as "failed"; read `status` first.
+            🔴 server >= 7.116.0 (S-1099) adds three values for the run store's own terminal verdicts, which used to live only in the `error`
+            sentence: `run.stalled` (heartbeat-lost reap — and the read-time fold that precedes the reap; sentence `run stalled (instance lost?)`),
+            `run.orphaned` (local-lane restart / session-occupancy takeover reclaim; sentence `run orphaned by engine restart`) and
+            `approval.expired` (the expiry reap of a durably parked approval; the column already carried it, the read face did not project it;
+            sentence `approval expired before decision`). None of the three means the request was wrong — resending the same request is
+            pointless, only a new submission makes a new run. READ `status` FIRST (`failed`), then branch on the code. Open set (a string; always keep a
+            default arm). ABSENCE: rows written by <= 7.115.x carry only the sentence; a one-time startup migration backfills the code
+            (log `one_time_migrations_applied` `holderDeathCodeRowsBackfilled`) and a new replica reads such a row as the code during the upgrade window,
+            but the migration has a window (30 days after the release, then the write-back and the read half are deleted) — so
+            "no `errorCode`" never proves "not a holder death": rows migrated late or after the window stay sentence-only.
         error: { type: string }
         jobId:
           type: string
@@ -8947,7 +9083,8 @@ components:
             server >=7.12.0 — the `GET /v1/outcomes` mechanical-signal read aggregate (design/73 §7.2) is
             available. Predicate mirrors the route's refusal arms exactly: a QUERYABLE ledger is wired (a
             file-only sink writes JSONL and has no query face ⇒ 501), AND on a multi-tenant deployment the
-            operator list is non-empty (single-user has no such gate — the only user IS the operator).
+            operator list is non-empty (single-user has no such gate — the only user IS the operator); with an empty
+            list the multi-tenant route answers 501 `capability.operator_principals_required` (server >= 7.116.0; 403 before).
             Added because this face previously had a 501 but NO capability bit, leaving consumers to
             trial-by-501 — the exact pattern this capability surface exists to remove.
         images:
@@ -8971,7 +9108,17 @@ components:
             principal→org membership fold present), so true ⟺ the face actually works — a deployment with
             the store but no membership authority deliberately reports false (and does not mount the routes).
         workflows: { type: boolean, description: "ENGINE-CAN: this worker's engine can orchestrate S8 self-orchestration workflows (server: `workflowsCapable ?? Boolean(workflowRunStore)`). The MOUNTING of the durable /v1/workflows read routes is the separate `workflowsList` bit below; the two coincide in today's wiring but are declared as orthogonal axes." }
-        workflowsList: { type: boolean, description: "`GET /v1/workflows` list face (separate from the per-run reads)." }
+        workflowsList: { type: boolean, description: "`GET /v1/workflows` list / detail / stream faces (the workflow run store is wired; separate from the per-run reads). server >= 7.116.0: the journal face `GET /v1/workflows/{id}/journal` is advertised by the new bit `workflowsJournal`, not by this one (value unchanged)." }
+        workflowsJournal:
+          type: boolean
+          description: >
+            server >= 7.116.0 (predicate class "facility": the workflow run store AND the journal store). Advertises
+            `GET /v1/workflows/{id}/journal`. On a deployment with the run store but no journal store (`DB_BACKEND=memory`,
+            multi-tenant bare boot, SQL coordinates not fully configured) with self-orchestration on, `workflowsList` is true
+            and this is false; the journal face then answers 501 `capability.workflow_store_required` (any id, ahead of the
+            per-row owner check; `capability.self_orchestration_required` when the run store is absent). A journal entry point reads THIS bit, not
+            `workflowsList`. ABSENT = an older server (<= 7.115.x): fall back to `workflowsList` (the old behaviour — the
+            bit could be true while the journal face always answers 501).
         workflowModels:
           type: array
           items: { type: string }
@@ -9014,8 +9161,8 @@ components:
             (DESIGN-278 §5 S2 — deployment config self-description) is mounted on this DEPLOYMENT. TWO-term
             conjunction, written against the route's own refusal arms: ① the `CONFIG_CATALOG_ENABLED` knob is
             on (default on; a compliance deployment that turns it off makes the path a 404 — the valve-family
-            precedent) AND ② the operator principal list is NON-EMPTY (with an empty list the route 403s every
-            identity). 🔴 DEPLOYMENT-LEVEL AVAILABILITY, NOT THE CALLER'S AUTHORIZATION: the caller's own
+            precedent; server >= 7.116.0 answers 501 `feature.config_catalog_disabled` there, 404 before) AND ② the operator principal list is NON-EMPTY (with an empty list the route refuses every
+            identity — 501 `capability.operator_principals_required` on server >= 7.116.0, 403 before). 🔴 DEPLOYMENT-LEVEL AVAILABILITY, NOT THE CALLER'S AUTHORIZATION: the caller's own
             identity is NOT in the predicate — the route additionally requires the CURRENT principal to be an
             explicit operator (`routes/config-catalog.ts` `explicitOperatorOk`, else 403 `auth.operator_only`),
             so a non-operator reads `true` and still gets 403. Show/invoke the catalog only for an identity you
@@ -9035,8 +9182,15 @@ components:
             `false`/absent otherwise (same predicate as the route's 501). `resume: "snapshot"` is a semantic
             advertisement: the bus is latest-state (not an event log) and every connection opens with a full
             snapshot frame, so reconnect = re-snapshot (deliberately no last-event-id cursor); transient
-            bg_notification frames re-deliver via the durable completion inbox. `steerPriority: "advisory"` =
-            steer body.priority is accepted + enum-validated but a no-op until the core queue seam (E15).
+            bg_notification frames re-deliver via the durable completion inbox. `steerPriority` (a string, open
+            set) says whether the steer body's `priority` takes effect on THIS server: `steerPriority: "advisory"`
+            (server <=7.115.x) = accepted + enum-validated + echoed but a no-op (nothing is handed to the engine);
+            `steerPriority: "engine"` (server >=7.116.0) = `priority` (`now` / `next` / `later`) is handed to the
+            engine as the injection tier, and the engine owns what each tier means — `now` cuts the in-flight turn
+            IMMEDIATELY (the running tool receives an abort, an approval card pending on this replica is revoked; one `engine_notice`
+            `task.turn_interrupted` frame is the evidence), `later` is delivered after the turn the run would have stopped on, no `priority` =
+            `next`. Read this bit before offering a `priority` choice; an absent
+            or unknown value means "do not assume it takes effect", never `"engine"`.
           oneOf:
             - type: boolean
               enum: [false]
@@ -9257,6 +9411,25 @@ components:
             outputStyle: { type: boolean }
             env: { type: boolean, description: 'TRUE on the single-user host lane (server emits `cwdHonored(config)`). It is NOT hard-coded false any more — the old always-false value predated the per-task shellEnv seam and hid a live capability.' }
             hooks: { type: boolean, description: 'Single-user deployments only (`requirePrincipal !== true`).' }
+        settings:
+          type: object
+          description: >
+            🔴 server >= 7.115.0 (S-654), ALWAYS present: `{ permissions: { allowGrant: true } }` — the VERSION bit for "which reading does this
+            server give `settings.permissions.allow` on a task submit". `permissions.allowGrant === true` = the `allow` bucket is compiled into
+            ALLOW RULES: a hit gives "somebody stated it" (so an MCP / A2A server-tool call nobody stated no longer raises a card) — it is NOT
+            "skip the question" and NOT a whitelist (a tool off the list is no longer refused; the engine's own write gate / shell checks still ask
+            on built-in tools, deny / ask still win; a bad-shape or content-form name is a whole-request 422).
+            🔴 ABSENT KEY = an older server (<= 7.114.x), which read `allow` as a WHITELIST (everything off the list refused) — do not put anything
+            in the allow bucket there. NOT the same bit as `taskSettings.permissions` (unchanged, still a boolean: "this server accepts the
+            `settings.permissions` face"). A version bit: constant `true`, never varies with the deployment; the deployment-level "who stated what"
+            (operator env `APPROVAL_GRANT`) is on the operator diagnostics face (`serverGates.approvalGrant`), not here.
+          additionalProperties: true
+          properties:
+            permissions:
+              type: object
+              additionalProperties: true
+              properties:
+                allowGrant: { type: boolean, description: 'Constant `true` on server >= 7.115.0: `settings.permissions.allow` is read as allow RULES (a statement), not as a list. The whole `settings` key being absent = an older server.' }
         memoryWrite:
           type: boolean
           description: >
@@ -9272,9 +9445,25 @@ components:
             S-15 换店; ≤7.51 the last conjunct was the file-snapshot store). Gate the whole sync surface off
             this. ⚠️ The two BLOB faces (PUT …/sync/blobs/{hash}, GET …/sync/history/blobs/{hash})
             additionally need the store's blob faces (`syncBlobFaces` — the SQL/cloud backends; the local
-            file backend has none): without them the PUT answers 501 `capability.snapshot_store_required`
-            and the history PULL answers the no-oracle 404 `not_found.blob`, while the REST of the sync
-            surface keeps working.
+            file backend has none): without them BOTH answer 501 `capability.snapshot_store_required`
+            (server >= 7.116.0; the history PULL answered a no-oracle 404 `not_found.blob` there on <= 7.115.x),
+            while the REST of the sync surface keeps working. Since server >= 7.116.0 the two blob faces are
+            advertised by their own bit `sessionSyncFileHistory`; this bit speaks for the conversation half
+            (its predicate additionally requires a session-policy store that can purge, `deleteBySession` —
+            a deployment whose embedder-supplied store lacks it answers the whole family 501
+            `capability.policy_purge_required` and this bit is false).
+        sessionSyncFileHistory:
+          type: boolean
+          description: >
+            server >= 7.116.0 (predicate class "facility": `sessionSync` AND the file-history store has blob transfer faces
+            — SQL backends only; `DB_BACKEND=local` is always false). Advertises exactly the two file-history blob faces
+            `PUT /v1/sessions/{sessionId}/sync/blobs/{hash}` and `GET /v1/sessions/{sessionId}/sync/history/blobs/{hash}`.
+            READ IT ON BOTH ENDS of a sync: if either is false, sync the conversation only — do not push `fileHistory`, do
+            not PUT blobs (a `fileHistory` pushed to a peer without the blob faces 422s `missing_blob` after commit). When
+            false the two routes answer 501 `capability.snapshot_store_required` (any session id, ahead of the owner check).
+            A blob that the session history graph does not reference / whose bytes are gone stays a 404 `not_found.blob`.
+            ABSENT = an older server (<= 7.115.x): the bit cannot be read there (a `DB_BACKEND=local` deployment with
+            `sessionSync: true` answered PUT blob 501 on every call), so try as before.
 
         # ─── S-139(sdk 8.3.0):对 server 7.60.0 的整体重对账补齐的 19 位 ───────────────────────
         # 行号 = server 7.60.0 树的 `src/http/routes/capabilities.ts`。语义与谓词的全文在
@@ -9367,7 +9556,8 @@ components:
           description: >
             Governance carry-out bundle pair `POST /v1/memory/{export,import}` (operator lane) —
             capabilities.ts:261, two conjuncts: both engine seams wired AND `operatorPrincipals` NON-EMPTY
-            (an empty roster makes those routes 403 for every identity). True does not promise the backend
+            (an empty roster makes those routes refuse every identity — 501 `capability.operator_principals_required` on
+            server >= 7.116.0, 403 before). True does not promise the backend
             has the bundle composite face (core then refuses loudly with `memory.export_incomplete`).
         memoryCompliance:
           type: boolean
@@ -9469,10 +9659,13 @@ components:
         a2aServe:
           type: boolean
           description: >
-            Server-as-peer knob (capabilities.ts:564 = `config.a2aServe !== undefined`): true ⟺
-            `GET /.well-known/agent-card.json` and `POST /v1/a2a` exist; false ⟺ both 404. Scope is ROUTE
-            EXISTENCE, not "every method runs" — `message/send` / `tasks/get` additionally need a durable run
-            store (without it they answer a named JSON-RPC `-32004`).
+            Server-as-peer: true ⟺ `GET /.well-known/agent-card.json` and `POST /v1/a2a` exist; false ⟺ both 404
+            (`not_found.route`, anti-fingerprint — the one registered exception to "unavailable = 501"). server >= 7.116.0
+            predicate (class "facility + config"): the `A2A_SERVE_ENABLED` knob AND a durable run store; <= 7.115.x looked at the knob
+            only (`config.a2aServe !== undefined`). 🔴 value change: with the knob on but NO durable run store
+            (`DB_BACKEND=memory`, multi-tenant bare boot) this bit is now false and the card and the RPC both answer 404 (7.115.x:
+            true, card 200, every `message/send` / `tasks/get` a JSON-RPC `-32004`); the startup log carries a warn
+            `a2a_serve_not_served`. The old "the server deliberately does not fold the run store into this bit" note is retired.
         agentRoster:
           type: boolean
           description: >
@@ -9667,6 +9860,23 @@ components:
             answers the request key with a 400 `request.body_shape` naming it under `unknownKeys` — do not send the key
             there and tell the user the factory skills stay installed. True only says "this server knows the key", not
             whether the deployment has any factory skills.
+        userInvokedSkills:
+          type: boolean
+          enum: [true]
+          description: >
+            server >= 7.116.0 (constant true; no predicate, no tenant gate) — the ADVANCE READING for the request key
+            `TaskRequest.userInvokedSkills` (skills the human named; effective from the start of the run, no `Skill` card);
+            the bit and the key are the SAME word. ABSENT = an older server (<= 7.115.x), which answers the key with a 400
+            `request.body_shape` naming it under `unknownKeys` — do not send it there.
+        skillToolLists:
+          type: boolean
+          enum: [true]
+          description: >
+            server >= 7.116.0 (constant true) — the skill tool lists `allowedTools` / `disallowedTools` TAKE EFFECT (allow-rule /
+            deny-rule source; see `SkillSpec.allowedTools`). ABSENT = an older server (<= 7.115.x): on a top-level skill the two
+            lists are accepted but the engine does not read them — they are silently inert and there is NO 400 to probe, so do not
+            expect them to stop a tool (fence with deny rules instead); on a delegated agent's skill they are an unknown key that
+            rejects the whole skill.
     WriteProtectionCapability:
       type: object
       additionalProperties: false
@@ -9801,11 +10011,42 @@ components:
         engine refuses the skill outright at load time, so the HTTP face answers first where the caller can read it).
         The bound is 1 048 576 **UTF-16 code units** (`MAX_SKILL_CONTENT_CHARS`); see the STRING-LENGTH UNIT
         convention in `info.description` for why this `maxLength` states that number verbatim.
+        🔴 server >= 7.116.0 (core 7.41.0): a skill carries two TOOL LISTS, `allowedTools` / `disallowedTools` — the
+        run-scoped ALLOW-RULE and DENY-RULE source of the skill once it is activated. NOT a fence (<= 7.115.x the engine read
+        the skill's tool list as "only these"): unlisted tools are judged as usual, listed ones are not asked about for the rest
+        of the run — which makes it WIDER than `settings.permissions.allow` (that one stays a statement and does not
+        release the engine's own write gate / shell ordinary asks on built-in tools). Probe `capabilities.skillToolLists`
+        (absent = an old server that accepts the keys on a top-level skill and silently ignores them). The skill's `manifest`
+        key is RETIRED: any value on a top-level skill is a 400 `request.field_invalid` ("skill.manifest was retired in core
+        7.41.0 — …"; rewrite `manifest.allowTools` to `allowedTools`; `allowPaths` has no replacement), and on a delegated
+        agent's skill (`agents[].skills[]`) it is an unknown key that rejects the whole skill.
       required: [name, description, content]
       properties:
         name: { type: string, minLength: 1 }
         description: { type: string }
         content: { type: string, minLength: 1, maxLength: 1048576 }
+        allowedTools:
+          type: array
+          items: { type: string }
+          description: >
+            server >= 7.116.0. The skill's run-scoped ALLOW-RULE source (permission-rule spellings: a tool name,
+            `mcp__<server>` / `mcp__<server>__*`; `*`, write paths and domain forms grant nothing). Once the skill is activated
+            (named in top-level `userInvokedSkills` — no `Skill` card — or activated by the model and the card approved) the
+            listed tools are not asked about for the rest of the run: it clears the engine's ordinary and "nobody stated it" asks,
+            so it is WIDER than `settings.permissions.allow`; deny / ask rules, `APPROVAL_REQUIRE`, `APPROVAL_NEVER_AUTO`, the shell
+            floor, write protection and plan-mode asks are not cleared. NOT a fence: unlisted tools are judged as usual. A non-string-array
+            is a 400 `request.field_invalid`; a protocol name whose server segment cannot be minted / is missing / is a wildcard
+            (`mcp__*`) is a 400 too (top-level `skills[]` and `agents[].skills[]` judge identically). Probe `capabilities.skillToolLists`.
+        disallowedTools:
+          type: array
+          items: { type: string }
+          description: >
+            server >= 7.116.0. The skill's run-scoped DENY-RULE source (same grammar / gates / probe as `allowedTools`): once the skill
+            is activated these tools are refused for the run (no execution, no card; `tool_end.gate.disposition` is
+            `{ kind: "denied", deniedBy: "policy" }`). `*` and domain forms (`WebFetch(domain:…)`) read as "none" on this side too —
+            accepted with 2xx and only an operator-audience notice `skills.allowed_tool_not_granted`; write-path forms and the rest compile
+            into deny rows (as the server contract states it for the engine's `compileSkillGrant`; the SDK did not re-run the engine on the deny side's write-path forms —
+            the engine's own notice text lists "a write-path or domain entry" among entries that "grant (or refuse) nothing").
 
     McpServerSpec:
       type: object
@@ -11740,6 +11981,11 @@ components:
         expiresAtMs: { type: number, description: 'Absolute window deadline — the SAME number minted once for the tool_approval frame (never recomputed).' }
         sessionId: { type: string }
         requiresRealApproval: { type: boolean, enum: [true] }
+        rememberRefused:
+          type: boolean
+          enum: [true]
+          description: >-
+            server >= 7.116.0, ADDITIVE, present ONLY when true (never `false`): the "remember for this session" answer (live `allow_session` / durable `/decide` `remember:"session"`) will NOT be remembered on this card — the decision is accepted and applies once, the receipt's `rememberApplied` is `false` (existing key, not a new one), later cards of the same kind still ask. A shell reads this to decide whether to render the "allow for the session" choice instead of inferring it from `requiresRealApproval` / `mandated` / `governanceForced`. One bit for four reasons: the operator-governance gate / a human must approve each time / a mandated card / the answer would also grant more than this one call (new in 7.116.0: approving an engine `Skill` card activates the skill and frees its listed tools for the run, which the card cannot show, so it is not remembered). ABSENT = remember works on this card, OR an older server (<= 7.115.x never carries the key). Same bit on the live frame, the `approval_request` card (= `card_json`, incl. the reconnect replay), the `livePending` row, and the `/v1/approvals` `pending[]` row (+ their `/stream` frames); NOT on inbox rows.
         governanceForced: { type: boolean, enum: [true] }
         mandated: { type: boolean, enum: [true], description: 'server >= 7.101.0 (T4①): the mandated bit, same layer and shape as the two flags above (present only when true); the SAME value as `frame.mandated` (read once when the entry is minted).' }
         mandate:
@@ -11902,6 +12148,9 @@ components:
             Present ⇔ the request carried `remember:"session"` and the worker has an exemption store. `true` = the
             per-session per-tool exemption landed; `false` = the grant failed (logged) or the gate carried no
             rememberable toolName — the decision itself still stands.
+            🔴 server >= 7.116.0: ALWAYS `false` on a card that carries `rememberRefused: true` (an engine `Skill` card etc. — the
+            answer would also grant more than this one call): the decision is accepted and applies once, the exemption store gets
+            zero writes (existing key, not a new one). Ordinary cards keep `true` = landed.
 
     ApprovalExemption:
       type: object
@@ -12045,6 +12294,11 @@ components:
             🔴 DISPLAY / TRIAGE ONLY, and ABSENT MEANS THERE REALLY IS NO SUPPLY (rule lane unarmed, the
             command yields no rule, no rule could silence this ask, or an old row) — never "the projection
             dropped it", which is precisely the bug this key exists to close. Never `null`, never `[]`.
+        rememberRefused:
+          type: boolean
+          enum: [true]
+          description: >-
+            server >= 7.116.0, ADDITIVE, present ONLY when true (never `false`): the "remember for this session" answer (live `allow_session` / durable `/decide` `remember:"session"`) will NOT be remembered on this card — the decision is accepted and applies once, the receipt's `rememberApplied` is `false` (existing key, not a new one), later cards of the same kind still ask. A shell reads this to decide whether to render the "allow for the session" choice instead of inferring it from `requiresRealApproval` / `mandated` / `governanceForced`. One bit for four reasons: the operator-governance gate / a human must approve each time / a mandated card / the answer would also grant more than this one call (new in 7.116.0: approving an engine `Skill` card activates the skill and frees its listed tools for the run, which the card cannot show, so it is not remembered). ABSENT = remember works on this card, OR an older server (<= 7.115.x never carries the key). Same bit on the live frame, the `approval_request` card (= `card_json`, incl. the reconnect replay), the `livePending` row, and the `/v1/approvals` `pending[]` row (+ their `/stream` frames); NOT on inbox rows.
         governanceForced:
           type: boolean
           enum: [true]
@@ -12997,31 +13251,97 @@ components:
       type: object
       description: >
         2c session-sync `GET …/sync/manifest` payload (wrapped server-side as `{ manifest }`). The THIN cross-backend
-        snapshot: entry IDS (oldest-first, NOT payloads) + per-snapshot relPath→blobHash + policy + anchors + leaf.
-      # 封闭(census 批2 第三段,2026-07-30):铸造点 `session-sync.ts`(exportSessionManifest 尾部
-      # 字面量)恰是这 7 键,全部无条件(leafId 缺席位=null 不省略)。
+        snapshot: entry IDS (oldest-first, NOT payloads) + the file-history envelope + policy + anchors + leaf.
+        🔴 server >= 7.52 (S-15, design/381; re-read byte for byte against 7.116.0): the key `snapshots` (per-snapshot
+        relPath→blobHash, the retired E19 whole-tree snapshot epoch) is NO LONGER SENT — the server's `exportSessionManifest` mints
+        `{ sessionId, entryIds, entryCount, leafId, fileHistory, policy, anchors }` and `fileHistory` (core's versioned
+        `FileHistoryExport` envelope; `null` = no history / the source store cannot export) replaces it. <= 7.51 servers still send
+        `snapshots` and no `fileHistory`. The blob BYTES never ride the manifest: content-addressed, via the history blob faces
+        (`GET …/sync/history/blobs/{hash}` / `PUT …/sync/blobs/{hash}`; probe `capabilities.sessionSyncFileHistory` on BOTH ends).
+        The SDK's `manifest()` fills `snapshots: []` when the wire omits it.
+      # 封闭(census 批2 第三段,2026-07-30;16.2.0 按 7.116.0 发布字节重核):铸造点 `session-sync.ts`(exportSessionManifest 尾部
+      # 字面量)恰是 `{ sessionId, entryIds, entryCount, leafId, fileHistory, policy, anchors }` 7 键(≥7.52),无 `snapshots`;
+      # ≤7.51 老 server 发 `snapshots`、无 `fileHistory` ⇒ 两键都不进 required(支持底线 3.0.0)。
       additionalProperties: false
-      required: [sessionId, entryIds, entryCount, leafId, snapshots, policy, anchors]
+      required: [sessionId, entryIds, entryCount, leafId, policy, anchors]
       properties:
         sessionId: { type: string }
         entryIds: { type: array, items: { type: string }, description: Oldest-first, verbatim cross-backend. }
         entryCount: { type: integer, description: '= entryIds.length (the `/sync/entries` trailer count).' }
         leafId: { type: [string, 'null'] }
-        snapshots: { type: array, items: { $ref: '#/components/schemas/SyncSnapshot' } }
+        snapshots: { type: array, items: { $ref: '#/components/schemas/SyncSnapshot' }, description: 'server <= 7.51 ONLY (the retired E19 snapshot epoch); server >= 7.52 does not send it — see `fileHistory`.' }
+        fileHistory:
+          oneOf:
+            - { $ref: '#/components/schemas/FileHistoryExport' }
+            - { type: 'null' }
+          description: 'server >= 7.52: the per-edited-file rewind history envelope; `null` = no history / the source store cannot export; key ABSENT = a <= 7.51 server (that generation sends `snapshots`).'
         policy: { type: array, items: { $ref: '#/components/schemas/SessionRulesRecord' } }
         anchors: { type: array, items: { $ref: '#/components/schemas/SyncAnchor' } }
 
+    FileHistoryExport:
+      type: object
+      description: >
+        Mirror of core's `FileHistoryExport` (`formatVersion: "file-history/1"`) — the session-sync envelope for the per-edited-file rewind history graph
+        (server >= 7.52; replaces the retired E19 `SyncSnapshot`). Blob bytes are NOT inside: they are content-addressed and travel through the history blob faces.
+        The SDK reads only `tracked[].versions[].blobHash` (which blobs to move) and passes everything else through verbatim — the server's import door judges
+        `formatVersion` (refuse-not-coerce) and the closed `keyKind` / `keyFamily` sets, so they are plain strings here.
+      required: [formatVersion, tracked, boundaries]
+      properties:
+        formatVersion: { type: string, description: 'today only `file-history/1`; the server refuses any other value.' }
+        tracked:
+          type: array
+          items:
+            type: object
+            required: [relOrAbsPath, keyKind, keyFamily, baseAvailable, versions]
+            properties:
+              relOrAbsPath: { type: string }
+              keyKind: { type: string }
+              keyFamily: { type: string }
+              baseAvailable: { type: boolean }
+              versions:
+                type: array
+                items:
+                  type: object
+                  required: [version, blobHash, backupTime]
+                  properties:
+                    version: { type: integer }
+                    blobHash: { type: [string, 'null'], description: '`null` = the "did not exist" marker (no blob to move).' }
+                    mode: { type: integer }
+                    parentIdent: { type: string }
+                    backupTime: { type: string }
+        boundaries:
+          type: array
+          items:
+            type: object
+            required: [entryId, files]
+            properties:
+              entryId: { type: string }
+              files:
+                type: array
+                items:
+                  type: object
+                  required: [relOrAbsPath, version]
+                  properties:
+                    relOrAbsPath: { type: string }
+                    version: { type: integer }
+
     SessionBundle:
       type: object
       description: >
         The portable state of ONE session, ready to replay into another backend. Blobs are NOT inlined (each
         snapshot carries only its `manifest`; the bytes stream through the content-addressed blob routes). The SDK
-        assembles this from a manifest + the streamed entries for a PUSH.
+        assembles this from a manifest + the streamed entries for a PUSH. server >= 7.52: the file history rides `fileHistory`
+        (the `FileHistoryExport` envelope) instead of `snapshots`.
       required: [sessionId, entries, snapshots, policy, anchors]
       properties:
         sessionId: { type: string }
         entries: { type: array, items: { $ref: '#/components/schemas/SyncEntry' } }
         snapshots: { type: array, items: { $ref: '#/components/schemas/SyncSnapshot' } }
+        fileHistory:
+          oneOf:
+            - { $ref: '#/components/schemas/FileHistoryExport' }
+            - { type: 'null' }
+          description: 'server >= 7.52 file-history envelope (same as `SessionManifest.fileHistory`); key absent = the source is a <= 7.51 server.'
         policy: { type: array, items: { $ref: '#/components/schemas/SessionRulesRecord' } }
         anchors: { type: array, items: { $ref: '#/components/schemas/SyncAnchor' } }
 
@@ -13270,7 +13590,27 @@ components:
             carry their own `field`.) Resume legs carry the same group on 409 `resume_blocked_by_policy`
             (`blockedBy: "request.field_invalid"`). Also on 409 `checkpoint.config_refused` (server >= 7.113.0): which part of the
             row's configuration was refused — `taskConfig` (change the configuration, then decide the SAME card again) or
-            `inheritedGate` (the row's recorded mode seed is bad — the run can only be cancelled). SDK: `err.extra.field`.
+            `inheritedGate` (the row's recorded mode seed is bad — the run can only be cancelled). Also on 400 `request.field_invalid` for a
+            `settings.hooks` tool-event matcher that selects an engine alias but not its canonical name (server >= 7.115.0 / S-1025):
+            `field` is always the literal `settings.hooks` (see `detail`). SDK: `err.extra.field`.
+        detail:
+          description: >
+            🔴 TWO SHAPES under one code — branch on `field` (or the `errorCode`), never guess from the type of `detail`. On 400
+            `request.field_invalid` for a `settings.hooks` tool-event matcher (server >= 7.115.0 / S-1025; additive, the sentence and the code
+            are unchanged): an OBJECT `{ event, alias, canonical }` — `event` = the tool event of the refused group (the first refused one when
+            several are), `alias` / `canonical` = the engine catalog's alias and canonical name (closed strings, never the caller's raw bytes),
+            beside `field: "settings.hooks"`. On 400 `request.field_invalid` for the two `POST /v1/adoption` principal sentences (adoption):
+            a human-readable STRING. Other codes (`rules.*` content refusals: `reason` + human `detail`; core `checkpoint.*` mirrors) carry their
+            own `detail`; read it by `errorCode`. SDK: `err.extra.detail` (verbatim, unnamed).
+          oneOf:
+            - type: object
+              required: [event, alias, canonical]
+              additionalProperties: false
+              properties:
+                event: { type: string }
+                alias: { type: string }
+                canonical: { type: string }
+            - type: string
         count:
           type: integer
           description: 'S-904 `reason: over_cap` only — how many entries the bucket had (server >= 7.106.0). SDK: `err.extra.count`.'
@@ -13864,16 +14204,29 @@ components:
         unattended leg run under `UNATTENDED_PERMISSION_MODE=dontAsk`).
     AskClass:
       type: string
-      enum: [content_question, hook, ancestor, unverifiable_delete, transcript_write, org_rule, governance_unavailable, rule_unreadable, ask_rule, denial_limit_fallback, operator_forced, shell_floor, write_protection_unresolved, probe, write_protection, tool_marks_mcp, tool_marks_a2a, policy_rra, artifact_shared_read, mode, ordinary]
-      description: >
-        core `ASK_CLASSES` (twenty-one words as of core 7.39.0 — 7.34.0 minted twenty; `shell_floor` joined in 7.39.0 #1260 and rides
-        server >= 7.113.0) — which CLASS an ask falls in (the columns of the mode × class arbitration table).
+      enum: [content_question, hook, ancestor, unverifiable_delete, transcript_write, org_rule, governance_unavailable, rule_unreadable, ask_rule, denial_limit_fallback, requires_user_interaction, operator_forced, shell_floor, write_protection_unresolved, probe, write_protection, tool_marks_mcp, tool_marks_a2a, policy_rra, artifact_shared_read, mode, unstated, ordinary]
+      description: >
+        core `ASK_CLASSES` (twenty-two words as of core 7.40.0, twenty-three as of core 7.41.0 — 7.34.0 minted twenty; `shell_floor` joined in 7.39.0 #1260 and rides
+        server >= 7.113.0; `unstated` joined in 7.40.0 and rides server >= 7.115.0; `requires_user_interaction` joined in 7.41.0 and rides
+        server >= 7.116.0) — which CLASS an ask falls in (the columns of the mode × class arbitration table).
+        `requires_user_interaction` = the MCP server declared, in the tool's advertisement, `_meta["anthropic/requiresUserInteraction"] === true`
+        (only the boolean `true`): EVERY call of that tool asks the human, in EVERY mode including `bypassPermissions` (it is not one of the ten
+        RELEASABLE classes), and only the human's answer clears it — `settings.permissions.allow`, operator `APPROVAL_GRANT`, a skill's tool list +
+        `userInvokedSkills` and a hook's explicit allow all fail to; with no approval seat the call is refused (the server sees nothing). The frame
+        also carries `requiresRealApproval: true` / `mandated: true` (`origin: "safety_tighten"`). A client that renders cards by exhaustive `askClass`
+        adds this one word.
+        `unstated` = NOBODY STATED IT: in an ask-class mode (`default` / `acceptEdits` / `auto` / `plan`) a call to an MCP server tool or A2A skill
+        (a seat that states no permission of its own) reached the end of the fold with no layer — rule / hook / approver / classifier / mode
+        release — having said "this time is fine"; the engine raises a card with `askClass: "unstated"` (sentence `The agent requested permission to use <tool>,
+        but it has not been granted yet.`), and with no approval surface the call is refused. It is clearable (one of the ten RELEASABLE
+        classes: an allow rule — `settings.permissions.allow` / operator `APPROVAL_GRANT` — an explicit hook `permissionDecision: "allow"`, the auto-mode
+        classifier or `bypassPermissions` clears it); under `plan` only READ-ONLY server tools raise it.
         `shell_floor` = the operator's `shellGate: "always"` floor on a shell-running seat (the question the `operator_always` mandate
         word discloses), a class of its own so a set that holds another forced question still holds it; like `operator_forced` it is
         bypass-IMMUNE (not releasable).
-        CLOSED on the gate record (screened with core `isAskClass`). `bypassPermissions` releases only the nine RELEASABLE classes
+        CLOSED on the gate record (screened with core `isAskClass`). `bypassPermissions` releases only the ten RELEASABLE classes
         (`transcript_write` / `rule_unreadable` / `probe` / `write_protection` / `tool_marks_mcp` / `tool_marks_a2a` /
-        `artifact_shared_read` / `mode` / `ordinary`); every other class (deployment-authored `operator_forced`, ask / org rules, hook,
+        `artifact_shared_read` / `mode` / `unstated` / `ordinary`); every other class (deployment-authored `operator_forced`, ask / org rules, hook,
         ancestor, content question, …) asks under every mode.
     ModeRelease:
       type: object
@@ -14514,6 +14867,15 @@ components:
           properties:
             backgroundAgentStore: { type: boolean }
             hostChildEventSink: { type: boolean }
+            subagentTranscripts:
+              type: string
+              description: >
+                server >= 7.115.0 (S-744; core 7.32.0 tier now on the wire) — the deployment's SUBAGENT TRANSCRIPT TIER, so a shell can render the
+                "durable record" wording truthfully: `none` (no agent-row store: subagent records are not kept) / `rows` (rows and terminal snapshots
+                survive a restart but the CONVERSATION does not: continuable only in this process / within the session store's TTL) / `full` (an
+                ended subagent can be resumed across a restart). 🔴 OPEN SET — read it open: the three words are core's today, do not enumerate (a
+                fourth word would be swallowed into "absent"); an unknown word means "unknown tier", never treat it as `full`. ABSENT = unknown
+                (older server / older engine) — never read it as `none`. Tenant and operator frames carry it alike.
         permissionRules:
           type: object
           additionalProperties: false
@@ -14645,7 +15007,8 @@ components:
             deliberately never reported (pattern TEXT is deployment material, not an enum).
             🔴 AN EMPTY ARRAY IS NEVER EMITTED ("off" and "on to nothing" are one fact) ⇒ treat `[]` as a bad
             producer. The tier vocabulary is owned by core — do not narrow it on the consumer side.
-            ⚠️ Deployment semantics flipped in core 7.22.0: `READ_DENY_BUILTIN_TIERS` UNSET = OFF.
+            ⚠️ Deployment default (server config catalog): an ABSENT `READ_DENY_BUILTIN_TIERS` ⇒ the factory pair `credentials,agent-config`
+            is on (core 7.34.0 R-2 onward; it was OFF in 7.22.0–7.33.x); `none` = the explicit empty posture; an empty value refuses to boot.
         autoConsolidation:
           allOf: [{ $ref: '#/components/schemas/WiringManifestAutoConsolidation' }]
           description: >
@@ -15452,6 +15815,11 @@ components:
         args:
           description: '"tool_approval" only: the call''s args, secret-redacted. UNTRUSTED for display. Absent (with argsOmitted) when over the byte cap or unserializable.'
         argsOmitted: { type: boolean, enum: [true] }
+        rememberRefused:
+          type: boolean
+          enum: [true]
+          description: >-
+            server >= 7.116.0, ADDITIVE, present ONLY when true (never `false`): the "remember for this session" answer (live `allow_session` / durable `/decide` `remember:"session"`) will NOT be remembered on this card — the decision is accepted and applies once, the receipt's `rememberApplied` is `false` (existing key, not a new one), later cards of the same kind still ask. A shell reads this to decide whether to render the "allow for the session" choice instead of inferring it from `requiresRealApproval` / `mandated` / `governanceForced`. One bit for four reasons: the operator-governance gate / a human must approve each time / a mandated card / the answer would also grant more than this one call (new in 7.116.0: approving an engine `Skill` card activates the skill and frees its listed tools for the run, which the card cannot show, so it is not remembered). ABSENT = remember works on this card, OR an older server (<= 7.115.x never carries the key). Same bit on the live frame, the `approval_request` card (= `card_json`, incl. the reconnect replay), the `livePending` row, and the `/v1/approvals` `pending[]` row (+ their `/stream` frames); NOT on inbox rows.
         governanceForced:
           type: boolean
           enum: [true]
@@ -15584,6 +15952,18 @@ components:
               properties:
                 shown: { type: array, items: { type: string } }
                 total: { type: integer }
+        probeReason:
+          type: string
+          description: >
+            server >= 7.115.0 (S-733), ADDITIVE, "tool_approval" only: the PROSE reason a reversibility probe gave for tightening this ask
+            (core `AskRequest.probeReason`; the server's narrow read: a non-string / blank value ⇒ absent, more than 201 code points ⇒
+            dropped WHOLE rather than truncated, content-family redaction — the same rule as the durable face's
+            `gate.riskDescriptor.probeReason`, so the two faces carry the same bytes for the same sentence). It runs ALONGSIDE
+            `probeCause` and does not replace it: engine-minted causes ride the structured seat, a deployment-written probe can only write this
+            sentence. RENDER: prefer `probeCause`'s structure; fall back to this key when there is none; neither ⇒ no cause to render
+            (absent != "no reason"). PRESENT ONLY WHEN IT HAS A VALUE (never an empty string) and ONLY ON THE LIVE card frame —
+            the presented frame (`approval_request`) and the durable card (`card_json`) do NOT carry it (the durable twin is
+            `gate.riskDescriptor.probeReason` on the parked row). Display / triage metadata, never an adjudication input; never in `message`.
         ruleEvidence:
           type: object
           description: >
@@ -15904,6 +16284,11 @@ components:
         argsOmitted: { type: boolean, enum: [true], description: 'Present (true) only when args exceeded the byte cap. Never false.' }
         toolCallId: { type: string, description: 'The engine''s tool-call id (the `call_…` on the assistant message''s tool_use block) — same domain as ToolApprovalFrame.toolCallId.' }
         risk: { $ref: '#/components/schemas/ApprovalRiskAxes' }
+        rememberRefused:
+          type: boolean
+          enum: [true]
+          description: >-
+            server >= 7.116.0, ADDITIVE, present ONLY when true (never `false`): the "remember for this session" answer (live `allow_session` / durable `/decide` `remember:"session"`) will NOT be remembered on this card — the decision is accepted and applies once, the receipt's `rememberApplied` is `false` (existing key, not a new one), later cards of the same kind still ask. A shell reads this to decide whether to render the "allow for the session" choice instead of inferring it from `requiresRealApproval` / `mandated` / `governanceForced`. One bit for four reasons: the operator-governance gate / a human must approve each time / a mandated card / the answer would also grant more than this one call (new in 7.116.0: approving an engine `Skill` card activates the skill and frees its listed tools for the run, which the card cannot show, so it is not remembered). ABSENT = remember works on this card, OR an older server (<= 7.115.x never carries the key). Same bit on the live frame, the `approval_request` card (= `card_json`, incl. the reconnect replay), the `livePending` row, and the `/v1/approvals` `pending[]` row (+ their `/stream` frames); NOT on inbox rows.
         governanceForced:
           type: boolean
           enum: [true]
@@ -16558,16 +16943,27 @@ components:
             sessionId: { type: string, description: 'gone.ask_parked ONLY — gate reconciliation coordinate 1; drive the existing durable-gate flow with it.' }
             gateBoundCallId: { type: string, description: 'gone.ask_parked ONLY — gate reconciliation coordinate 2.' }
             gateBoundInputHash: { type: string, description: 'gone.ask_parked ONLY — gate reconciliation coordinate 3.' }
-            state: { type: string, enum: [DENIED, VOID], description: 'gone.ask ONLY — the terminal state.' }
+            state: { type: string, enum: [DENIED, VOID], description: 'gone.ask ONLY — the terminal state. server >= 7.116.0 also mints `VOID` for "the process that held the ask is gone" (local lane restart; see `deniedReason`).' }
             deniedReason:
               type: string
               description: >
                 gone.ask ONLY — attribution, GROUPED BY `state`. `DENIED` carries the single-member deny
                 vocabulary `routing_failure_fail_closed`; `VOID` carries the separate (and growing) void
-                vocabulary, e.g. `adhoc_leg_no_durable_domain`. The two vocabularies never mix.
+                vocabulary, seven words today: `run_cancelled`, `batch_aborted`, `batch_bound_elsewhere`,
+                `adhoc_leg_no_durable_domain`, `orphan_ttl_exceeded` and — new in server 7.116.0 (local lane) —
+                `crashed_before_park` (the process that held the ask crashed / was killed) and `shutdown_before_park`
+                (an orderly shutdown could not settle the card inside its grace window; a fault shape, hard to build black-box).
+                The last two are the SAME word as `GET /v1/approvals` `crashConverged[].cause`; the other six were already on the wire
+                (7.3.0 / 7.55.0 / 7.108.0) and are only registered in the server's self-minted word table by 7.116.0.
+                ABSENT = the row carries no attribution. The two vocabularies never mix; the VOID one is open (read an unknown word as "the ask ended without
+                a human decision, reason unknown").
       description: >
         410 body. THE TWO LEGS ARE DISJOINT: `gone.ask_parked` carries exactly the three gate coordinates,
-        `gone.ask` carries exactly `{state, deniedReason?}`. Routing off field presence across the legs is how a
+        `gone.ask` carries exactly `{state, deniedReason?}` (no `consumerState`).
+        🔴 server >= 7.116.0 (local lane, `DB_BACKEND=local`): after a crash / kill and a restart on the same data root, answering the PREVIOUS
+        life's still-open card is now `410 gone.ask` with `state: "VOID"` and `deniedReason` `crashed_before_park` / `shutdown_before_park` —
+        <= 7.115.x answered `200` + `consumerState: "absent"` (the run had long been reclaimed; nothing executed). An ask that was already decided
+        (decided, then the process died mid-execution) is unchanged: `409 conflict.ask_decided`. SQL backends are unchanged in 7.116.0. Routing off field presence across the legs is how a
         consumer ends up driving the wrong durable gate.
         🔴 The checkpoint token is NEVER here: the resume credential is not externally disclosed. Use
         `sessionId`.
@@ -17913,6 +18309,15 @@ components:
           properties:
             backgroundAgentStore: { type: boolean }
             hostChildEventSink: { type: boolean }
+            subagentTranscripts:
+              type: string
+              description: >
+                server >= 7.115.0 (S-744; core 7.32.0 tier now on the wire) — the deployment's SUBAGENT TRANSCRIPT TIER, so a shell can render the
+                "durable record" wording truthfully: `none` (no agent-row store: subagent records are not kept) / `rows` (rows and terminal snapshots
+                survive a restart but the CONVERSATION does not: continuable only in this process / within the session store's TTL) / `full` (an
+                ended subagent can be resumed across a restart). 🔴 OPEN SET — read it open: the three words are core's today, do not enumerate (a
+                fourth word would be swallowed into "absent"); an unknown word means "unknown tier", never treat it as `full`. ABSENT = unknown
+                (older server / older engine) — never read it as `none`. Tenant and operator frames carry it alike.
         governance:
           type: object
           description: 'OPERATOR-AUDIENCE section (presence of the four deployment governance faces). Absent on every tenant-readable face.'
@@ -18242,6 +18647,16 @@ components:
             `SESSION_AUTO_TITLE` AND who set it. Its default is the SAME on every deployment shape (true), so this
             knob has NO posture arm — an unset one reads `source: "engine-default"` and says so in `note`.
         checkpointStore: { type: boolean, description: 'A checkpoint store is wired (= the park facility exists).' }
+        approvalGrant:
+          type: array
+          items: { type: string }
+          description: >
+            server >= 7.115.0 — the operator's allow rules `APPROVAL_GRANT` (env; off by default) VERBATIM (tool-name rules are not secrets;
+            an EMPTY list = the knob is unset, count = length). It answers "who did the DEPLOYMENT state for": a matching MCP / A2A
+            server-tool call no longer raises a card for want of a statement — it releases no layer's own question (deny / ask / session rules /
+            the engine's write gate all still apply). OPERATOR face only (this endpoint is operator-only); deliberately NOT in `GET /v1/capabilities`
+            (that face says what a caller can use — see `Capabilities.settings`). Not in `required`: the key is absent on a server < 7.115.0
+            (no such knob there), which is a different fact from `[]` (knob present, unset).
 
     WiringDiagnostics:
       type: object
@@ -18327,9 +18742,15 @@ components:
       description: >-
         [2400] TR-4 — per-message queue priority on POST /v1/runs/{taskId}/steer. ACCEPTED + ENUM-VALIDATED
         FAIL-LOUD (`routes/runs.ts`; anything else is 400 `request.field_invalid`) and echoed back on the
-        receipt, but ADVISORY today: core's steer is a single-slot last-writer-wins with no per-message priority
-        or addressable drop, so a faithful priority queue (and DELETE /v1/runs/{taskId}/queue/{messageId}) waits
-        on a core seam.
+        receipt. WHETHER IT TAKES EFFECT is the server's call — read `Capabilities.fleet.steerPriority` first:
+        `"engine"` (server >=7.116.0) = the tier is handed to the engine on every delivery leg (`now` cuts the in-flight turn
+        IMMEDIATELY — the running tool receives an abort, an approval card pending on this replica is revoked, one `engine_notice`
+        `task.turn_interrupted` frame is the evidence; `next` ≡ no `priority`; `later` is delivered after the turn the run would have stopped on; parked
+        legs store the tier and deliver on the resume's / wake's first turn; replaying the same `Idempotency-Key` + text with a different effective
+        tier is 409 `steering.duplicate_input_id`); `"advisory"` (server <=7.115.x) = accepted and echoed but NOT applied —
+        core's steer was a single-slot last-writer-wins with no per-message priority or addressable drop, so a
+        faithful priority queue (and DELETE /v1/runs/{taskId}/queue/{messageId}) waited on a core seam. An absent
+        or unknown capability value means "do not assume it is applied".
 
     SteerReceipt:
       type: object
@@ -18606,6 +19027,8 @@ components:
             server 1.239 ([1392]②): on allow_session, an honest echo of whether the grant was REALLY
             recorded (true = landed in the bridge store; false = no sessionId, could not record — do not
             render "session-wide allowed"). Omitted on non-allow_session decisions and on older servers.
+            🔴 server >= 7.116.0: ALWAYS `false` on a card that carries `rememberRefused: true` (an engine `Skill` card etc.) — the decision
+            applies once and nothing is remembered (existing key, not a new one).
         updatedInputForwarded:
           type: boolean
           description: >