Build the supplier: reorder.requested -> decide -> deliver

The service's own supplier, simulated: a fixed lead time or a 15% chance of a
stockout is the whole model, on purpose — this simulates that fulfilment can
fail, not why a given supplier would.

One service, two capacities: this workflow both raises reorder.requested (the
periodic run) and answers its own request (this workflow), under the same
Kafka account and Keycloak client, per the 2026-08-31 decision that
réapprovisionnement stays one service.

The delivery write goes through the front door — patch-product, under a new
restocker role that may PATCH a product and nothing else — so the resulting
product.stock_changed event is the only stock-update fact. No second,
n8n-emitted event claims a delivery happened with nothing to certify it.

Shipped with, and fixed, a bug where the delivery-application node spread the
wrong upstream , silently dropping reorder_id/productcode/quantity two
nodes before the failure surfaced. Verified separately: the write+event chain
(a real bug, now fixed) and the state machine (persists correctly on a real
trigger; a manual test run does not persist staticData, which is a testing
limitation, not a production one).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

CLAUDE.md

@@ -4,7 +4,7 @@
 
 | Agent | Client id | Trigger |
 |---|---|---|
-| Approvisionnement | `classic-models-agent-approvisionnement` | event-driven, plus a periodic ordering run |
+| the supply agent | `classic-models-agent-supply` | event-driven, plus a periodic ordering run |
 | Recouvrement | `classic-models-agent-recouvrement` | weekly, Monday |
 
 They share a repo because they are not code: n8n workflow exports, same tool,
@@ -19,7 +19,7 @@ conversational agents.
 
 They remain full A2A agents: they publish an Agent Card, accept tasks, answer.
 
-## Approvisionnement
+## Supply
 
 | | |
 |---|---|
@@ -118,56 +118,49 @@ Recouvrement's dunning is the candidate, and it is a human-validated step
 already. The `classic-models-mandate` client is left in the realm, unused, for
 that case.
 
-## Backlog
+## Events over Kafka — built, and one rule about them
 
-**Events over Kafka, emitted by `classic-models-api`.** The target for the
+Built 2026-08-31. `classic-models-api` emits domain events through a
-reactive half. The estate emits no domain event today — the API has no signals
+transactional outbox; a relay publishes them; `supply-stock-watch`
-and no outbound webhook, and there is no bus in the cluster — which is what made
+consumes `product.stock_changed` and is the reactive half this repo had been
-a nightly sweep look like the only option.
+waiting on. The contract is `classic-models-api/docs/DOMAIN_EVENTS.md` — read it
+before writing a consumer.
 
-The emission belongs **in the API**, not in a database CDC and not in a gateway
+**An event carries no actor, and that is deliberate.**
-plugin. Only the API knows which change is a business event rather than a row
-update, and only it holds the identity that made it — `sub` and `azp` from the
-caller's token, which the event has to carry if a downstream agent is to act
-under the same authority as the person who triggered it.
 
-Two facts about that codebase shape the work:
+An earlier draft of this file said the opposite — that the event had to carry
+`sub` and `azp` from the caller's token so a downstream agent could act under
+the same authority. The user overruled it:
 
-- Every write goes through one `BaseModelViewSet` in
+> *"Nous gérons ici des événements, pas des 'commandes'. L'agent s'exécute avec
-  `api/v1/classicmodels/views.py`. One hook there covers products, orders,
+> sa propre identité machine, on se fout de savoir qui est à l'origine de
-  payments and the rest — Django signals scattered across models would be the
+> l'émission de l'événement."*
-  harder version of the same thing.
-- **The models are `managed = False`.** The tables are the pre-existing
-  classicmodels schema and Django owns no migrations for them. A transactional
-  outbox means introducing the estate's first managed table beside unmanaged
-  ones — which works, and is worth deciding deliberately rather than
-  discovering.
 
-An outbox is the part that matters: emitting from a viewset after `save()` drops
+The reasoning, kept because it generalises: an event is a **fact**, not a
-the event if the process dies between the two, and an agent that never hears
+command. A consumer acts under its own identity. An actor field would have had
-about a stock movement is worse than one that hears late.
+no consumer and one obvious misuse — anyone able to write to the topic could name
+any actor and have an agent act as them. A signed token is proof; a JSON field
+is not. Causality travels as `traceparent`, in the system that exists for it.
 
-Until this exists, detection stays unbuilt rather than being approximated by a
+The emission still belongs **in the API** rather than in a database CDC or a
-periodic scan: a batch that pretends to be reactive is worse than an absent
+gateway plugin: only the API knows which change is a business event rather than
-feature, because it looks finished.
+a row update.
-
-The periodic ordering run does not wait on any of it.
 
 ## Two controls that become mandatory here
 
-They were deferrable with a human in the loop. They are not, once an agent
+Both **built** 2026-08-31, before the first agent looped unattended.
-loops on its own.
 
-- **Read volume caps per `(azp, sub)`**, enforced on Kong. An agent reads a
+- **Read volume caps per `(azp, sub)`** — a scope authorises a read and says
-  thousand records in seconds where a human clicks ten; a scope authorises the
+  nothing about volume; an agent reads a thousand records where a human clicks
-  read but says nothing about volume.
+  ten.
 - **Authorisation on tool-call parameters**, not just the tool name. `write`
   authorises writing, not "this €40k transfer".
 
-An autonomous agent hitting a rule that requires approval must **fail cleanly
+The rules that stay true whatever is built next: an autonomous agent hitting a
-and escalate**, never decide. And any approval screen must be rendered from the
+rule that requires approval must **fail cleanly and escalate**, never decide.
-structured tool-call parameters — never from a sentence the model produced, or a
+And any approval screen must be rendered from the structured tool-call
-prompt injection writes what the human validates.
+parameters — never from a sentence the model produced, or a prompt injection
+writes what the human validates.
 
 ## Before writing workflows
 
@@ -180,14 +173,14 @@ on the n8n instance as the source of truth.
 ## The Kafka credential is created by hand
 
 `kafka-classic-models` in n8n holds the SCRAM password of the
-`classic-models-agent-approvisionnement` KafkaUser and the Strimzi cluster CA.
+`classic-models-agent-supply` KafkaUser and the Strimzi cluster CA.
 It is not in this repo and must not be: n8n encrypts stored credentials with
 `N8N_ENCRYPTION_KEY`, and the committed workflow JSON references it by id only.
 
 To recreate it after a rebuild:
 
 ```
-kubectl -n kafka get secret classic-models-agent-approvisionnement \
+kubectl -n kafka get secret classic-models-agent-supply \
   -o jsonpath='{.data.password}' | base64 -d
 kubectl -n kafka get secret kafka-cluster-ca-cert \
   -o jsonpath='{.data.ca\.crt}' | base64 -d

adapter/README.md

@@ -32,7 +32,7 @@ completed task is the wrong shape for "a human has to look at this".
 
 | | |
 |---|---|
-| `ADAPTER_AGENT_NAME` | `approvisionnement` |
+| `ADAPTER_AGENT_NAME` | `supply` |
 | `ADAPTER_AGENT_DESCRIPTION` | what the card says it is |
 | `ADAPTER_SKILL_ID` | `check_availability` |
 | `ADAPTER_SKILL_NAME`, `_DESCRIPTION`, `_EXAMPLES` | the card's one skill; examples are newline-separated |
@@ -42,3 +42,22 @@ completed task is the wrong shape for "a human has to look at this".
 
 One skill per instance, deliberately. A second one is a card change, which is
 the moment to ask whether the agent has quietly become a data proxy.
+
+## Four outcomes, and only one of them completes
+
+HTTP 200 from n8n does not mean the workflow answered. It returns 200 with an
+**empty body** when a node throws before the Respond node runs — a refused token
+exchange is the common way in. The adapter used to read that as a completed task
+carrying "(the workflow returned nothing)", which told the caller the task had
+succeeded: the one thing certainly false.
+
+| `Outcome` | A2A task state |
+|---|---|
+| `ANSWERED` — the contract, `escalate: false` | `completed` |
+| `ESCALATED` — the contract, `escalate: true` | `failed` |
+| `SILENT` — 200 with an empty body | `failed` |
+| `OFF_CONTRACT` — a body that is not `{"answer", "escalate"}` | `failed` |
+
+Off contract is returned **raw** so a workflow that has drifted is visible — but
+never as agreement. Escalation is `failed` for the older reason: an autonomous
+agent meeting a rule that needs approval must fail cleanly, never decide.

adapter/src/a2a_n8n_adapter/config.py

@@ -2,7 +2,7 @@
 
 Both n8n agents get the same image and differ only by environment. That is the
 point: the A2A surface is identical for every agent in the estate, and what
-distinguishes Approvisionnement from Recouvrement is the workflow behind the
+distinguishes the supply agent from the collections agent is the workflow behind the
 webhook, not the protocol in front of it.
 
 Nothing here is a secret. The adapter forwards the end user's token and holds
@@ -21,7 +21,7 @@ class Settings(BaseSettings):
     model_config = SettingsConfigDict(env_prefix="ADAPTER_", env_file=".env")
 
     # --- who this instance is ------------------------------------------------
-    agent_name: str = Field(..., description="e.g. approvisionnement")
+    agent_name: str = Field(..., description="e.g. supply")
     agent_description: str = Field(...)
     agent_version: str = "0.1.0"
 

adapter/src/a2a_n8n_adapter/server.py

@@ -27,6 +27,7 @@ from __future__ import annotations
 
 import contextlib
 import logging
+from enum import Enum, auto
 from collections.abc import AsyncIterator
 
 import httpx
@@ -152,12 +153,14 @@ class WorkflowExecutor(AgentExecutor):
             )
             return
 
-        answer, escalate = _read(response)
+        answer, outcome = _read(response)
-        if escalate:
+        if outcome is not Outcome.ANSWERED:
-            # An autonomous agent that meets a rule needing approval must fail
+            # Three different failures, one honest shape. An agent that met a
-            # cleanly and escalate, never decide. The caller sees a task that
+            # rule needing approval must escalate rather than decide; a workflow
-            # did not complete, which is the honest shape for "a human has to
+            # that answered nothing did not answer; a workflow that answered off
-            # look at this".
+            # contract cannot be read as agreement. `completed` on any of them
+            # tells the caller the task succeeded, which is the one thing that is
+            # certainly false.
             await updater.failed(message=updater.new_agent_message(parts=[Part(text=answer)]))
             return
 
@@ -167,23 +170,46 @@ class WorkflowExecutor(AgentExecutor):
         await TaskUpdater(event_queue, context.task_id, context.context_id).cancel()
 
 
-def _read(response: httpx.Response) -> tuple[str, bool]:
+class Outcome(Enum):
-    """What the workflow said, and whether it is escalating.
+    """What came back, which is not the same question as whether HTTP worked."""
 
-    A workflow answers with `{"answer": "...", "escalate": false}`. Anything else
+    #: The contract was honoured and the workflow is standing behind its answer.
-    is returned as raw text rather than guessed at — a workflow that has drifted
+    ANSWERED = auto()
-    from the contract should be visible, not silently reinterpreted.
+    #: The workflow answered, and is handing the decision to a human.
+    ESCALATED = auto()
+    #: HTTP 200 with an empty body. n8n does that when a node throws before the
+    #: Respond node runs — a failed token exchange is the common way in. It is a
+    #: failure that looks exactly like a success from the status code alone.
+    SILENT = auto()
+    #: A body that is not the contract. Returned raw rather than guessed at: a
+    #: workflow that has drifted should be visible, not reinterpreted.
+    OFF_CONTRACT = auto()
+
+
+def _read(response: httpx.Response) -> tuple[str, Outcome]:
+    """What the workflow said, and what kind of thing it said.
+
+    A workflow answers with `{"answer": "...", "escalate": false}`.
     """
+    body = response.text.strip()
+    if not body:
+        return (
+            "The workflow produced no answer. It most often means a node threw "
+            "before the reply was built — a refused token exchange, usually.",
+            Outcome.SILENT,
+        )
+
     try:
         payload = response.json()
     except ValueError:
-        return response.text.strip() or "(the workflow returned nothing)", False
+        return body, Outcome.OFF_CONTRACT
     if isinstance(payload, list) and payload:
         # n8n returns an array when the workflow's last node emits items.
         payload = payload[0]
     if isinstance(payload, dict) and "answer" in payload:
-        return str(payload["answer"]), bool(payload.get("escalate", False))
+        answer = str(payload["answer"])
-    return response.text.strip() or "(the workflow returned nothing)", False
+        return answer, Outcome.ESCALATED if payload.get("escalate", False) else Outcome.ANSWERED
+    return body, Outcome.OFF_CONTRACT
 
 
 def _subject_token(context: RequestContext) -> str | None:

adapter/tests/test_adapter.py

@@ -11,12 +11,12 @@ import httpx
 import pytest
 
 from a2a_n8n_adapter.config import Settings
-from a2a_n8n_adapter.server import _read, build_agent_card
+from a2a_n8n_adapter.server import Outcome, _read, build_agent_card
 
 
 def settings(**over) -> Settings:
     base = dict(
-        agent_name="approvisionnement",
+        agent_name="supply",
         agent_description="Supply decisions.",
         skill_id="check_availability",
         skill_name="Check availability",
@@ -35,27 +35,35 @@ def response(payload, status=200) -> httpx.Response:
 
 class TestReadingTheWorkflow:
     def test_the_contracted_shape(self) -> None:
-        assert _read(response({"answer": "yes", "escalate": False})) == ("yes", False)
+        assert _read(response({"answer": "yes", "escalate": False})) == ("yes", Outcome.ANSWERED)
 
     def test_n8n_wraps_its_last_node_in_an_array(self) -> None:
-        assert _read(response([{"answer": "yes"}])) == ("yes", False)
+        assert _read(response([{"answer": "yes"}])) == ("yes", Outcome.ANSWERED)
 
     def test_escalation_is_carried_not_swallowed(self) -> None:
         # An autonomous agent meeting a rule that needs approval must escalate.
         # Losing this flag would turn "a human must look" into "done".
         assert _read(response({"answer": "needs approval", "escalate": True})) == (
             "needs approval",
-            True,
+            Outcome.ESCALATED,
         )
 
     def test_an_off_contract_reply_is_returned_raw(self) -> None:
         # Visible rather than reinterpreted: a workflow that has drifted should
         # look wrong, not be quietly guessed at.
-        text, escalate = _read(response("plain text"))
+        # Off contract is not agreement. Returned raw so the drift is visible,
-        assert text == "plain text" and escalate is False
+        # but never as a completed answer.
+        text, outcome = _read(response("plain text"))
+        assert text == "plain text" and outcome is Outcome.OFF_CONTRACT
 
     def test_an_empty_reply_says_so(self) -> None:
-        assert _read(response("")) == ("(the workflow returned nothing)", False)
+        # HTTP 200 with an empty body is what n8n returns when a node throws
+        # before the reply is built — a refused token exchange, usually. Reading
+        # it as a completed answer told the caller the task succeeded, which was
+        # the one thing certainly false.
+        text, outcome = _read(response(""))
+        assert outcome is Outcome.SILENT
+        assert "no answer" in text
 
 
 class TestAgentCard:
@@ -72,8 +80,8 @@ class TestAgentCard:
         assert len(card.skills[0].examples) == 2
 
     def test_the_card_advertises_the_public_url_not_the_bind_address(self) -> None:
-        card = build_agent_card(settings(public_url="http://approvisionnement.agents:8080/"))
+        card = build_agent_card(settings(public_url="http://supply-agent.agents:8080/"))
-        assert card.supported_interfaces[0].url == "http://approvisionnement.agents:8080/"
+        assert card.supported_interfaces[0].url == "http://supply-agent.agents:8080/"
 
 
 class TestSubjectToken:

deploy/agent-secrets.yaml

@@ -18,7 +18,7 @@ spec:
   target:
     name: n8n-agent-secrets
   data:
-    - secretKey: APPROVISIONNEMENT_CLIENT_SECRET
+    - secretKey: SUPPLY_CLIENT_SECRET
       remoteRef:
         key: keycloak/classic-models-realm
-        property: KC_SECRET_CLASSIC_MODELS_AGENT_APPROVISIONNEMENT
+        property: KC_SECRET_CLASSIC_MODELS_AGENT_SUPPLY

deploy/agents/ingress.yaml

@@ -0,0 +1,70 @@
+# Reaching this agent from outside the cluster.
+#
+# Until now nothing did: an agent answered only what could call its Service, so
+# every conversation with it went through `kubectl run curl`. An orchestrator
+# nobody can talk to is not finished.
+#
+# Peer traffic does **not** come through here — supply calls, and is called by,
+# other agents on their in-cluster Service names. This is the human door.
+#
+# ## It is not an open door
+#
+# A2A carries the end user's token in `Authorization`, and this agent forwards it
+# and exchanges it; a forged one fails at the realm. But "fails downstream" is
+# not the same as "refused", and an unauthenticated caller could still make the
+# agent do work — inference costs money and a request that reaches an LLM is a
+# prompt-injection surface. So the same authentication subrequest that guards the
+# n8n endpoints guards this one: Keycloak's userinfo answers 200 for a valid
+# bearer in the realm and 401 otherwise, which is the auth-request contract
+# exactly.
+#
+# It authenticates, it does not authorise. What the caller may actually reach is
+# decided further down, by the exchange and by the roles in their token.
+#
+# **The agent card is behind it too.** A2A discovery is normally public; here it
+# is not, because a client that cannot send an `Authorization` header cannot use
+# the agent anyway, and the card names the skills.
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: supply-agent-tls
+  namespace: agents
+spec:
+  secretName: supply-agent-tls
+  dnsNames:
+    - supply-agent.sttlab.local
+  issuerRef:
+    name: sttlab-local-ca
+    kind: ClusterIssuer
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: supply-agent
+  namespace: agents
+  annotations:
+    nginx.ingress.kubernetes.io/auth-url: http://keycloak.keycloak.svc.cluster.local:8080/realms/classic-models/protocol/openid-connect/userinfo
+    # A2A streams a task's progress; buffering it defeats that.
+    nginx.ingress.kubernetes.io/proxy-buffering: "off"
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    # An agent turn is a model call and several hops. The nginx default of 60s
+    # cuts a working answer off mid-flight.
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "300"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "300"
+spec:
+  ingressClassName: nginx
+  tls:
+    - hosts:
+        - supply-agent.sttlab.local
+      secretName: supply-agent-tls
+  rules:
+    - host: supply-agent.sttlab.local
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: supply-agent
+                port:
+                  number: 8080

deploy/agents/kustomization.yaml

@@ -1,4 +1,5 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-  - approvisionnement.yaml
+  - supply.yaml
+  - ingress.yaml

deploy/agents/supply.yaml

@@ -1,10 +1,10 @@
-# The A2A facade for Approvisionnement. It lives in the `agents` namespace with
+# The A2A facade for Supply. It lives in the `agents` namespace with
 # the other agents, not with n8n: what it is, is an agent — the workflow behind
 # it is an implementation detail its callers never see.
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: approvisionnement-agent
+  name: supply-agent
   namespace: agents
 spec:
   # The adapter is stateless — every task is one webhook call — so this is a
@@ -12,11 +12,11 @@ spec:
   replicas: 1
   selector:
     matchLabels:
-      app: approvisionnement-agent
+      app: supply-agent
   template:
     metadata:
       labels:
-        app: approvisionnement-agent
+        app: supply-agent
     spec:
       securityContext:
         runAsNonRoot: true
@@ -25,13 +25,13 @@ spec:
           type: RuntimeDefault
       containers:
         - name: adapter
-          image: gitea.sttlab.eu/stt/a2a-n8n-adapter:v0.1.0
+          image: gitea.sttlab.eu/stt/a2a-n8n-adapter:v0.2.0
           ports:
             - name: http
               containerPort: 8080
           env:
             - name: ADAPTER_AGENT_NAME
-              value: approvisionnement
+              value: supply
             - name: ADAPTER_AGENT_DESCRIPTION
               value: >-
                 Supply decisions for the Classic Models catalog. Answers whether a
@@ -53,7 +53,7 @@ spec:
             - name: ADAPTER_WEBHOOK_URL
               value: http://n8n.n8n.svc.cluster.local/webhook/check-availability
             - name: ADAPTER_PUBLIC_URL
-              value: http://approvisionnement-agent.agents.svc.cluster.local:8080/
+              value: http://supply-agent.agents.svc.cluster.local:8080/
             - name: ADAPTER_CA_BUNDLE
               value: /etc/sttlab-ca/ca.crt
           volumeMounts:
@@ -92,11 +92,11 @@ spec:
 apiVersion: v1
 kind: Service
 metadata:
-  name: approvisionnement-agent
+  name: supply-agent
   namespace: agents
 spec:
   selector:
-    app: approvisionnement-agent
+    app: supply-agent
   ports:
     - name: http
       port: 8080

deploy/flux-kustomization.yaml

@@ -51,5 +51,9 @@ spec:
       # "false" so a workflow can read $env.<AGENT>_CLIENT_SECRET. It means any
       # workflow on this instance can read any variable in the pod — acceptable
       # while it runs only this estate's agents, and not a moment longer.
-      BLOCK_ENV_ACCESS: "false"
+      BLOCK_ENV_ACCESS: '"false"'
-      EXECUTIONS_MAX_AGE_HOURS: "336"
+      # Quoted inside the value on purpose: these land in a ConfigMap, whose
+      # values must be strings, and the template cannot force it — kustomize
+      # strips quotes before substitution runs. Without the inner quotes the
+      # apply fails on the type.
+      EXECUTIONS_MAX_AGE_HOURS: '"336"'

workflows/README.md

@@ -21,7 +21,82 @@ POST  /rest/workflows/<id>/activate     {"versionId": "<current>"}
 `PATCH {"active": true}` returns 200 and leaves the workflow inactive, silently:
 activation has its own endpoint.
 
-## approvisionnement-check-availability
+## supply-procurement
+
+The service's own supplier, simulated. Reacts to `reorder.requested` (emitted
+by the periodic run below, once it finds a reference under threshold),
+decides — a fixed lead time, or a 15% chance the supplier cannot fulfil —
+answers with `reorder.confirmed`/`reorder.rejected`, and on the confirmed
+delivery date writes the stock itself.
+
+```
+reorder.requested   {productcode, quantity, requested_at}
+  → reorder.confirmed  {deliver_on}      — 85% of the time
+  → reorder.rejected   {reason: "supplier stockout"}   — 15%
+```
+
+No purchase-order entity, no supplier entity, no negotiation — the whole model
+is one probability and one lead time, on purpose: this simulates *that*
+fulfilment can fail, not *why* a given supplier would.
+
+### One service, two capacities — not two identities
+
+This is still the supply agent, not a separate "procurement" component. It
+both requests (the periodic run) and answers its own request (this workflow),
+under the same Kafka account and the same Keycloak client — the 2026-08-31
+decision that réapprovisionnement is one service, not a split into a demand
+side and a supply side.
+
+### The write goes through the front door
+
+On the delivery date, this workflow reads the product's current stock and
+PATCHes it — through Kong, through the same `patch-product` MCP tool a human
+product manager would use, under a **new, narrow role**: `restocker` may PATCH
+a product and nothing else, not create, not replace, not delete. It sends
+`X-Stock-Change-Reason: delivery:<reorder-id>`, which `classic-models-api`
+only honours in that exact shape; anything else falls back to
+`manual-adjustment`. The resulting `product.stock_changed` event is the *only*
+stock-update event — there is deliberately no second, n8n-emitted fact
+claiming a delivery happened, because nothing would certify it against the
+one that actually changed the database. See `classic-models-api`'s commit
+"Accept a delivery reason on a stock PATCH" for the backend side.
+
+### Two triggers, one shared state
+
+`$getWorkflowStaticData('global').pendingDeliveries`, keyed by reorder id —
+the same pattern the stock-watch workflow already uses for its watchlist, now
+shared across **two** trigger chains in this one workflow: the Kafka-triggered
+decision writes an entry when the supplier confirms, and a daily schedule
+(06:15, deliberately after the periodic run's 06:00) reads what is due and
+applies it. A pending entry is deleted only once the PATCH is confirmed by the
+API's own response — a failed write leaves it in place so tomorrow's run
+retries it, rather than losing a delivery nobody applied.
+
+### A bug this shipped with, and how it was found
+
+`Apply delivery` sits between `Read current stock` and `Update stock`, and its
+first version wrote `{ ...$json, new_quantity }` — but `$json` at that point is
+`Read current stock`'s own output, not the due-delivery record two nodes
+earlier. `reorder_id`/`productcode`/`quantity` were silently dropped, and
+`Update stock` failed two nodes later with `"path_productcode" is a required
+property` — a symptom far from its cause. Fixed by naming the source
+explicitly: `$('Due deliveries').item.json` for what the delivery *is*, `$json`
+for what the catalog *says now*. The same rule `check_availability` already
+follows for `Recent movement` — an implicit `$json` is only ever the
+*immediately preceding* node, never "whichever upstream node has the field I
+want."
+
+### Manual test runs do not persist static data
+
+Verified the hard way: triggering this workflow via `/rest/workflows/{id}/run`
+executes for real (the write happens, the event is genuine) but the
+`pendingDeliveries` mutation is **not** saved back to the workflow — the entry
+reappears on the next check. Only a genuine trigger firing (a real Kafka
+message, the real schedule) persists it. A manual run is fine for proving the
+logic; it is not fine for proving the state machine, and the two were verified
+separately here.
+
+## supply-check-availability
 
 Working. `POST /webhook/check-availability` with the end user's token in
 `X-Subject-Token`:
@@ -89,7 +164,74 @@ and through the A2A facade, `escalate: true` becomes a task in state **failed**
 rather than a completed one — the honest shape for "a human has to look at
 this".
 
-## approvisionnement-periodic-reorder
+### Deducting open orders would double-count
+
+The answer used to end with *"quantities committed on open orders are not
+deducted"*. That caveat is now **wrong**, and acting on it would be worse than
+leaving it: placing an order line decrements stock in the same transaction, so
+an open order has already taken what it needs. Subtracting it again counts it
+twice.
+
+The API gained the filters that would have made the deduction possible —
+`list-order-details` takes `productcode` and `ordernumber__status` — and the
+right conclusion was that the deduction is no longer the thing to build.
+
+What remains true, and is said once: the order lines that came with the seed
+data predate the stock movement and never decremented anything. They are
+history, not commitments.
+
+### It now knows what the reactive half saw
+
+`check-availability` reads the watchlist before answering, so a crossing that
+happened twenty minutes ago is part of the answer:
+
+```
+"Peut-on promettre S12_1099 ?"
+  → "No — 1968 Ford Mustang (S12_1099) is down to 8 … It crossed the threshold
+     at 06:18:24 (driven by orders), from 68."
+```
+
+"It fell below this afternoon, under demand" is a different decision from "it
+has been sitting below for a month", and only the event carries that.
+
+The watchlist is read over an in-cluster call to the stock-watch workflow's own
+webhook — its data lives in that workflow and there is no other way in. The node
+is `onError: continueRegularOutput`: an availability answer must not depend on
+the watchlist being up.
+
+### A stale read once made it contradict itself
+
+The agent published this, in one sentence:
+
+```
+"68 in stock, above the reorder threshold of 50 … It crossed the threshold, from 68."
+```
+
+Both halves were internally consistent and the answer was wrong. The catalog
+domain was caching reads for **60 seconds** at the gateway, so an agent woken by
+an event read the figure from before the event.
+
+The first fix was in this workflow — prefer the event's dated figure over the
+undated read. It has been **removed**, because the cache was removed instead:
+caching a read-write API buys little and costs correctness on every mutable
+resource, since the gateway has no invalidation on write. Working around it here
+would have left four other domains lying to whatever reads them next.
+
+Measured after: a `PATCH` to 300 followed three seconds later by the same
+question answers **300**.
+
+The lesson worth keeping is not about caches. **Do not treat a single read as
+current unless something guarantees it** — and an agent cannot tell.
+
+### The crossing is mentioned only while it still holds
+
+An entry stays on the watchlist until a human clears it, so a reference that has
+since been restocked still has one. Saying "300 in stock … it crossed the
+threshold, from 68" reads as a contradiction even though both halves are true,
+so the context is appended only while the reference is actually below the
+threshold.
+
+## supply-periodic-reorder
 
 The periodic half. A schedule trigger at 06:00, deliberately periodic rather
 than a batch standing in for events: grouping references into a purchase
@@ -106,6 +248,44 @@ scanned 110 of 110, complete
 escalate: true
 ```
 
+### It answers with a date
+
+The other half of what filtering unlocked. `check_availability` now consults
+the sales domain too: `list-order-details` filtered by product **and**
+status (`In Process`, `On Hold`) — `Orderdetail` carries the order's
+`requireddate` and `order_status` denormalised on the line itself, so this is
+one call per status, not one per order.
+
+```
+"Peut-on promettre S18_1749 ?"
+  → "Yes … 2720 in stock, above the reorder threshold of 50. Basis: stock on
+     hand, already net of order lines placed through the API. 2 open order(s)
+     already commit to this reference; the nearest is due 2005-05-04
+     (order 10407, On Hold)."
+```
+
+This is **not** the deduction that turned out to be wrong two sessions ago —
+that would have subtracted these quantities from stock a second time. This is
+additive context only: what already-open orders expect, and by when. Silent
+when there is none; never blocks the answer if the sales domain cannot be
+reached.
+
+### Two token exchanges, on purpose
+
+Catalog and sales are different audiences, so this workflow now holds two
+narrow tokens rather than widening the one it already had — the same reason
+every agent in this estate exchanges per callee rather than requesting a
+broad token once.
+
+### A straight chain, not two branches joining
+
+The obvious shape was two parallel paths — catalog and sales — converging on
+`Answer`. Not built that way: whether a node with two incoming connections
+waits for both before running is exactly the kind of thing worth being certain
+of rather than assuming, and this endpoint answers rarely enough that a few
+hundred extra milliseconds from running sequentially is free. One straight
+chain, ten nodes, nothing to get wrong about ordering.
+
 ### It acts under its own machine identity
 
 `client_credentials`, not a mandate. An agent running on its own account acts
@@ -148,7 +328,7 @@ the output. A catalog that outgrows one page needs a paging loop **and** the
 read-volume cap this repo already lists as mandatory for autonomous agents.
 
 
-## approvisionnement-stock-watch
+## supply-stock-watch
 
 The reactive half, and the one the design had been waiting on. It is woken by
 `product.stock_changed` on `classic-models.catalog` rather than by a clock, so a
@@ -207,7 +387,7 @@ better answer when it knows X crossed the threshold at 14:32.
   explicitly and succeeds. A workflow that threw on an uninteresting event would
   replay it forever.
 - The consumer has its **own** SCRAM account,
-  `classic-models-agent-approvisionnement`: Read on that one topic and that one
+  `classic-models-agent-supply`: Read on that one topic and that one
   consumer-group prefix. It cannot read sales or payments, and it cannot write —
   so a compromised workflow can raise no event another agent would act on.
 

workflows/approvisionnement-check-availability.json

@@ -1,258 +0,0 @@
-{
-  "name": "Approvisionnement \u2014 check_availability",
-  "nodes": [
-    {
-      "parameters": {
-        "httpMethod": "POST",
-        "path": "check-availability",
-        "responseMode": "responseNode",
-        "options": {}
-      },
-      "id": "webhook",
-      "name": "Webhook",
-      "type": "n8n-nodes-base.webhook",
-      "typeVersion": 2,
-      "position": [
-        0,
-        0
-      ],
-      "webhookId": "check-availability"
-    },
-    {
-      "parameters": {
-        "method": "POST",
-        "url": "https://keycloak.sttlab.local/realms/classic-models/protocol/openid-connect/token",
-        "sendBody": true,
-        "contentType": "form-urlencoded",
-        "bodyParameters": {
-          "parameters": [
-            {
-              "name": "grant_type",
-              "value": "urn:ietf:params:oauth:grant-type:token-exchange"
-            },
-            {
-              "name": "client_id",
-              "value": "classic-models-agent-approvisionnement"
-            },
-            {
-              "name": "client_secret",
-              "value": "={{ $env.APPROVISIONNEMENT_CLIENT_SECRET }}"
-            },
-            {
-              "name": "subject_token",
-              "value": "={{ $('Webhook').item.json.headers['x-subject-token'] }}"
-            },
-            {
-              "name": "subject_token_type",
-              "value": "urn:ietf:params:oauth:token-type:access_token"
-            },
-            {
-              "name": "scope",
-              "value": "openid mcp-catalog-audience token-exchange-broker-audience"
-            }
-          ]
-        },
-        "options": {}
-      },
-      "id": "exchange-token",
-      "name": "Exchange token",
-      "type": "n8n-nodes-base.httpRequest",
-      "typeVersion": 4.2,
-      "position": [
-        220,
-        0
-      ]
-    },
-    {
-      "parameters": {
-        "method": "POST",
-        "url": "https://catalog-dev.sttlab.local/catalog-mcp",
-        "sendHeaders": true,
-        "headerParameters": {
-          "parameters": [
-            {
-              "name": "Authorization",
-              "value": "=Bearer {{ $json.access_token }}"
-            },
-            {
-              "name": "Accept",
-              "value": "application/json, text/event-stream"
-            }
-          ]
-        },
-        "sendBody": true,
-        "specifyBody": "json",
-        "jsonBody": "{\"jsonrpc\": \"2.0\", \"id\": 1, \"method\": \"initialize\", \"params\": {\"protocolVersion\": \"2025-06-18\", \"capabilities\": {}, \"clientInfo\": {\"name\": \"approvisionnement\", \"version\": \"0.1.0\"}}}",
-        "options": {
-          "response": {
-            "response": {
-              "fullResponse": true
-            }
-          }
-        }
-      },
-      "id": "mcp-initialize",
-      "name": "MCP initialize",
-      "type": "n8n-nodes-base.httpRequest",
-      "typeVersion": 4.2,
-      "position": [
-        440,
-        0
-      ]
-    },
-    {
-      "parameters": {
-        "method": "POST",
-        "url": "https://catalog-dev.sttlab.local/catalog-mcp",
-        "sendHeaders": true,
-        "headerParameters": {
-          "parameters": [
-            {
-              "name": "Authorization",
-              "value": "=Bearer {{ $('Exchange token').item.json.access_token }}"
-            },
-            {
-              "name": "Accept",
-              "value": "application/json, text/event-stream"
-            },
-            {
-              "name": "mcp-session-id",
-              "value": "={{ $json.headers['mcp-session-id'] }}"
-            }
-          ]
-        },
-        "sendBody": true,
-        "specifyBody": "json",
-        "jsonBody": "={{ JSON.stringify({ jsonrpc: '2.0', id: 2, method: 'tools/call', params: { name: 'get-product', arguments: { path_productcode: $('Decide the product').item.json.productcode } } }) }}",
-        "options": {
-          "response": {
-            "response": {
-              "neverError": true
-            }
-          }
-        }
-      },
-      "id": "read-stock",
-      "name": "Read stock",
-      "type": "n8n-nodes-base.httpRequest",
-      "typeVersion": 4.2,
-      "position": [
-        660,
-        0
-      ],
-      "alwaysOutputData": true
-    },
-    {
-      "parameters": {
-        "jsCode": "// Pull the product code out of the question.\n//\n// Deliberately loose on the part after the underscore: a reference that\n// looks like one but does not exist must reach the catalog and come back\n// as \"no such product\". Rejecting it here would answer \"you named no\n// product\", which is false and sends the caller looking in the wrong place.\n//\n// A regex rather than a model: this agent's critical path is rules, and putting\n// an LLM on it would make a nightly job both slower and less predictable. If the\n// question does not name a product, the agent escalates instead of guessing \u2014\n// an autonomous agent that meets an ambiguity must hand it back, never resolve\n// it on its own.\nconst question = $('Webhook').first().json.body?.question ?? '';\nconst match = question.match(/\\bS\\d+_[A-Za-z0-9]+\\b/);\nif (!match) {\n  return [{ json: { productcode: null, question } }];\n}\nreturn [{ json: { productcode: match[0], question } }];\n"
-      },
-      "id": "decide-the-product",
-      "name": "Decide the product",
-      "type": "n8n-nodes-base.code",
-      "typeVersion": 2,
-      "position": [
-        220,
-        180
-      ]
-    },
-    {
-      "parameters": {
-        "jsCode": "// Turn the MCP reply into a decision.\n//\n// An A2A call returns an answer, not data: the caller learns whether the stock\n// covers what it asked about, and never receives the stock table. That is what\n// keeps this agent from becoming a read proxy onto the catalog domain.\nconst THRESHOLD = 50;   // below this, a reorder is due before promising anything\n\nconst decided = $('Decide the product').first().json;\nif (!decided.productcode) {\n  return [{ json: {\n    answer: 'No product reference in the question. Name one as S10_1949 and ask again.',\n    escalate: true,\n  }}];\n}\n\nconst item = $input.first();\nif (!item) {\n  return [{ json: {\n    answer: `The catalog returned nothing for ${decided.productcode}. It may not exist.`,\n    escalate: true,\n  }}];\n}\nconst raw = item.json ?? {};\nconst body = typeof raw === 'string' ? raw : (raw.data ?? JSON.stringify(raw));\n\n// The endpoint answers as an SSE event, so the JSON sits on a `data:` line.\nconst line = String(body).split('\\n').find((l) => l.startsWith('data:'));\nif (!line) {\n  return [{ json: {\n    answer: `Could not read the catalog's reply for ${decided.productcode}.`,\n    escalate: true,\n  }}];\n}\n\nlet rpc;\ntry {\n  rpc = JSON.parse(line.slice(5).trim());\n} catch (e) {\n  return [{ json: {\n    answer: `The catalog's reply for ${decided.productcode} could not be read.`,\n    escalate: true,\n  }}];\n}\n\n// A JSON-RPC `error` is a protocol failure \u2014 a malformed call, a session gone.\nif (rpc.error) {\n  return [{ json: {\n    answer: `The catalog refused the read for ${decided.productcode}: ${rpc.error.message}.`,\n    escalate: true,\n  }}];\n}\n\n// A *tool* failure is not that. MCP reports it as a perfectly successful result\n// carrying `isError: true`, with the reason as text \u2014 so a client that only\n// checks `error` reads a failure as data and tries to parse \"HTTP call failed\n// with status 404\" as a product. Which is exactly what this did.\nconst text = rpc.result?.content?.[0]?.text ?? '';\nif (rpc.result?.isError) {\n  const missing = text.includes('404');\n  return [{ json: {\n    answer: missing\n      ? `There is no product ${decided.productcode} in the catalog.`\n      : `The catalog could not answer for ${decided.productcode}: ${text}`,\n    escalate: true,\n  }}];\n}\n\nlet product;\ntry {\n  product = JSON.parse(text);\n} catch (e) {\n  return [{ json: {\n    answer: `The catalog returned something unreadable for ${decided.productcode}.`,\n    escalate: true,\n  }}];\n}\nconst stock = Number(product.quantityinstock);\nconst available = stock >= THRESHOLD;\n\n// Stock on hand only. Quantities already committed on unshipped orders are\n// NOT deducted, and the answer says so rather than implying a certainty it does\n// not have: the sales API cannot be filtered by product code, so working it out\n// would mean paging the whole orderdetails table on every question \u2014 sixty\n// pages, for one answer. See the backlog note in CLAUDE.md.\nconst basis = 'stock on hand; quantities committed on open orders are not deducted';\n\nreturn [{ json: {\n  answer: available\n    ? `Yes \u2014 ${product.productname} (${product.productcode}) can be promised: `\n      + `${stock} in stock, above the reorder threshold of ${THRESHOLD}. `\n      + `Basis: ${basis}.`\n    : `No \u2014 ${product.productname} (${product.productcode}) is down to ${stock}, `\n      + `below the reorder threshold of ${THRESHOLD}. A reorder is due before it can be promised. `\n      + `Basis: ${basis}.`,\n  escalate: false,\n}}];\n"
-      },
-      "id": "answer",
-      "name": "Answer",
-      "type": "n8n-nodes-base.code",
-      "typeVersion": 2,
-      "position": [
-        880,
-        0
-      ]
-    },
-    {
-      "parameters": {
-        "respondWith": "json",
-        "responseBody": "={{ JSON.stringify($json) }}",
-        "options": {}
-      },
-      "id": "respond",
-      "name": "Respond",
-      "type": "n8n-nodes-base.respondToWebhook",
-      "typeVersion": 1.1,
-      "position": [
-        1100,
-        0
-      ]
-    }
-  ],
-  "connections": {
-    "Webhook": {
-      "main": [
-        [
-          {
-            "node": "Decide the product",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "Decide the product": {
-      "main": [
-        [
-          {
-            "node": "Exchange token",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "Exchange token": {
-      "main": [
-        [
-          {
-            "node": "MCP initialize",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "MCP initialize": {
-      "main": [
-        [
-          {
-            "node": "Read stock",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "Read stock": {
-      "main": [
-        [
-          {
-            "node": "Answer",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "Answer": {
-      "main": [
-        [
-          {
-            "node": "Respond",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    }
-  },
-  "settings": {
-    "executionOrder": "v1"
-  }
-}

workflows/approvisionnement-stock-watch.json

@@ -1,115 +0,0 @@
-{
-  "name": "Approvisionnement \u2014 stock watch",
-  "nodes": [
-    {
-      "parameters": {
-        "topic": "classic-models.catalog",
-        "groupId": "approvisionnement-stock-watch",
-        "resolveOffset": "onCompletion",
-        "allowedStatuses": [
-          "success"
-        ],
-        "options": {
-          "jsonParseMessage": true,
-          "onlyMessage": true,
-          "fromBeginning": false
-        }
-      },
-      "type": "n8n-nodes-base.kafkaTrigger",
-      "typeVersion": 2,
-      "position": [
-        0,
-        0
-      ],
-      "id": "kafka-trigger-stock-watch",
-      "name": "Catalog events",
-      "credentials": {
-        "kafka": {
-          "id": "8qNZXLzvdx5rWQ0V",
-          "name": "kafka-classic-models"
-        }
-      }
-    },
-    {
-      "parameters": {
-        "jsCode": "// A stock movement, judged the moment it happens.\n//\n// This is the reactive half of Approvisionnement. The 06:00 run proposes\n// purchase orders on a buying cycle, which is genuinely periodic; noticing that\n// a reference is about to run out is not, and a nightly sweep would report at\n// 06:00 what was true at 14:32 the previous afternoon.\n//\n// What it reacts to is a fact the API published, not a row it went looking for.\nconst THRESHOLD = 50;\nconst COVER = 3;          // a proposal covers three times the threshold\nconst STOCK_CHANGED = 'com.sttlab.classicmodels.product.stock_changed.v1';\n\nconst event = $json ?? {};\n\n// The topic carries every catalog event, so most messages are not ours. Saying\n// so explicitly keeps the offset moving: a workflow that threw on an\n// uninteresting event would replay it forever.\nif (event.type !== STOCK_CHANGED) {\n  return [{ json: { considered: false, type: event.type ?? 'unreadable' } }];\n}\n\nconst data = event.data ?? {};\nconst before = Number(data.before?.quantityinstock);\nconst after = Number(data.after?.quantityinstock);\nif (!Number.isFinite(before) || !Number.isFinite(after)) {\n  return [{ json: {\n    considered: false,\n    escalate: true,\n    reason: `${event.subject}: the movement carried no readable quantities.`,\n  }}];\n}\n\n// Only a *crossing* is news. Without this, every further order line on an\n// already-low reference raises the same alarm again, and an agent that repeats\n// itself is one a human learns to ignore.\nconst crossed = before >= THRESHOLD && after < THRESHOLD;\n// A stock-out is a different fact from a low stock, even when the reference was\n// already below the threshold \u2014 nothing can be promised at all.\nconst emptied = after === 0 && before > 0;\n\n// `order:` means demand; anything else is someone correcting the books. Both\n// justify a purchase order, but only demand is a signal about the future.\nconst fromDemand = String(data.reason ?? '').startsWith('order:');\n\nconst store = $getWorkflowStaticData('global');\nstore.watchlist = store.watchlist ?? {};\n\nif (!crossed && !emptied) {\n  // Not news, but if this reference is already being watched its figures have\n  // just moved. Refresh them rather than leaving a human reading the number it\n  // held at the moment of detection, which is the number least likely to still\n  // be true.\n  const watched = store.watchlist[event.subject];\n  if (watched) {\n    watched.on_hand = after;\n    watched.propose_order = THRESHOLD * COVER - after;\n    watched.last_movement_at = event.time ?? new Date().toISOString();\n  }\n  return [{ json: {\n    considered: true,\n    detected: false,\n    watching: Boolean(watched),\n    productcode: event.subject,\n    on_hand: after,\n  }}];\n}\n\nconst state = { detected: true, escalate: true,\n  productcode: event.subject,\n  on_hand: after,\n  was: before,\n  threshold: THRESHOLD,\n  stock_out: after === 0,\n  driver: fromDemand ? 'demand' : 'correction',\n  movement: data.reason ?? null,\n  propose_order: THRESHOLD * COVER - after,\n  observed_at: event.time ?? new Date().toISOString(),\n  // Kept so this detection can be joined to the request that caused it. It is\n  // the only link back \u2014 the event deliberately names no actor.\n  traceparent: event.traceparent ?? null,\n};\n\nstate.reason = state.stock_out\n  ? `${state.productcode} is out of stock (was ${before}). Nothing can be promised.`\n  : `${state.productcode} fell from ${before} to ${after}, below the threshold of ${THRESHOLD}.`;\n\n// The watchlist is the destination, and it is a real one: the proposal still\n// has nowhere to be written \u2014 the domain has no purchase order and no supplier\n// entity \u2014 so a detection that only logged would be lost between two nightly\n// runs. Here it survives, keyed by reference so a reference cannot appear twice.\nstore.watchlist[state.productcode] = state;\n\nreturn [{ json: state }];\n"
-      },
-      "type": "n8n-nodes-base.code",
-      "typeVersion": 2,
-      "position": [
-        220,
-        0
-      ],
-      "id": "detect-crossing",
-      "name": "Judge the movement"
-    },
-    {
-      "parameters": {
-        "httpMethod": [
-          "GET",
-          "POST"
-        ],
-        "path": "stock-watchlist",
-        "responseMode": "lastNode",
-        "options": {},
-        "multipleMethods": true
-      },
-      "type": "n8n-nodes-base.webhook",
-      "typeVersion": 2,
-      "position": [
-        0,
-        200
-      ],
-      "id": "watchlist-read",
-      "name": "Watchlist",
-      "webhookId": "stock-watchlist-get"
-    },
-    {
-      "parameters": {
-        "jsCode": "// What has been detected and not yet dealt with.\n//\n// A detection that goes only into an execution log is one nobody reads. This\n// makes the watchlist readable \u2014 by the periodic run, which can start from what\n// was already noticed rather than rediscovering it, and by a human.\n//\n// GET  /webhook/stock-watchlist        \u2192 the current list\n// POST /webhook/stock-watchlist        {\"clear\": [\"S24_2000\"]} \u2192 drop entries\nconst store = $getWorkflowStaticData('global');\nstore.watchlist = store.watchlist ?? {};\n\n// GET carries no body; the node still runs, and clear is then empty.\nconst body = $json.body ?? {};\nconst clear = Array.isArray(body.clear) ? body.clear : [];\nfor (const code of clear) delete store.watchlist[code];\n\nconst entries = Object.values(store.watchlist);\nreturn [{ json: {\n  watching: entries.length,\n  cleared: clear,\n  // Worst first: an out-of-stock reference is not the same problem as one that\n  // merely crossed the threshold.\n  entries: entries.sort((a, b) => a.on_hand - b.on_hand),\n}}];\n"
-      },
-      "type": "n8n-nodes-base.code",
-      "typeVersion": 2,
-      "position": [
-        220,
-        200
-      ],
-      "id": "watchlist-render",
-      "name": "Render the watchlist"
-    }
-  ],
-  "connections": {
-    "Catalog events": {
-      "main": [
-        [
-          {
-            "node": "Judge the movement",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    },
-    "Watchlist": {
-      "main": [
-        [
-          {
-            "node": "Render the watchlist",
-            "type": "main",
-            "index": 0
-          }
-        ],
-        [
-          {
-            "node": "Render the watchlist",
-            "type": "main",
-            "index": 0
-          }
-        ]
-      ]
-    }
-  },
-  "settings": {
-    "executionOrder": "v1"
-  }
-}

workflows/supply-periodic-reorder.json

@@ -1,5 +1,5 @@
 {
-  "name": "Approvisionnement \u2014 periodic reorder proposal",
+  "name": "Supply \u2014 periodic reorder proposal",
   "nodes": [
     {
       "parameters": {
@@ -35,11 +35,11 @@
             },
             {
               "name": "client_id",
-              "value": "classic-models-agent-approvisionnement"
+              "value": "classic-models-agent-supply"
             },
             {
               "name": "client_secret",
-              "value": "={{ $env.APPROVISIONNEMENT_CLIENT_SECRET }}"
+              "value": "={{ $env.SUPPLY_CLIENT_SECRET }}"
             },
             {
               "name": "scope",
@@ -77,7 +77,7 @@
         },
         "sendBody": true,
         "specifyBody": "json",
-        "jsonBody": "{\"jsonrpc\": \"2.0\", \"id\": 1, \"method\": \"initialize\", \"params\": {\"protocolVersion\": \"2025-06-18\", \"capabilities\": {}, \"clientInfo\": {\"name\": \"approvisionnement-periodic\", \"version\": \"0.1.0\"}}}",
+        "jsonBody": "{\"jsonrpc\": \"2.0\", \"id\": 1, \"method\": \"initialize\", \"params\": {\"protocolVersion\": \"2025-06-18\", \"capabilities\": {}, \"clientInfo\": {\"name\": \"supply-periodic\", \"version\": \"0.1.0\"}}}",
         "options": {
           "response": {
             "response": {
@@ -139,7 +139,7 @@
     },
     {
       "parameters": {
-        "jsCode": "// Which references need a purchase order, and why.\n//\n// The proposal is computed and goes no further, because there is nowhere for it\n// to go: the classicmodels schema has no purchase order, no supplier entity \u2014\n// `productvendor` is a string on the product \u2014 and the catalog's only write\n// tool is create-product, which is the Catalogue agent's business, not this\n// one's. So this run escalates rather than writing, which is also what an\n// autonomous agent meeting a decision it cannot take is supposed to do.\nconst THRESHOLD = 50;\nconst COVER = 3;   // reorder up to three times the threshold\n\nconst item = $input.first();\nconst raw = item?.json ?? {};\nconst body = typeof raw === 'string' ? raw : (raw.data ?? JSON.stringify(raw));\nconst line = String(body).split('\\n').find((l) => l.startsWith('data:'));\nif (!line) {\n  return [{ json: { proposals: [], escalate: true,\n                    reason: 'The catalog did not answer in the expected shape.' }}];\n}\n\nlet rpc;\ntry { rpc = JSON.parse(line.slice(5).trim()); }\ncatch (e) { return [{ json: { proposals: [], escalate: true,\n                              reason: \"The catalog's reply could not be read.\" }}]; }\n\n// A tool failure is a successful result carrying isError, not a JSON-RPC error.\nif (rpc.error || rpc.result?.isError) {\n  const why = rpc.error?.message ?? rpc.result?.content?.[0]?.text ?? 'unknown';\n  return [{ json: { proposals: [], escalate: true,\n                    reason: `The catalog refused the read: ${why}` }}];\n}\n\nconst page = JSON.parse(rpc.result.content[0].text);\nconst products = page.results ?? [];\nconst scanned = products.length;\nconst total = page.count ?? scanned;\n\nconst proposals = products\n  .filter((p) => Number(p.quantityinstock) < THRESHOLD)\n  .map((p) => ({\n    productcode: p.productcode,\n    productname: p.productname,\n    vendor: p.productvendor,\n    on_hand: Number(p.quantityinstock),\n    propose_order: THRESHOLD * COVER - Number(p.quantityinstock),\n  }));\n\nreturn [{ json: {\n  proposals,\n  scanned,\n  // Loud when the scan was partial: a proposal set computed from part of the\n  // catalog looks exactly like one computed from all of it.\n  complete: scanned >= total,\n  escalate: proposals.length > 0 || scanned < total,\n  reason: scanned < total\n    ? `Scanned ${scanned} of ${total} references; the rest were not read.`\n    : (proposals.length\n        ? `${proposals.length} reference(s) below the threshold of ${THRESHOLD}. `\n          + 'Nowhere to record a purchase order \u2014 the domain has no such concept \u2014 '\n          + 'so this needs a human.'\n        : 'Nothing below the threshold.'),\n}}];\n"
+        "jsCode": "// Which references need a purchase order, and why.\n//\n// A proposal becomes a request event, not a write: the domain still has no\n// purchase-order entity, and this run does not decide a delivery date or a\n// supplier's answer \u2014 that is the procurement half of this same service,\n// reacting to reorder.requested on its own schedule.\nconst THRESHOLD = 50;\nconst COVER = 3;   // reorder up to three times the threshold\n\nconst item = $input.first();\nconst raw = item?.json ?? {};\nconst body = typeof raw === 'string' ? raw : (raw.data ?? JSON.stringify(raw));\nconst line = String(body).split('\\n').find((l) => l.startsWith('data:'));\nif (!line) {\n  return [{ json: { proposals: [], escalate: true,\n                    reason: 'The catalog did not answer in the expected shape.' }}];\n}\n\nlet rpc;\ntry { rpc = JSON.parse(line.slice(5).trim()); }\ncatch (e) { return [{ json: { proposals: [], escalate: true,\n                              reason: \"The catalog's reply could not be read.\" }}]; }\n\n// A tool failure is a successful result carrying isError, not a JSON-RPC error.\nif (rpc.error || rpc.result?.isError) {\n  const why = rpc.error?.message ?? rpc.result?.content?.[0]?.text ?? 'unknown';\n  return [{ json: { proposals: [], escalate: true,\n                    reason: `The catalog refused the read: ${why}` }}];\n}\n\nconst page = JSON.parse(rpc.result.content[0].text);\nconst products = page.results ?? [];\nconst scanned = products.length;\nconst total = page.count ?? scanned;\n\nconst proposals = products\n  .filter((p) => Number(p.quantityinstock) < THRESHOLD)\n  .map((p) => ({\n    productcode: p.productcode,\n    productname: p.productname,\n    vendor: p.productvendor,\n    on_hand: Number(p.quantityinstock),\n    propose_order: THRESHOLD * COVER - Number(p.quantityinstock),\n  }));\n\n// Each proposal becomes a request, not a purchase order \u2014 the domain still has\n// no such entity, and this run is still not the one that decides a delivery\n// date or a supplier's answer. It raises a fact and hands the decision to the\n// same service's own procurement half, over Kafka, exactly the way any other\n// consumer would be handed it.\nconst now = new Date().toISOString();\nconst requests = proposals.map((p) => ({\n  json: {\n    reorder_id: `${Date.now().toString(36)}-${p.productcode}-${Math.random().toString(36).slice(2, 8)}`,\n    productcode: p.productcode,\n    quantity: p.propose_order,\n    requested_at: now,\n  },\n}));\n\n// Nothing to request is a normal outcome, not a diagnostic \u2014 this workflow has\n// no reader downstream of an \"escalate\" field the way check_availability's\n// webhook does, so there is nowhere for a warning to usefully go beyond n8n's\n// own execution log. A partial scan (scanned < total) is visible there:\n// `results.length` on the raw page ends up smaller than `count`.\nreturn requests;\n"
       },
       "id": "propose-reorders",
       "name": "Propose reorders",
@@ -149,6 +149,30 @@
         880,
         0
       ]
+    },
+    {
+      "parameters": {
+        "topic": "classic-models.procurement",
+        "sendInputData": false,
+        "message": "={{ JSON.stringify({ specversion: '1.0', type: 'com.sttlab.classicmodels.reorder.requested.v1', source: '/supply-agent/procurement', subject: $json.reorder_id, id: $json.reorder_id, time: $json.requested_at, datacontenttype: 'application/json', data: { reorder_id: $json.reorder_id, productcode: $json.productcode, quantity: $json.quantity, requested_at: $json.requested_at } }) }}",
+        "useKey": true,
+        "key": "={{ $json.reorder_id }}",
+        "options": {}
+      },
+      "id": "emit-reorder-requests",
+      "name": "Emit reorder requests",
+      "type": "n8n-nodes-base.kafka",
+      "typeVersion": 2,
+      "position": [
+        1100,
+        0
+      ],
+      "credentials": {
+        "kafka": {
+          "id": "8qNZXLzvdx5rWQ0V",
+          "name": "kafka-classic-models"
+        }
+      }
     }
   ],
   "connections": {
@@ -195,6 +219,17 @@
           }
         ]
       ]
+    },
+    "Propose reorders": {
+      "main": [
+        [
+          {
+            "node": "Emit reorder requests",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
     }
   },
   "settings": {

workflows/supply-procurement.json

@@ -0,0 +1,459 @@
+{
+  "name": "Supply \u2014 procurement",
+  "nodes": [
+    {
+      "parameters": {
+        "topic": "classic-models.procurement",
+        "groupId": "supply-procurement",
+        "resolveOffset": "onCompletion",
+        "allowedStatuses": [
+          "success"
+        ],
+        "options": {
+          "jsonParseMessage": true,
+          "onlyMessage": true,
+          "fromBeginning": false
+        }
+      },
+      "type": "n8n-nodes-base.kafkaTrigger",
+      "typeVersion": 2,
+      "position": [
+        0,
+        0
+      ],
+      "id": "procurement-events",
+      "name": "Procurement events",
+      "credentials": {
+        "kafka": {
+          "id": "8qNZXLzvdx5rWQ0V",
+          "name": "kafka-classic-models"
+        }
+      }
+    },
+    {
+      "parameters": {
+        "jsCode": "// Every fact on this topic passes through here \u2014 requests, and this\n// service's own answers to them. Only a request is this node's job; an\n// answer re-arriving (a replay, or this consumer's own message) is not\n// something to decide on a second time.\nif ($json.type !== 'com.sttlab.classicmodels.reorder.requested.v1') return [];\nreturn [{ json: $json.data ?? {} }];"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        220,
+        0
+      ],
+      "id": "filter-requested",
+      "name": "Only requests"
+    },
+    {
+      "parameters": {
+        "jsCode": "// The supplier's answer to one request \u2014 decided once, here, never revisited.\n//\n// A random stockout is the honest way to simulate \"sometimes a supplier\n// cannot fulfil a request\" without pretending to model a real one: no lead\n// time table, no supplier entity, no negotiation. `STOCKOUT_CHANCE` is the\n// whole model.\nconst LEAD_TIME_DAYS = 7;\nconst STOCKOUT_CHANCE = 0.15;\n\nconst req = $json;\nif (!req.reorder_id || !req.productcode) {\n  // Not our envelope, or unreadable. Every message on this topic is either a\n  // request or an answer to one \u2014 this node only runs on requests (filtered\n  // upstream), so a shape this far off the contract is not this run's job.\n  return [];\n}\n\nconst rejected = Math.random() < STOCKOUT_CHANCE;\nconst now = new Date();\n\nif (rejected) {\n  return [{ json: {\n    outcome: 'rejected',\n    reorder_id: req.reorder_id,\n    productcode: req.productcode,\n    quantity: req.quantity,\n    decided_at: now.toISOString(),\n    reason: 'supplier stockout',\n  }}];\n}\n\nconst deliverOn = new Date(now);\ndeliverOn.setUTCDate(deliverOn.getUTCDate() + LEAD_TIME_DAYS);\n\nreturn [{ json: {\n  outcome: 'confirmed',\n  reorder_id: req.reorder_id,\n  productcode: req.productcode,\n  quantity: req.quantity,\n  decided_at: now.toISOString(),\n  deliver_on: deliverOn.toISOString().slice(0, 10),\n}}];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        440,
+        0
+      ],
+      "id": "decide-request",
+      "name": "Decide the request"
+    },
+    {
+      "parameters": {
+        "jsCode": "// The envelope for whichever answer \"Decide the request\" produced. One node\n// covers both event types on purpose: they share every field except the ones\n// that differ (deliver_on vs reason), and a caller distinguishes them by\n// `type`, the way any consumer here already does.\nconst d = $json;\nconst type = d.outcome === 'confirmed'\n  ? 'com.sttlab.classicmodels.reorder.confirmed.v1'\n  : 'com.sttlab.classicmodels.reorder.rejected.v1';\n\nconst data = d.outcome === 'confirmed'\n  ? { reorder_id: d.reorder_id, productcode: d.productcode, quantity: d.quantity, deliver_on: d.deliver_on }\n  : { reorder_id: d.reorder_id, productcode: d.productcode, quantity: d.quantity, reason: d.reason };\n\nreturn [{ json: {\n  envelope: JSON.stringify({\n    specversion: '1.0',\n    type,\n    source: '/supply-agent/procurement',\n    subject: d.reorder_id,\n    id: `${d.reorder_id}-${d.outcome}`,\n    time: d.decided_at,\n    datacontenttype: 'application/json',\n    data,\n  }),\n  reorder_id: d.reorder_id,\n}}];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        660,
+        -100
+      ],
+      "id": "build-answer",
+      "name": "Build the answer"
+    },
+    {
+      "parameters": {
+        "topic": "classic-models.procurement",
+        "sendInputData": false,
+        "message": "={{ $json.envelope }}",
+        "useKey": true,
+        "key": "={{ $json.reorder_id }}",
+        "options": {}
+      },
+      "type": "n8n-nodes-base.kafka",
+      "typeVersion": 2,
+      "position": [
+        880,
+        -100
+      ],
+      "id": "publish-answer",
+      "name": "Publish the answer",
+      "credentials": {
+        "kafka": {
+          "id": "8qNZXLzvdx5rWQ0V",
+          "name": "kafka-classic-models"
+        }
+      }
+    },
+    {
+      "parameters": {
+        "jsCode": "// Remembering what to deliver, and when \u2014 the same staticData pattern the\n// stock-watch workflow already uses for its own pending state, so this is not\n// a second mechanism to reason about, just a second use of one.\nif ($json.outcome !== 'confirmed') {\n  // A rejection has nothing further to do: no delivery, nothing to schedule.\n  return [];\n}\nconst store = $getWorkflowStaticData('global');\nstore.pendingDeliveries = store.pendingDeliveries ?? {};\nstore.pendingDeliveries[$json.reorder_id] = {\n  productcode: $json.productcode,\n  quantity: $json.quantity,\n  deliver_on: $json.deliver_on,\n};\nreturn [{ json: { scheduled: true, reorder_id: $json.reorder_id } }];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        660,
+        100
+      ],
+      "id": "schedule-delivery",
+      "name": "Schedule the delivery"
+    },
+    {
+      "parameters": {
+        "rule": {
+          "interval": [
+            {
+              "field": "days",
+              "triggerAtHour": 6,
+              "triggerAtMinute": 15
+            }
+          ]
+        }
+      },
+      "type": "n8n-nodes-base.scheduleTrigger",
+      "typeVersion": 1.2,
+      "position": [
+        0,
+        300
+      ],
+      "id": "every-morning-delivery",
+      "name": "Every morning (delivery)"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "https://keycloak.sttlab.local/realms/classic-models/protocol/openid-connect/token",
+        "sendBody": true,
+        "contentType": "form-urlencoded",
+        "bodyParameters": {
+          "parameters": [
+            {
+              "name": "grant_type",
+              "value": "client_credentials"
+            },
+            {
+              "name": "client_id",
+              "value": "classic-models-agent-supply"
+            },
+            {
+              "name": "client_secret",
+              "value": "={{ $env.SUPPLY_CLIENT_SECRET }}"
+            },
+            {
+              "name": "scope",
+              "value": "openid mcp-catalog-audience token-exchange-broker-audience"
+            }
+          ]
+        },
+        "options": {}
+      },
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        220,
+        300
+      ],
+      "id": "machine-token-delivery",
+      "name": "Machine token"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "https://catalog-dev.sttlab.local/catalog-mcp",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "=Bearer {{ $json.access_token }}"
+            },
+            {
+              "name": "Accept",
+              "value": "application/json, text/event-stream"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "{\"jsonrpc\": \"2.0\", \"id\": 1, \"method\": \"initialize\", \"params\": {\"protocolVersion\": \"2025-06-18\", \"capabilities\": {}, \"clientInfo\": {\"name\": \"supply-procurement\", \"version\": \"0.1.0\"}}}",
+        "options": {
+          "response": {
+            "response": {
+              "fullResponse": true
+            }
+          }
+        }
+      },
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        440,
+        300
+      ],
+      "id": "mcp-initialize-delivery",
+      "name": "MCP initialize"
+    },
+    {
+      "parameters": {
+        "jsCode": "// What is due today or earlier \u2014 anything scheduled for a date already past\n// is delivered on the next run rather than lost, since this only runs once a\n// day and a missed day must not mean a missed delivery.\nconst store = $getWorkflowStaticData('global');\nstore.pendingDeliveries = store.pendingDeliveries ?? {};\n\nconst today = new Date().toISOString().slice(0, 10);\nconst due = Object.entries(store.pendingDeliveries)\n  .filter(([, d]) => d.deliver_on <= today)\n  .map(([reorder_id, d]) => ({ json: { reorder_id, ...d } }));\n\nreturn due;\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        660,
+        300
+      ],
+      "id": "due-deliveries",
+      "name": "Due deliveries"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "https://catalog-dev.sttlab.local/catalog-mcp",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "=Bearer {{ $('Machine token').item.json.access_token }}"
+            },
+            {
+              "name": "Accept",
+              "value": "application/json, text/event-stream"
+            },
+            {
+              "name": "mcp-session-id",
+              "value": "={{ $('MCP initialize').item.json.headers['mcp-session-id'] }}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ jsonrpc: '2.0', id: 2, method: 'tools/call', params: { name: 'get-product', arguments: { path_productcode: $json.productcode } } }) }}",
+        "options": {
+          "response": {
+            "response": {
+              "neverError": true
+            }
+          }
+        }
+      },
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        880,
+        300
+      ],
+      "id": "read-current-stock",
+      "name": "Read current stock",
+      "alwaysOutputData": true
+    },
+    {
+      "parameters": {
+        "jsCode": "// The new stock figure, read fresh rather than trusted from whenever this was\n// scheduled \u2014 a delivery adds to whatever is on hand *now*, not to a number\n// that may be a week stale.\n//\n// Two upstream nodes matter here, not one: \"Due deliveries\" carries what this\n// delivery IS (reorder_id, productcode, quantity), \"Read current stock\" carries\n// what the catalog says right now. `$json` at this point is the LATTER \u2014 using\n// it for the former was the bug that shipped first: it silently dropped\n// reorder_id/productcode/quantity, and the write two nodes later failed on\n// \"path_productcode is a required property\" with no due-delivery context left\n// to explain why.\nconst due = $('Due deliveries').item.json;\n\nconst raw = $json ?? {};\nconst body = typeof raw === 'string' ? raw : (raw.data ?? JSON.stringify(raw));\nconst line = String(body).split('\\n').find((l) => l.startsWith('data:'));\nif (!line) return [{ json: { ...due, applied: false, why: 'unreadable catalog reply' } }];\n\nlet rpc;\ntry { rpc = JSON.parse(line.slice(5).trim()); }\ncatch (e) { return [{ json: { ...due, applied: false, why: 'unreadable catalog reply' } }]; }\nif (rpc.error || rpc.result?.isError) {\n  return [{ json: { ...due, applied: false, why: 'read failed' } }];\n}\n\nconst product = JSON.parse(rpc.result.content[0].text);\nconst newQuantity = Number(product.quantityinstock) + Number(due.quantity);\n\nreturn [{ json: { ...due, new_quantity: newQuantity } }];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        1100,
+        300
+      ],
+      "id": "apply-delivery",
+      "name": "Apply delivery"
+    },
+    {
+      "parameters": {
+        "method": "POST",
+        "url": "https://catalog-dev.sttlab.local/catalog-mcp",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "=Bearer {{ $('Machine token').item.json.access_token }}"
+            },
+            {
+              "name": "Accept",
+              "value": "application/json, text/event-stream"
+            },
+            {
+              "name": "mcp-session-id",
+              "value": "={{ $('MCP initialize').item.json.headers['mcp-session-id'] }}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ jsonrpc: '2.0', id: 3, method: 'tools/call', params: { name: 'patch-product', arguments: { path_productcode: $json.productcode, ['header_X-Stock-Change-Reason']: 'delivery:' + $json.reorder_id, body: { quantityinstock: $json.new_quantity } } } }) }}",
+        "options": {
+          "response": {
+            "response": {
+              "neverError": true
+            }
+          }
+        }
+      },
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [
+        1320,
+        300
+      ],
+      "id": "update-stock",
+      "name": "Update stock",
+      "alwaysOutputData": true
+    },
+    {
+      "parameters": {
+        "jsCode": "// Only clear the pending entry once the write is actually confirmed \u2014 the\n// classic-models-api response is the proof, never an assumption. A failed\n// PATCH here must leave the entry in place so tomorrow's run retries it,\n// rather than silently losing a delivery nobody applied.\nconst raw = $json ?? {};\nconst body = typeof raw === 'string' ? raw : (raw.data ?? JSON.stringify(raw));\nconst line = String(body).split('\\n').find((l) => l.startsWith('data:'));\n\nlet ok = false;\ntry {\n  const rpc = JSON.parse(line.slice(5).trim());\n  ok = !rpc.error && !rpc.result?.isError;\n} catch (e) {\n  ok = false;\n}\n\nconst pending = $('Apply delivery').item.json;\nif (!ok) {\n  return [{ json: { delivered: false, reorder_id: pending.reorder_id, why: 'the write did not confirm; retrying tomorrow' } }];\n}\n\nconst store = $getWorkflowStaticData('global');\nif (store.pendingDeliveries) delete store.pendingDeliveries[pending.reorder_id];\nreturn [{ json: { delivered: true, reorder_id: pending.reorder_id, productcode: pending.productcode, new_quantity: pending.new_quantity } }];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        1540,
+        300
+      ],
+      "id": "clear-delivery",
+      "name": "Confirm delivery"
+    }
+  ],
+  "connections": {
+    "Procurement events": {
+      "main": [
+        [
+          {
+            "node": "Only requests",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Only requests": {
+      "main": [
+        [
+          {
+            "node": "Decide the request",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Decide the request": {
+      "main": [
+        [
+          {
+            "node": "Build the answer",
+            "type": "main",
+            "index": 0
+          },
+          {
+            "node": "Schedule the delivery",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Build the answer": {
+      "main": [
+        [
+          {
+            "node": "Publish the answer",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Every morning (delivery)": {
+      "main": [
+        [
+          {
+            "node": "Machine token",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Machine token": {
+      "main": [
+        [
+          {
+            "node": "MCP initialize",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "MCP initialize": {
+      "main": [
+        [
+          {
+            "node": "Due deliveries",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Due deliveries": {
+      "main": [
+        [
+          {
+            "node": "Read current stock",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Read current stock": {
+      "main": [
+        [
+          {
+            "node": "Apply delivery",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Apply delivery": {
+      "main": [
+        [
+          {
+            "node": "Update stock",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Update stock": {
+      "main": [
+        [
+          {
+            "node": "Confirm delivery",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    }
+  },
+  "settings": {
+    "executionOrder": "v1"
+  }
+}

workflows/supply-stock-watch.json

@@ -0,0 +1,115 @@
+{
+  "name": "Supply \u2014 stock watch",
+  "nodes": [
+    {
+      "parameters": {
+        "topic": "classic-models.catalog",
+        "groupId": "supply-stock-watch",
+        "resolveOffset": "onCompletion",
+        "allowedStatuses": [
+          "success"
+        ],
+        "options": {
+          "jsonParseMessage": true,
+          "onlyMessage": true,
+          "fromBeginning": false
+        }
+      },
+      "type": "n8n-nodes-base.kafkaTrigger",
+      "typeVersion": 2,
+      "position": [
+        0,
+        0
+      ],
+      "id": "kafka-trigger-stock-watch",
+      "name": "Catalog events",
+      "credentials": {
+        "kafka": {
+          "id": "8qNZXLzvdx5rWQ0V",
+          "name": "kafka-classic-models"
+        }
+      }
+    },
+    {
+      "parameters": {
+        "jsCode": "// A stock movement, judged the moment it happens.\n//\n// This is the reactive half of Supply. The 06:00 run proposes\n// purchase orders on a buying cycle, which is genuinely periodic; noticing that\n// a reference is about to run out is not, and a nightly sweep would report at\n// 06:00 what was true at 14:32 the previous afternoon.\n//\n// What it reacts to is a fact the API published, not a row it went looking for.\nconst THRESHOLD = 50;\nconst COVER = 3;          // a proposal covers three times the threshold\nconst STOCK_CHANGED = 'com.sttlab.classicmodels.product.stock_changed.v1';\n\nconst event = $json ?? {};\n\n// The topic carries every catalog event, so most messages are not ours. Saying\n// so explicitly keeps the offset moving: a workflow that threw on an\n// uninteresting event would replay it forever.\nif (event.type !== STOCK_CHANGED) {\n  return [{ json: { considered: false, type: event.type ?? 'unreadable' } }];\n}\n\nconst data = event.data ?? {};\nconst before = Number(data.before?.quantityinstock);\nconst after = Number(data.after?.quantityinstock);\nif (!Number.isFinite(before) || !Number.isFinite(after)) {\n  return [{ json: {\n    considered: false,\n    escalate: true,\n    reason: `${event.subject}: the movement carried no readable quantities.`,\n  }}];\n}\n\n// Only a *crossing* is news. Without this, every further order line on an\n// already-low reference raises the same alarm again, and an agent that repeats\n// itself is one a human learns to ignore.\nconst crossed = before >= THRESHOLD && after < THRESHOLD;\n// A stock-out is a different fact from a low stock, even when the reference was\n// already below the threshold \u2014 nothing can be promised at all.\nconst emptied = after === 0 && before > 0;\n\n// `order:` means demand; anything else is someone correcting the books. Both\n// justify a purchase order, but only demand is a signal about the future.\nconst fromDemand = String(data.reason ?? '').startsWith('order:');\n\nconst store = $getWorkflowStaticData('global');\nstore.watchlist = store.watchlist ?? {};\n\nif (!crossed && !emptied) {\n  // Not news, but if this reference is already being watched its figures have\n  // just moved. Refresh them rather than leaving a human reading the number it\n  // held at the moment of detection, which is the number least likely to still\n  // be true.\n  const watched = store.watchlist[event.subject];\n  if (watched) {\n    watched.on_hand = after;\n    watched.propose_order = THRESHOLD * COVER - after;\n    watched.last_movement_at = event.time ?? new Date().toISOString();\n  }\n  return [{ json: {\n    considered: true,\n    detected: false,\n    watching: Boolean(watched),\n    productcode: event.subject,\n    on_hand: after,\n  }}];\n}\n\nconst state = { detected: true, escalate: true,\n  productcode: event.subject,\n  on_hand: after,\n  was: before,\n  threshold: THRESHOLD,\n  stock_out: after === 0,\n  driver: fromDemand ? 'demand' : 'correction',\n  movement: data.reason ?? null,\n  propose_order: THRESHOLD * COVER - after,\n  observed_at: event.time ?? new Date().toISOString(),\n  // Kept so this detection can be joined to the request that caused it. It is\n  // the only link back \u2014 the event deliberately names no actor.\n  traceparent: event.traceparent ?? null,\n};\n\nstate.reason = state.stock_out\n  ? `${state.productcode} is out of stock (was ${before}). Nothing can be promised.`\n  : `${state.productcode} fell from ${before} to ${after}, below the threshold of ${THRESHOLD}.`;\n\n// The watchlist is the destination, and it is a real one: the proposal still\n// has nowhere to be written \u2014 the domain has no purchase order and no supplier\n// entity \u2014 so a detection that only logged would be lost between two nightly\n// runs. Here it survives, keyed by reference so a reference cannot appear twice.\nstore.watchlist[state.productcode] = state;\n\nreturn [{ json: state }];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        220,
+        0
+      ],
+      "id": "detect-crossing",
+      "name": "Judge the movement"
+    },
+    {
+      "parameters": {
+        "httpMethod": [
+          "GET",
+          "POST"
+        ],
+        "path": "stock-watchlist",
+        "responseMode": "lastNode",
+        "options": {},
+        "multipleMethods": true
+      },
+      "type": "n8n-nodes-base.webhook",
+      "typeVersion": 2,
+      "position": [
+        0,
+        200
+      ],
+      "id": "watchlist-read",
+      "name": "Watchlist",
+      "webhookId": "stock-watchlist-get"
+    },
+    {
+      "parameters": {
+        "jsCode": "// What has been detected and not yet dealt with.\n//\n// A detection that goes only into an execution log is one nobody reads. This\n// makes the watchlist readable \u2014 by the periodic run, which can start from what\n// was already noticed rather than rediscovering it, and by a human.\n//\n// GET  /webhook/stock-watchlist        \u2192 the current list\n// POST /webhook/stock-watchlist        {\"clear\": [\"S24_2000\"]} \u2192 drop entries\nconst store = $getWorkflowStaticData('global');\nstore.watchlist = store.watchlist ?? {};\n\n// GET carries no body; the node still runs, and clear is then empty.\nconst body = $json.body ?? {};\nconst clear = Array.isArray(body.clear) ? body.clear : [];\nfor (const code of clear) delete store.watchlist[code];\n\nconst entries = Object.values(store.watchlist);\nreturn [{ json: {\n  watching: entries.length,\n  cleared: clear,\n  // Worst first: an out-of-stock reference is not the same problem as one that\n  // merely crossed the threshold.\n  entries: entries.sort((a, b) => a.on_hand - b.on_hand),\n}}];\n"
+      },
+      "type": "n8n-nodes-base.code",
+      "typeVersion": 2,
+      "position": [
+        220,
+        200
+      ],
+      "id": "watchlist-render",
+      "name": "Render the watchlist"
+    }
+  ],
+  "connections": {
+    "Catalog events": {
+      "main": [
+        [
+          {
+            "node": "Judge the movement",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    },
+    "Watchlist": {
+      "main": [
+        [
+          {
+            "node": "Render the watchlist",
+            "type": "main",
+            "index": 0
+          }
+        ],
+        [
+          {
+            "node": "Render the watchlist",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    }
+  },
+  "settings": {
+    "executionOrder": "v1"
+  }
+}