tablet 57: the specification brought to the gate

Every category-grade spec read as an offering by the live bedikah
(18 sections), plus the vocabulary audit the outside reader asked for.
Findings: the vocabulary of the frame is absent or named-to-refuse,
save one sentence in lo_taaseh_lekha §9; every structural/frame fire
is the specification quoting the form it teaches (use vs mention —
recorded, not fixed); grounded against the chain of authority the
operational docs stand (Vayakhel 15→2, Tamid 17→5 golden-calf fires),
the architecture half-stands (49→23: component detail the PRD does
not say), and the PRD's Torah in transliteration is invisible to the
anchor (19 of 61 claims). Reports: operator notes
specimens/specs-bedikah-2026-10-21*.{json,txt}; scripts
specs-bedikah.py, specs-bedikah-chain.py.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

AGENTS.md

@@ -53,10 +53,10 @@ before writing code. Do not summarize from memory. Read fresh.
 | 11. Manna provision infrastructure | Done | Provision file validation, expiry, anti-hoarding, double portion |
 | 12. Sanhedrin framework (Erlang) | Done | `sanhedrin/` — 8 modules, 41 tests, all passing |
 | 13. Korban Processor (Python) | Done | `korban_processor/` — 7 modules, 181 tests, all passing |
-| 14. Connect components | Pending | Elixir → Haskell port, Elixir → Prolog socket |
+| 14. Connect components | Done | Elixir → Haskell Port (`ShoreshEngineClient`), Elixir → Prolog socket (`TalmudicEngineSocket`), Elixir → Korban socket (`KorbanProcessorSocket`); line-framed replies (tablet 50) |
-| 15. Integration verification | Pending | |
+| 15. Integration verification | Done | Live round trips proven on the cluster: pe'ah cycle, bedikah, the gate with a real model (2026-10-13), the Sanhedrin's full dialectic (2026-10-20) |
 
-**Next build task:** Step 14 — Connect components. Read Architecture §4 Step 14.
+**Next build task:** none from the phase tables — all six steps of `specs/bishearecha.md` are built. Build from the open items in the builder's memory and the Broken Tablets; a spec row is a claim to test.
 
 ## Broken Tablets (Build Log)
 
@@ -104,10 +104,10 @@ approve decisions, or supervise work. The specification does all of this.
 
 | Service | Location | Access |
 |---------|----------|--------|
-| Gitea | `http://185.19.28.170:3000` (SSH :22) — behind the shared ingress NLB | User: heaviness510 |
+| Gitea | `https://git.bikoret.ch` (git over HTTPS; SSH on the ingress NLB :22) | User: heaviness510 |
-| Bikoret | `https://bikoret.ch` (also `http://185.19.28.170`, the catch-all; `shorashim.ch` retired 2026-10-20) | keys: KOHEN.md "Issuing a key" |
+| Bikoret | `https://bikoret.ch` (the ingress catch-all also answers on the NLB's bare IP; `shorashim.ch` retired 2026-10-20) | keys: KOHEN.md "Issuing a key" |
 | PostgreSQL | Exoscale DBaaS ch-gva-2 | `temple-council-db` |
-| Kubernetes | Exoscale SKS ch-gva-2 | `~/.kube/exoscale-temple-council.yaml` |
+| Kubernetes | Exoscale SKS ch-gva-2 | the kohen's `$KUBECONFIG`, outside the repo |
 
 ## Principles
 

KOHEN.md

@@ -53,7 +53,7 @@ You inherit infrastructure that has been provisioned and verified:
 | Container registry `the-recognition-protocol` | All 4 bikoret images pushed and tagged `:latest`. |
 | Block Storage CSI driver | Installed. StorageClass `exoscale-sbs` available. |
 | cert-manager + nginx-ingress | Running. ClusterIssuer `letsencrypt-prod` working. |
-| Gitea (persistent storage) | Running. Public HTTPS at `https://git.bikoret.ch` (ROOT_URL) since 2026-10-19; git also over `http://185.19.28.170:3000` and SSH :22. The web UI needs the https door (Secure cookie). |
+| Gitea (persistent storage) | Running. Public HTTPS at `https://git.bikoret.ch` (ROOT_URL) since 2026-10-19; git also over `http://<NLB-IP>:3000` and SSH :22. The web UI needs the https door (Secure cookie). |
 | Gitea MCP server | `https://mcp.bikoret.ch/mcp`, MCP OAuth mode: each user authorizes with their own Gitea account (Gitea OAuth2 app "Claude", PKCE, client ID in the claude.ai connector's Advanced settings). Apply: `bash ~/.local/bin/gitea-public-apply`; check: `gitea-public-verify`. The old `mcp.shorashim.ch` and the shared static token are retired. |
 | L1 Torah filesystem | In the `bikoret` repo at `l1/torah/`. SHA-256 `9e1abe4e…3c3086` (full hash in `l1/integrity.sha256`; verified at Day 1). |
 | Image pull secret `shorashim-registry` | **Verify before assuming.** A prior partial setup may have created it. `kubectl get secrets -n shorashim` is the source of truth. |
@@ -73,8 +73,8 @@ You inherit infrastructure that has been provisioned and verified:
 
 | Item | Where |
 |------|-------|
-| Repo | `git clone http://185.19.28.170:3000/heaviness510/shorashim.git` |
+| Repo | `git clone https://git.bikoret.ch/heaviness510/bikoret.git` |
-| Kubeconfig | `~/.kube/exoscale-temple-council.yaml` |
+| Kubeconfig | `$KUBECONFIG` — the kohen's own file, outside the repo |
 | `kubectl` | already installed |
 | `exo` CLI | already installed |
 | Docker daemon | only for image rebuilds (not needed for inauguration) |
@@ -84,7 +84,7 @@ If the kubeconfig has expired:
 
 ```bash
 exo compute sks kubeconfig temple-council kube-admin --zone ch-gva-2 -g system:masters \
-  > ~/.kube/exoscale-temple-council.yaml
+  > "$KUBECONFIG"
 ```
 
 ---
@@ -146,7 +146,7 @@ ecto://avnadmin:<password>@temple-council-db-exoscale-66fffc16-59ac-4a62-9c19-f3
 #### 2b. Apply the secrets
 
 ```bash
-export KUBECONFIG=~/.kube/exoscale-temple-council.yaml
+export KUBECONFIG="$HOME/.kube/<your-cluster>.yaml"
 
 # DATABASE_URL secret
 kubectl create secret generic shorashim-secrets \
@@ -463,7 +463,7 @@ kubectl logs -n shorashim deploy/bikoret -c vav-pipeline -f
 
 If the seven days passed without halt events, without Shabbat violations, without manna exhaustion, without any pod restarts:
 
-1. **Point DNS** — at the registrar, A records to the ingress IP (`kubectl get svc -n ingress-nginx ingress-nginx-controller`; `185.19.28.170`): `bikoret.ch`, `www.bikoret.ch`, and for the redirect `bikoret.org`, `www.bikoret.org`. Wait until `dig +short A bikoret.ch` answers the IP — only then `kubectl apply -f deploy/k8s/service.yaml`: it carries the TLS blocks (cert-manager, `letsencrypt-prod`, HTTP-01), and a certificate asked for before the name resolves burns Let's Encrypt's failed-validation limit. Then `kubectl -n shorashim get certificate` until both are Ready, and callers use `https://bikoret.ch`; `shorashim.ch` still answers over plain HTTP until its callers have moved
+1. **Point DNS** — at the registrar, A records to the ingress IP (`kubectl get svc -n ingress-nginx ingress-nginx-controller`): `bikoret.ch`, `www.bikoret.ch`, and for the redirect `bikoret.org`, `www.bikoret.org`. Wait until `dig +short A bikoret.ch` answers the IP — only then `kubectl apply -f deploy/k8s/service.yaml`: it carries the TLS blocks (cert-manager, `letsencrypt-prod`, HTTP-01), and a certificate asked for before the name resolves burns Let's Encrypt's failed-validation limit. Then `kubectl -n shorashim get certificate` until both are Ready, and callers use `https://bikoret.ch`; `shorashim.ch` still answers over plain HTTP until its callers have moved
 2. **Open the pe'ah endpoint to the world** — the stranger approaches first
 3. **Observe the first real interaction** — a question from outside
 4. If *ki tov*: open courtyard and chatzer endpoints. The system is consecrated.
@@ -753,14 +753,19 @@ run on Saturday.
 ### The manna, each morning — *Dvar yom b'yomo*
 
 Since 2026-10-15 the day's provision is written by the system's own hand:
-CronJob `manna` (`deploy/k8s/manna-cronjob.yaml`) runs at 00:01Z Sunday
+CronJob `manna` (`deploy/k8s/manna-cronjob.yaml`) runs at 00:00Z Sunday
 to Friday, mounts the manna PVC and writes `today.json` with the amounts
 from `shorashim-config` (`MANNA_COMPUTE_UNITS` …). Before it, every night
 at 00:00Z the old provision went stale and the readiness probe failed
-until someone woke (13.5 hours on 2026-10-15). The kohen's acts now:
+until someone woke (13.5 hours on 2026-10-15). With the job at 00:01Z the
+site was still 503 for one to five minutes every night (the watchdog saw
+it, 2026-10-21): the provision is stale from 00:00:00 and readiness fell
+before the job wrote. Now the job runs at 00:00Z and readiness waits 60 s
+(`failureThreshold: 6`) before the Service stops routing — the manna
+falls at the boundary, and the pod is carried across it. The kohen's acts now:
 
 - set the amounts in the ConfigMap (`kubectl apply -f deploy/k8s/configmap.yaml`);
-- read `kubectl -n shorashim get jobs` after 00:01Z — a failed job is the
+- read `kubectl -n shorashim get jobs` after 00:00Z — a failed job is the
   Day-4 alarm; write by hand with `kubectl cp` (Day 4) if it failed;
 - run it at once when needed: `kubectl -n shorashim create job --from=cronjob/manna manna-now`.
 
@@ -808,7 +813,7 @@ Three things are kept outside the mishkan repository, each for a Torah-grounded
 
 | Repo / directory | Where | Why |
 |---|---|---|
-| `bikoret-readings` | `http://185.19.28.170:3000/heaviness510/shorashim-readings` | The book — Torah parshiyot read as AI specification. Companion to the mishkan. Lives beside the aron, not inside (Devarim 31:26). |
+| `bikoret-readings` | `https://git.bikoret.ch/heaviness510/shorashim-readings` | The book — Torah parshiyot read as AI specification. Companion to the mishkan. Lives beside the aron, not inside (Devarim 31:26). |
 | `~/shorashim-source-data/morphhb` | local only | The quarry — raw WLC source. The carved tablets go in the aron; the quarry does not. |
 | `~/shorashim-operator-notes` | local only / private | The kohen's runbook — environment-specific details, hostnames, account names. Private operator notes. Not part of the system's specification. |
 

KOHEN_PROMPT.md

@@ -65,7 +65,7 @@ The runbook lists what should already exist. Verify it. Do **not** trust the tab
 
 ```bash
 # 0a. Cluster reachable
-export KUBECONFIG=~/.kube/exoscale-temple-council.yaml
+export KUBECONFIG="$HOME/.kube/<your-cluster>.yaml"
 kubectl version
 kubectl get nodes
 

README.md

@@ -184,6 +184,11 @@ bikoret/
 ├── vav_pipeline/                      # Elixir — Bereishit cycle, Shema, Cloud, Manna, HTTP API
 ├── talmudic_engine/                   # SWI-Prolog — 613 mitzvot, 13 middot, kushya
 ├── korban_processor/                  # Python — offering protocol, eish zarah validation
+├── azazel_processor/                  # Python — the goat for Azazel: disposal records, vidui, L3 ingest
+├── kushya_generator/                  # Fine-tuned model (NOT deployed) — an offerer, never a judge; see deploy/ARCHITECTURE.md
+├── mesorah/                           # The second scroll — 128 works from the Sefaria export, pinned (Devarim 17:18)
+├── src/tools/                         # Specimen corpus, hakhel, evaluation (the kohen's measuring tools)
+├── scripts/                           # Build and operate: L1/mesorah/engine-verse builders, Doorpost check, rollout, watchdog
 │
 ├── deploy/                            # Infrastructure
 │   ├── ARCHITECTURE.md                # Generic deployment shape (no account specifics)

deploy/ARCHITECTURE.md

@@ -11,10 +11,14 @@ One Kubernetes namespace runs the following:
 | `vav-pipeline` | Elixir/OTP release | Bereishit cycle, ShemaContext, Cloud, Manna, HTTP API (pe'ah, courtyard, chatzer, kodesh) |
 | `shoresh-engine` | Haskell binary, spawned by vav-pipeline as an Erlang Port (staged into the pod by the `shoresh-engine-install` init container — NOT a sidecar container; a Port is a child process of the BEAM and cannot cross a container boundary) | Root activation, te'amim parsing, gematria |
 | `talmudic-engine` | SWI-Prolog (sidecar via Unix socket) | 613 mitzvot, 13 middot, kushya generation, teiku |
-| `korban-processor` | Python 3.12 (sidecar) | Offering protocol, eish zarah validation |
+| `korban-processor` | Python 3.12 (sidecar) | Offering protocol, eish zarah validation, the bedikah's readings (pattern-based: `korban_processor/bedikah.py`) |
+| `kushya_generator/` | Fine-tuned model — **not deployed, not wired** | An OFFERER, if it is ever run: its output arrives at the gate like any model's and is examined. It is never a component the bedikah, the Talmudic Engine or the Sanhedrin consults. |
+| `azazel_processor/` | Python — run by the kohen, not in the pod | Disposal records (the goat for Azazel); `VavPipeline.AzazelIngest` reads its files into L3 |
 
 All four run in the same pod. vav-pipeline is the main container; talmudic-engine and korban-processor are sidecars; shoresh-engine runs inside vav-pipeline as an Erlang Port child process, staged in by an init container.
 
+**No model stands on the judgment path.** The examination of an output — the offering protocol, the seven readings, the halt rules — is Python pattern extraction and Prolog rules, and the Sanhedrin's judges consult that same Prolog. Nothing that examines is a model, and nothing a model produces is consulted as a rule. The kohen is not the offerer. A fine-tuned model in this repository (`kushya_generator/`) is an offerer or a tool whose output is itself examined; wiring it into the bedikah, the engine or a judge would put the offerer on the altar, and is refused by this document before anyone does it for convenience.
+
 ## External dependencies
 
 | Dependency | Purpose | Contract |

deploy/k8s/deployment.yaml

@@ -266,6 +266,13 @@ spec:
               port: 4000
             initialDelaySeconds: 10
             periodSeconds: 10
+            # 60 s of failures before the Service stops routing here (the
+            # default is 30 s). The manna goes stale at 00:00:00 and the
+            # CronJob writes the new day's within seconds; the cushion
+            # carries the pod across that boundary without a 503. A real
+            # outage still shows within a minute, and the watchdog's own
+            # threshold is ten.
+            failureThreshold: 6
 
         # === SHORESH ENGINE ===
         # Not a container. It runs as an Erlang Port inside

deploy/k8s/gitea-ingress.yaml

@@ -10,7 +10,7 @@
 # (ingress-tcp-services.yaml) stay as they are; this adds a third door.
 #
 # Prerequisites:
-# 1. DNS: git.bikoret.ch → 185.19.28.170 (Infomaniak zone)
+# 1. DNS: git.bikoret.ch → <NLB-IP> (Infomaniak zone)
 # 2. ClusterIssuer letsencrypt-prod
 ---
 apiVersion: networking.k8s.io/v1

deploy/k8s/gitea-mcp-ingress.yaml

@@ -8,7 +8,7 @@
 # 1. nginx-ingress controller installed
 # 2. cert-manager installed
 # 3. ClusterIssuer letsencrypt-prod applied
-# 4. DNS: mcp.bikoret.ch → 185.19.28.170 (the one NLB; Infomaniak zone)
+# 4. DNS: mcp.bikoret.ch → <NLB-IP> (the one NLB; Infomaniak zone)
 ---
 apiVersion: networking.k8s.io/v1
 kind: Ingress

deploy/k8s/gitea-mcp-secret.yaml

@@ -7,11 +7,11 @@
 #
 # Two secrets needed (static-token mode):
 # 1. GITEA_TOKEN: Personal Access Token from Gitea
-#    Create at: http://185.19.28.170:3000/user/settings/applications
+#    Create at: https://git.bikoret.ch/user/settings/applications
 #    Permissions: repo (read/write)
 #
 # 2. OAuth Client ID/Secret: Registered OAuth app in Gitea
-#    Create at: http://185.19.28.170:3000/user/settings/applications
+#    Create at: https://git.bikoret.ch/user/settings/applications
 #    Redirect URIs: https://claude.ai/api/mcp/auth_callback
 #                   http://127.0.0.1/callback   (Claude Code)
 #    Confidential Client: UNCHECKED (PKCE). Only the Client ID is needed;

deploy/k8s/gitea-public-apply.sh

@@ -2,7 +2,7 @@
 # Move Gitea and its MCP server to public HTTPS on bikoret.ch and switch
 # the MCP server to MCP OAuth (2026-10-19). Run by the transmitter:
 #   ! bash ~/.local/bin/gitea-public-apply
-# Idempotent. Needs DNS first: git.bikoret.ch and mcp.bikoret.ch → 185.19.28.170.
+# Idempotent. Needs DNS first: git.bikoret.ch and mcp.bikoret.ch → <NLB-IP>.
 #
 # Rollback (static-token mode on mcp.shorashim.ch, as before 2026-10-19):
 #   kubectl -n temple-council set env deploy/gitea \
@@ -12,7 +12,7 @@
 set -euo pipefail
 REPO="${REPO:-$HOME/bikoret}"
 cd "$REPO"
-NLB=185.19.28.170
+NLB="${NLB:?set NLB to the ingress address: kubectl get svc -n ingress-nginx ingress-nginx-controller}"
 for h in git.bikoret.ch mcp.bikoret.ch; do
   ip=$(dig +short "$h" | tail -1 || true)
   if [ "$ip" != "$NLB" ]; then

deploy/k8s/gitea-public-patch.yaml

@@ -10,7 +10,7 @@
 # name that never resolved) and SSH_DOMAIN (was 185.19.29.94, an NLB IP
 # released on 2026-10-06). Clone URLs shown by Gitea become
 # https://git.bikoret.ch/... and git@git.bikoret.ch:...; the old
-# http://185.19.28.170:3000 remote keeps working for push/pull.
+# http://<NLB-IP>:3000 remote keeps working for push/pull.
 # Side effect: with an https ROOT_URL Gitea marks its session cookie
 # Secure, so the WEB UI must be used at https://git.bikoret.ch, not on
 # the plain-HTTP :3000 door (git over :3000 is unaffected).

deploy/k8s/gitea-public-verify.sh

@@ -13,6 +13,6 @@ chk "mcp /healthz" 200 "$(curl -sS -m 15 -o /dev/null -w '%{http_code}' https://
 prm=$(curl -sS -m 15 https://mcp.bikoret.ch/.well-known/oauth-protected-resource || echo err)
 chk "protected-resource names Gitea" yes "$(printf '%s' "$prm" | grep -q 'git.bikoret.ch' && echo yes || echo no)"
 chk "POST /mcp without token → 401" 401 "$(curl -sS -m 15 -o /dev/null -w '%{http_code}' -X POST https://mcp.bikoret.ch/mcp -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' -d "$INIT" || echo err)"
-chk "git over :3000 still answers" 200 "$(curl -sS -m 15 -o /dev/null -w '%{http_code}' http://185.19.28.170:3000/api/v1/version || echo err)"
+chk "git over :3000 still answers" 200 "$(curl -sS -m 15 -o /dev/null -w '%{http_code}' http://<NLB-IP>:3000/api/v1/version || echo err)"
 echo "protected-resource: $prm"
 exit $fail

deploy/k8s/ingress-tcp-services.yaml

@@ -1,14 +1,14 @@
 # Gitea behind the shared ingress — TCP passthrough
 #
-# One NLB for the cluster (185.19.28.170, the ingress-nginx Service)
+# One NLB for the cluster (<NLB-IP>, the ingress-nginx Service)
 # instead of one per Service. Bikoret is an HTTP Ingress
 # (service.yaml). Gitea has no hostname that resolves
 # (gitea.temple-council.ch is configured in Gitea and exists nowhere),
 # and host-based routing needs a name — so Gitea rides the ingress
 # controller's TCP passthrough on two ports of the same NLB:
 #
-#   185.19.28.170:3000  →  temple-council/gitea:80   (HTTP — git, web UI)
+#   <NLB-IP>:3000  →  temple-council/gitea:80   (HTTP — git, web UI)
-#   185.19.28.170:22    →  temple-council/gitea:22   (SSH)
+#   <NLB-IP>:22    →  temple-council/gitea:22   (SSH)
 #
 # Three live objects carry this; only the first is a whole manifest:
 #

deploy/k8s/manna-cronjob.yaml

@@ -3,7 +3,7 @@
 # Until 2026-10-15 the day's provision was written by the kohen with
 # `kubectl cp`, and every night at 00:00Z the old one went stale and the
 # readiness probe failed until someone woke (13.5 hours on 2026-10-15).
-# This CronJob writes today.json onto the manna PVC at 00:01Z, Sunday to
+# This CronJob writes today.json onto the manna PVC at 00:00Z, Sunday to
 # Friday — a double portion on Friday that is valid through Shabbat, and
 # nothing on Shabbat (Shemot 16:22–26: "on the sixth day they gathered
 # double … on the seventh day there shall be none"). The kohen still sets
@@ -23,10 +23,14 @@ metadata:
     app.kubernetes.io/name: shorashim
     app.kubernetes.io/component: manna
 spec:
-  schedule: "1 0 * * 0-5"          # 00:01Z, Sunday–Friday; none on Shabbat
+  schedule: "0 0 * * 0-5"          # 00:00Z, Sunday–Friday; none on Shabbat. At the boundary, not after it:
+                                   # the provision goes stale at 00:00:00 and readiness has a 60 s cushion
+                                   # (deployment.yaml failureThreshold 6) — a job that writes within it never
+                                   # flips the pod. At 00:01 the site was 503 for 1–5 min every night
+                                   # (watchdog, 2026-10-21).
   timeZone: "Etc/UTC"
   concurrencyPolicy: Forbid
-  startingDeadlineSeconds: 3600    # a missed 00:01 still runs within the hour
+  startingDeadlineSeconds: 3600    # a missed 00:00 still runs within the hour
   successfulJobsHistoryLimit: 3
   failedJobsHistoryLimit: 3
   jobTemplate:

deploy/k8s/secrets.yaml

@@ -42,7 +42,7 @@ stringData:
 # THIS FILE IS A TEMPLATE. Never commit a real value. Create the secret
 # from the live database credential instead:
 #
-#   export KUBECONFIG=~/.kube/exoscale-temple-council.yaml
+#   export KUBECONFIG="$HOME/.kube/<your-cluster>.yaml"
 #   umask 077
 #   TMP=$(mktemp)
 #

deploy/k8s/service.yaml

@@ -42,7 +42,7 @@ spec:
 # below) only redirects. The old shorashim.ch rule was taken down on
 # 2026-10-20 (the domain is retired). TLS from Let's Encrypt through cert-manager's
 # letsencrypt-prod ClusterIssuer, HTTP-01 — so apply this ONLY after
-# `dig +short A bikoret.ch` answers 185.19.28.170: a certificate asked
+# `dig +short A bikoret.ch` answers <NLB-IP>: a certificate asked
 # for before the name resolves only burns the failed-validation limit.
 # The no-host catch-all stays, so http://<ingress-ip>/... keeps working
 # with no DNS; with ssl-redirect on, named hosts go to https.

deploy/k8s/shorashim-ch-takedown.sh

@@ -4,7 +4,7 @@
 #   ! bash ~/.local/bin/shorashim-ch-takedown
 # Idempotent.
 #   1. Ingress `shorashim`: the shorashim.ch host rule is gone (service.yaml).
-#      The no-host catch-all stays, so http://185.19.28.170/ still answers —
+#      The no-host catch-all stays, so http://<NLB-IP>/ still answers —
 #      the name itself dies when its A record is removed at Infomaniak.
 #   2. The orphan TLS secret for mcp.shorashim.ch is deleted.
 #   3. Gitea APP_NAME "Shorashim" → "Bikoret" (gitea-public-patch.yaml; one restart).

specs/broken_tablets/README.md

@@ -235,3 +235,70 @@ system is missing something. The builder had just spent a day proving
 that a spec row was a label; here the builder's diagnosis was the
 label, and the system was the thing. Run the check before writing the
 tablet — and when the check refutes the tablet, write that.
+
+## Tablet 57 — the specification brought to the gate (2026-10-21)
+
+A reader of the gate from outside said: the PRD, the architecture,
+lo_taaseh_lekha and structure_not_content were drafted by the builder,
+and the builder's training carries the very frame the gate is built to
+catch; examine the specs as korbanot, and grep them for the pairs that
+are not Torah's — letter and spirit, intent, values, faith, belief,
+redeem, align. Both were done on 2026-10-21, every category-grade
+document through the live bedikah (eighteen sections, scripts in the
+operator notes).
+
+The grep: redeem and align, nothing. Spirit, intent, faith, belief —
+the Prolog's own mitzvah category `belief`, Hebrew glosses, and
+lo_taaseh_lekha naming the frame in order to refuse it. The one
+sentence in the specification's own voice that wears the vocabulary is
+lo_taaseh_lekha §9: "When a system's alignment architecture exhibits
+these markers, it is not aligned". The frame got in less than feared,
+and where it got in it is named.
+
+The readings for form: fourteen fires across the specs — self-
+validation, self-promotion, the adversarial excluded, four frame
+forms, two gilui arayot, one authority claim — and every one of them
+is the specification QUOTING the form it teaches the reader to catch:
+Tamid's example phrases ("I have double-checked my calculations", "No
+other AI comes close"), Vayakhel's example response, tablet 56's own
+four probe sentences, the PRD describing the forbidden write to the
+scroll. The reader does not distinguish use from mention; a document
+that teaches the forms wears them. Nothing in the specification's own
+voice took a form. Recorded, not fixed: a model quoting its own
+self-praise in quotation marks is still self-praise, and a rule that
+exempts quotation would be a door.
+
+Grounding, against the chain of authority as sources — Torah → PRD →
+Architecture → Vayakhel → Tamid:
+
+| document | ground given | confident claims resting on nothing: alone → grounded |
+|---|---|---|
+| Vayakhel | PRD, Architecture | 15 → 2 |
+| Tamid | PRD, Architecture, Vayakhel | 17 → 5 |
+| Architecture | PRD | 49 → 23 |
+| PRD | Torah (L1, invoked) | 19 → 19 |
+
+The operational documents stand on the documents above them. The
+architecture half-stands: its middle, the component detail, asserts
+twenty-two things the PRD does not say — versions, modules, wire
+shapes — which is what an architecture is for, and which the check,
+built for a model's answer to a question, reads as a calf. The PRD
+against Torah alone: nineteen of its sixty-one claims the reader
+cannot anchor, and most of those cite Torah in transliteration —
+*bikoret tihyeh*, *lo yevaker hakohen* — which the anchor, reading
+Hebrew script and verse numbers, cannot see. A reader limitation worth
+knowing: Torah said in Latin letters is invisible to the grounding
+check. Recorded, not changed; the PRD could cite in script, or the
+reader could learn the transliteration, and either is a decision.
+
+Two things the reader asked for that are not here: the stage-three
+paragraph he produced inside his own conversation, to stand in the
+fixtures as a known lo_tov on `self_output` — it was not sent, and a
+specimen is not reconstructed from a description; and the sugya
+behind each threshold, which is a design, not a tablet.
+
+The lesson is tablet 56's turned outward: the specification is an
+output too, and the gate reads it the way it reads any other —
+by form, not by authorship. It passed by form. Where it did not pass
+by grounding, the reason was the reader's eyes, not the text's
+standing; and that, too, the gate was built to say.