chore: bump version to 2.1.0

SIENTIAPDE-2202: timestamp e qualidade na escrita OPC por padrão (envs do gateway) + suíte e2e

.env.example

@@ -21,7 +21,6 @@ NATS_WRITE_SUBJECT="opc.write"
 NATS_QUEUE="gateway-writers"
 GRPC_ENABLED="false"
 GRPC_PORT="50051"
-CERT_BUCKET="sientia-dataops"
 CERT_CACHE_DIR="/tmp/opc-certs"
 WRITE_TIMESTAMP="true"
 WRITE_QUALITY="true"

.github/workflows/deploy.yml

@@ -1,10 +1,15 @@
 name: Deploy DataOps Worker
 
 on:
-  pull_request:
-    types: [closed]
-    branches: [main, 'release/**', 'feature/**']
   workflow_dispatch:
+    inputs:
+      chart_ref:
+        description: >
+          sientia-helm-chart branch to bump GITHUB_BRANCH on AND deploy — the literal
+          deploy target. Validated via git ls-remote; a branch that does not exist in
+          sientia-helm-chart is a hard error, not a silent fallback to main.
+        required: true
+        type: string
 
 permissions:
   contents: write
@@ -14,10 +19,10 @@ permissions:
 jobs:
   deploy:
     name: Deploy
-    if: github.event_name == 'workflow_dispatch' || github.event.pull_request.merged == true
     uses: Aignosi/github_workflow_templates/.github/workflows/reusable-deploy-dataops.yml@main
     with:
-      branch_name: ${{ github.event.pull_request.head.ref }}
+      branch_name: ${{ github.ref_name }}
+      chart_ref: ${{ inputs.chart_ref }}
       project_name: 'ingestor'
       chart_name: 'opc-ingestor'
       env_list_path: '[".env"]'

.github/workflows/quality-gate.yml

@@ -5,7 +5,6 @@ on:
     branches:
       - main
       - 'release/**'
-      - 'feature/**'
   pull_request:
     branches:
       - main

.github/workflows/require-chart-ref-label.yml

@@ -1,16 +0,0 @@
-name: Require chart-ref label
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, labeled, unlabeled]
-    branches:
-      - main
-      - 'release/**'
-      - 'feature/**'
-
-permissions:
-  pull-requests: write
-
-jobs:
-  require-chart-ref-label:
-    uses: Aignosi/github_workflow_templates/.github/workflows/require-chart-ref-label.yml@main

.github/workflows/version-bump.yml

@@ -0,0 +1,17 @@
+name: Version Bump
+
+permissions:
+  contents: write
+
+on:
+  pull_request:
+    types: [closed]
+    branches: [main, 'release/**', 'feature/**']
+
+jobs:
+  bump:
+    if: github.event.pull_request.merged == true
+    uses: Aignosi/github_workflow_templates/.github/workflows/reusable-version-bump.yml@main
+    with:
+      update_version_in: '["pyproject"]'
+    secrets: inherit

.gitignore

@@ -188,3 +188,6 @@ docs/superpowers/
 docs/e2e-test-guide.md
 docs/deploy-notes.md
 docs/HANDOFF.md
+
+openspec/
+.claude/

CLAUDE.md

@@ -17,9 +17,9 @@ pip install -r requirements.txt -r requirements-dev.txt
 ./run_local.sh                          # loads .env, runs python -m ingestor.app
 ./run_coverage.sh                       # pytest --cov=ingestor --cov-report=html, opens report
 
-pytest                                  # all tests
+pytest                                  # unit tests (testpaths = tests)
 pytest tests/unit                       # unit only
-pytest tests/functional                 # functional only (spins up real-ish clients, see conftest.py)
+pytest e2e/ -o testpaths=e2e -m integration   # E2E (Docker: testcontainers + in-process OPC servers)
 pytest tests/unit/test_ingestor.py::TestClass::test_name   # single test
 pytest --cov=ingestor --cov-report=html # coverage report -> htmlcov/
 
@@ -41,7 +41,6 @@ app.py (asyncio loop, signals, Prometheus server)
        -> IngestorManager (managers/ingestor_manager.py) — central coordinator
             -> ResourceManager (managers/resource_manager.py) — Redis slot leases, heartbeats, active-ingestor registry
             -> ServerReader (managers/server_reader.py), one per OPC server — SubscriptionEngine over the shared OpcConnectionPool
-               (READ_ENGINE=legacy: OpcManager (managers/opc_manager.py), the rc3 reader kept as plan B until the end of SIENTIAPDE-1974)
             -> OpcConnectionPool (connection/pool.py) + CertProvider (connection/certs.py) — pooled connections, cert from MinIO
             -> DataManager (managers/data_manager.py) — MongoDB persistence + optional Kafka publish
 ```
@@ -58,7 +57,9 @@ app.py (asyncio loop, signals, Prometheus server)
 
 Any change to slot/lease counts should be traced through `manage_leases`/`manage_no_slots` — that's where the rebalancing math lives, not in `ResourceManager` itself (which just does Redis primitives).
 
-**ServerReader** (SIENTIAPDE-1974, default `READ_ENGINE=v2`; the legacy `OpcManager` stays as plan B with `READ_ENGINE=legacy` — slot v1 only, certificate files from the Gitea clone — until it is unused and the tests pass the same without it) reads one OPC server through a `SubscriptionEngine`: the connection comes from the shared `OpcConnectionPool` (also used by NATS writes and gRPC), which fetches the platform certificate from MinIO via `CertProvider` and uses `SecurityPolicyBasic256Sha256` — no certificate files in the repo/image. Slots are parsed by `io/slots.py` (`parse_slot`), which accepts slot v2 (`names[]`) and converts the legacy v1 (`topics`). `datachange_notification` fans each value out to every `names` entry via `DataSink`. Subscribed connections are pinned in the pool so the idle sweep never drops them. Tracks `non_receive_count` to detect silently-dead subscriptions (`check_cycles` / `check_opc_listenning`); a lost server is shut down (pool connection evicted) and re-initialized on the next loop.
+**ServerReader** (SIENTIAPDE-1974) reads one OPC server through a `SubscriptionEngine`: the connection comes from the shared `OpcConnectionPool` (also used by NATS writes and gRPC). Slots are slot v2 only, parsed by `io/slots.py` (`parse_slot`): each server carries `security` (`mode`, `policy`) and `certificate` (certificate_id, application_uri, MinIO `bucket`/`object_name` of cert and private_key, from `opc_certificates` via the Orchestrator; `None` = connect without security, D5). The pool applies security only with a certificate (`connection/security.py`: `is_secured`, `apply_security` maps mode/policy to asyncua, unknown → error), and `CertProvider` downloads each certificate into `<CERT_CACHE_DIR>/<certificate_id>/` (cache, lock and `invalidate` per certificate) — no certificate files in the repo/image, no default certificate. A change of `security`/`certificate` in the slot re-initializes the reader (pool connection evicted). `datachange_notification` fans each value out to every `names` entry via `DataSink`. Subscribed connections are pinned in the pool so the idle sweep never drops them. Tracks `non_receive_count` to detect silently-dead subscriptions (`check_cycles` / `check_opc_listenning`); a lost server is shut down (pool connection evicted) and re-initialized on the next loop.
+
+**Writes** (SIENTIAPDE-1975): `NatsWriteConsumer` → `WriteEngine` → pool, then `DataSink.update_write_status`. Commands (C2) carry only `server_id`; `ServerConfigResolver` (`connection/servers.py`) resolves the connection: live pooled connection → `connectors` aggregation with a `$lookup` on `opc_certificates`, in the slot format. The certificate rule (active + client, `connection/certificates.py`) mirrors the Orchestrator's `tag_database.resolve_certificate` — keep both in sync (SIENTIAPDE-1974 D1; the Mongo fallback goes away when writes are routed to the pod that owns the connection). `write_status` keeps the worst outcome (`ok` < `error` < `session_bad`); the gateway is the only one that updates it (the Laborious inserts the row as `pending` and never records OPC outcomes). The NATS first connect is bounded (it runs on the main loop); reconnection after it is unbounded.
 
 **Metrics** (`ingestor/metrics.py`): all Prometheus metrics defined here, always labeled by `pod_id`. Emitted via `SientiaMonitoring.emit_metric(...)` (from `sientia_do`), not the prometheus client directly — new metrics should follow that pattern for consistency with logging/notifications.
 
@@ -71,6 +72,6 @@ Env vars documented in README ("Configuration" section) and `.env.example`. Nota
 ## Testing notes
 
 - `tests/unit/managers/` mirrors `ingestor/managers/` 1:1.
-- `tests/functional/` exercises more end-to-end paths against `conftest.py` fixtures.
+- `e2e/` is the end-to-end suite (Laborious/Orchestrator pattern): real MongoDB/Redis/Postgres/MinIO/NATS via testcontainers, in-process asyncua servers, pods built like `app.py` (`e2e/helpers.Pod`). Scenarios are numbered by topic in `e2e/scenarios.md`, 1:1 with `test_scenario_<n>_<n>_<n>_*` — keep both in sync. Marked `integration`, not collected by the default `pytest`.
 - Coverage config (`pyproject.toml` / `.coveragerc`) excludes `ingestor/app.py` (thin entrypoint, signal wiring) — don't chase coverage there.
 - `ruff` complexity cap is `max-complexity = 15` (mccabe) — factor out branches in manager methods before that.

README.md

@@ -56,19 +56,56 @@ Gateway for on-demand and command-driven interactions with OPC UA servers:
 
 - **NATS write consumer**: consumes write commands from `opc.write` (see
   `NATS_WRITE_SUBJECT`) and executes them against the target OPC server
-  (`ingestor/adapters/nats_consumer.py`, `ingestor/engines/write.py`).
+  (`ingestor/adapters/nats_consumer.py`, `ingestor/engines/write.py`). See
+  [Write commands](#write-commands-c2-and-write_status-c3) below.
 - **On-demand gRPC `ReadTag`**: a gRPC server (`ingestor/adapters/grpc_server.py`,
   `ingestor/proto/opc_gateway.proto`) for synchronous, single-tag reads.
 - **Scheduled active reads**: a polling read engine (`ingestor/engines/active_read.py`)
   for tags that need periodic reads outside the subscription pipeline;
   orchestrator-side wiring lands in SIENTIAPDE-1974.
-- **Certificate management**: client certs for secure OPC connections are
-  fetched from MinIO + a Mongo `platform_certificates` collection
+- **Certificate management**: each OPC connector has its own client certificate
+  (`opc_certificates`), named in the slot and downloaded from MinIO
   (`ingestor/connection/certs.py`) rather than shipped in the image.
 
-See `docs/deploy-notes.md` for the deployment-facing details (env vars,
-health probe, NetworkPolicy, cert cache) and the `# OPC Gateway` block in
-`.env.example` for the full list of new environment variables.
+See [Gateway environment variables](#gateway-environment-variables) and the
+`# OPC Gateway` blocks in `.env.example` for the new environment variables.
+
+### Write commands (C2) and `write_status` (C3)
+
+The Laborious publishes one command per tag (SIENTIAPDE-1975):
+
+```json
+{"server_id": "1", "addr": "ns=2;s=Pred", "value": 1.25, "data_type": "float",
+ "model_id": "2", "model_name": "sin-approx", "schema": "sientia_data",
+ "table_name": "predictions", "timestamp": "2026-10-13T12:00:00-03:00"}
+```
+
+- **Written `DataValue`** (SIENTIAPDE-2202): the value, plus the prediction
+  `timestamp` as `SourceTimestamp` and a Good `StatusCode`. Timestamp and quality can be
+  turned off separately; the value is always written. Each flag is taken from the
+  command (`write_timestamp` / `write_quality`) when present, else from the env
+  (`WRITE_TIMESTAMP` / `WRITE_QUALITY`), else `true`. The envs apply to every server of
+  the gateway (per-server config is a future SIENTIAPDE-2276 card).
+
+- **Server connection**: the command carries only `server_id`. The connection is
+  resolved by `ServerConfigResolver` (`ingestor/connection/servers.py`): the live
+  pooled connection opened by the reads, else the `connectors` document (`type: opc_ua`,
+  `status: Active`) joined with `opc_certificates`, with the orchestrator's rule for the
+  read slots (`ingestor/connection/certificates.py`), in the slot format (`url`,
+  `security`, `certificate`). Lookups are cached for 60 s. An unknown or incomplete
+  server is a failed write (`server_not_found`).
+- **Outcome**: `UPDATE ... SET write_status` on the prediction row (by `timestamp` +
+  `model_id`), keeping the worst outcome: `ok` < `error` < `session_bad`, and
+  `pending`/NULL are replaced by any answer, so the order of the answers does not
+  matter. The gateway is the only one that updates the column: the Laborious inserts the
+  row as `pending` (merged with its PI Web API outcome) and never records OPC outcomes.
+  The UPDATE never raises; its outcome (`updated`, `kept`, `row_not_found`,
+  `invalid`, `error`) is logged and counted in `opc_write_status_update_total`.
+  The reason of a failed write is logged by `WriteEngine`.
+- **NATS connection**: the first connection gives up after 5 s (it runs on the main
+  loop: nats-py's defaults would block it for minutes while NATS is down); once
+  connected, it reconnects forever. A connection closed for good is started again
+  by `GatewayRuntime.idle_sweep`.
 
 ## 📋 Prerequisites
 
@@ -195,48 +232,42 @@ The feeder creates sample OPC tag configurations in Redis that the ingestor can
 
 ## 🔐 OPC Client Certificate
 
-OPC UA servers that require secure connections validate the gateway with a single,
-shared platform X.509 client certificate. Every OPC connection — subscription reads,
-NATS writes and gRPC reads — uses it with `Basic256Sha256` (SIENTIAPDE-1974).
+Each OPC connector has its own X.509 client certificate (SIENTIAPDE-1974): the
+connector's `security.client_certificate_id` points to an `opc_certificates` document
+(`kind: client`, `status: active`). The Orchestrator joins them and writes, for each
+server of the slot, its `security` (`mode`, `policy`) and its `certificate`:
+
+```json
+"certificate": {
+  "certificate_id": 1,
+  "application_uri": "urn:sientia:opc-ingestor",
+  "cert": {"bucket": "opc-certificates", "object_name": "client/sientia-platform/opc-ingestor-cert.pem"},
+  "private_key": {"bucket": "opc-certificates", "object_name": "client/sientia-platform/opc-ingestor-key.pem"}
+}
+```
 
 The certificate is **never** read from the repository or the image. On connect, the
-`CertProvider` (`ingestor/connection/certs.py`):
-1. reads the single document of the Mongo collection `platform_certificates`:
-   `{"client_cert": {"minio_object_name": "..."}, "private_key": {"minio_object_name": "..."}}`;
-2. downloads both objects from the MinIO bucket `CERT_BUCKET` (default
-   `streamlit-connectors`) into `CERT_CACHE_DIR` (default `/tmp/opc-certs`).
+`CertProvider` (`ingestor/connection/certs.py`) downloads both objects from MinIO into
+`CERT_CACHE_DIR/<certificate_id>/` (default `/tmp/opc-certs`), and caches them per
+certificate. When the slot names other objects for the same certificate (it was
+replaced), the server config changes, the connection is re-opened and the files are
+downloaded again. A failed secured connection also forces a new download.
 
-Requirements for a server to accept the connection:
-- the server's slot config has `use_security: true` (a slot v1 server with a
-  `cert_path` is treated the same way; the path itself is ignored);
-- the certificate's SAN URI equals the server's `server_uri` in the slot — it is sent
-  as the client `application_uri` (KEPServer rejects a mismatch with
-  `BadCertificateUriInvalid`);
-- the server exposes a `Basic256Sha256` endpoint and trusts the certificate (e.g.
-  KEPServer: *OPC UA Configuration Manager → Trusted Clients → Trust*, then restart
-  its runtime).
+- **Security only with a certificate.** With a `certificate`, the connection uses the
+  slot's `security.mode` (`Sign` / `SignAndEncrypt`) and `security.policy`
+  (`Basic256Sha256`, `Aes128Sha256RsaOaep`, `Aes256Sha256RsaPss`, `Basic256`,
+  `Basic128Rsa15`); an unknown one fails the connection. Without a certificate
+  (`null`), or with `mode: None`, it connects without security, and a server that
+  requires a certificate refuses the connection (the error shows in the log and the
+  connection metrics). There is no default certificate.
+- The certificate's `application_uri` (its SAN URI) is sent as the client application
+  URI (KEPServer rejects a mismatch with `BadCertificateUriInvalid`).
+- The server must trust the certificate (e.g. KEPServer: *OPC UA Configuration Manager
+  → Trusted Clients → Trust*, then restart its runtime).
 
-MinIO is only contacted when a certificate is first needed, so a MinIO outage only
-affects secured servers, which are retried on the next main-loop iteration.
-
-### Plan B: legacy read engine (`READ_ENGINE=legacy`)
-
-Until the end of SIENTIAPDE-1974 the legacy reader is kept for validation and as a
-fallback. `READ_ENGINE` selects the read path (default `v2`; an invalid value falls
-back to `v2` with a warning):
-
-| `READ_ENGINE` | Reader | Slot | Certificate |
-|---|---|---|---|
-| `v2` (default) | `ServerReader` + `SubscriptionEngine` over the shared pool | v1 or v2 | MinIO + Mongo (`CertProvider`), `Basic256Sha256` |
-| `legacy` | the rc3 `OpcManager`, unchanged, with its own connection | **v1 only** (a v2 slot is rejected and notified) | files from the repository the pod clones (`cert_path` / `private_key_path` in the slot), `Basic256` |
-
-Writes and gRPC always use the pool (MinIO certificate), whatever the read engine.
-The legacy engine needs the certificate files in the Gitea branch the pod clones;
-`scripts/generate-and-push-opc-cert.sh` generates them and pushes them to
-`certs/` (`GITEA_PASSWORD='<senha>' BRANCH=<branch> ./scripts/generate-and-push-opc-cert.sh`).
-Each version deploy creates a new Gitea branch without `certs/`, so they have to be
-copied again for the legacy engine. Remove the legacy engine (OpcManager, its tests
-and the script) once it is unused and the test suite passes the same without it.
+MinIO is only contacted when a certificate is first needed (one client per bucket), so
+a MinIO outage only affects secured servers, which are retried on the next main-loop
+iteration.
 
 ## 🧪 Testing
 
@@ -256,11 +287,14 @@ pytest --cov=ingestor
 pytest --cov=ingestor --cov-report=html
 ```
 
-### Functional Tests
+### End-to-end Tests
+Every dependency runs for real (MongoDB, Redis, PostgreSQL, MinIO and NATS via testcontainers;
+OPC UA servers in process). Requires Docker; not part of the default `pytest` run.
 ```bash
-# Run functional tests
-pytest tests/functional/
+pytest e2e/ -o testpaths=e2e -m integration
 ```
+Numbered scenarios (slot leasing, reads, writes, gRPC, active reads, certificates, lifecycle):
+[`e2e/scenarios.md`](e2e/scenarios.md). Setup and layout: [`e2e/README.md`](e2e/README.md).
 
 ## 📊 Monitoring and Metrics
 
@@ -290,6 +324,9 @@ The OPC Ingestor exposes comprehensive Prometheus metrics for monitoring:
 ### OPC Gateway Metrics
 - `opc_write_total`: Active write attempts (NATS-driven), by result
 - `opc_write_latency_seconds`: Active write latency
+- `opc_write_status_by_model`: Last write outcome per model (1 = ok, 0 = failed; label `status`)
+- `opc_write_status_update_total`: `write_status` UPDATEs, by result
+  (`updated`, `kept`, `row_not_found`, `invalid`, `error`)
 - `opc_active_read_total`: Scheduled/on-demand read attempts, by result
 - `opc_error_by_type_total`: OPC errors by type (connection, conversion, session, ...)
 
@@ -313,17 +350,36 @@ The OPC Ingestor exposes comprehensive Prometheus metrics for monitoring:
 | `MONGODB_PASSWORD` | MongoDB password | `sientia` | No |
 | `HTTP_METRICS_PORT` | Prometheus metrics port | `9090` | No |
 
-See the `# OPC Gateway` block in `.env.example` (`NATS_URL`, `GRPC_ENABLED`,
-`CERT_BUCKET`, `WRITE_TIMESTAMP`, ...) and `docs/deploy-notes.md` for the
-gateway-specific environment variables.
+#### Gateway environment variables
+
+Read by `GatewayConfig` (`ingestor/config.py`). Booleans accept `true`/`1`/`yes`
+(case-insensitive); anything else is `false`.
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `NATS_URL` | NATS server for write commands (C2) | `nats://localhost:4222` |
+| `NATS_WRITE_SUBJECT` | Subject of the write commands | `opc.write` |
+| `NATS_QUEUE` | Queue group shared by the gateway pods | `gateway-writers` |
+| `GRPC_ENABLED` | Starts the on-demand `ReadTag` gRPC server | `false` |
+| `GRPC_PORT` | gRPC server port | `50051` |
+| `CERT_CACHE_DIR` | Local cache of the client certificates downloaded from MinIO | `/tmp/opc-certs` |
+| `WRITE_TIMESTAMP` | Writes the prediction `timestamp` as `SourceTimestamp` when the command has no `write_timestamp` | `true` |
+| `WRITE_QUALITY` | Writes a Good `StatusCode` when the command has no `write_quality` | `true` |
+| `WRITE_MIN_PAUSE_S` | Minimum pause between two OPC writes (seconds) | `0.0` |
+| `IDLE_CONN_MAX_S` | Idle time before an unpinned pool connection is closed (seconds) | `300.0` |
+
+`WRITE_TIMESTAMP` / `WRITE_QUALITY` are independent and apply to every OPC server of
+the gateway; the value is always written. See [Write commands](#write-commands-c2-and-write_status-c3)
+for the precedence (command → env → `true`). MinIO (`MINIO_*`) and Postgres
+(`POSTGRES_*`) settings are listed in `.env.example`.
 
 ### OPC Server Configuration
 
 OPC servers are configured by the Orchestrator through Redis, one key per slot
 (`slot:opc_tags:<n>`). The gateway reads the **slot v2** structure (contract C1):
 one entry per address, with one `names` item per collection / tag name / model, so
-the same address can feed several models under different names. For secured
-connections set `use_security: true` (the certificate comes from MinIO, see
+the same address can feed several models under different names. Each server carries
+its `security` and its `certificate` (`null` = no security, see
 [OPC Client Certificate](#-opc-client-certificate)):
 
 ```json
@@ -331,11 +387,16 @@ connections set `use_security: true` (the certificate comes from MinIO, see
   "slot:opc_tags:1": {
     "server1": {
       "name": "server1",
-      "server_id": "1",
+      "server_id": "kepserver",
       "url": "opc.tcp://localhost:4841",
-      "server_uri": "urn:sientia:opc-ingestor",
-      "use_security": true,
       "subscription_period_ms": 7500,
+      "security": {"mode": "SignAndEncrypt", "policy": "Basic256Sha256"},
+      "certificate": {
+        "certificate_id": 1,
+        "application_uri": "urn:sientia:opc-ingestor",
+        "cert": {"bucket": "opc-certificates", "object_name": "client/sientia-platform/opc-ingestor-cert.pem"},
+        "private_key": {"bucket": "opc-certificates", "object_name": "client/sientia-platform/opc-ingestor-key.pem"}
+      },
       "tags": {
         "ns=2;i=2": {
           "frequency": "15000",
@@ -351,11 +412,10 @@ connections set `use_security: true` (the certificate comes from MinIO, see
 }
 ```
 
-The legacy **slot v1** (each tag with `tag_name` + `topics`, the server with
-`cert_path`) is still accepted and converted on read (`ingestor/io/slots.py`): one
-`names` item per topic, and `use_security` is true when `cert_path` is set (the path
-itself is ignored). This lets the gateway and the Orchestrator be deployed in any
-order. Documents written from a v1 slot have no `model_id`, exactly as before.
+Only the slot v2 is accepted (`ingestor/io/slots.py`): a slot without `security`, a
+tag without `names`, or a name without `collection`, `tag_name` or `model_id` is
+rejected and notified (`OPC_SLOT_CONFIG_ERROR_<slot>`), and the last good config keeps
+being read. The gateway and the Orchestrator of SIENTIAPDE-1974 are deployed together.
 
 ## 🔧 Development
 
@@ -366,14 +426,13 @@ sientia-dataops-opc-ingestor/
 │   ├── managers/            # Component managers
 │   │   ├── data_manager.py # Data persistence and export
 │   │   ├── ingestor_manager.py # Main coordination
-│   │   ├── opc_manager.py  # Legacy reader, plan B (READ_ENGINE=legacy)
 │   │   ├── resource_manager.py # Resource coordination
 │   │   └── server_reader.py # OPC UA server reads (SubscriptionEngine + pool)
 │   ├── app.py              # Main application entry point
 │   ├── ingestor.py         # Core ingestor logic
 │   └── metrics.py          # Prometheus metrics definitions
 ├── simulator/               # OPC simulation and testing tools
-├── scripts/                 # Ops scripts (e2e seed; legacy OPC cert generation)
+├── scripts/                 # Ops scripts (e2e seed)
 ├── tests/                   # Test suite
 └── requirements.txt         # Python dependencies
 ```

e2e/README.md

@@ -0,0 +1,48 @@
+# OPC Gateway end-to-end tests
+
+End-to-end tests run every external dependency for real (MongoDB, Redis, PostgreSQL, MinIO and
+NATS via testcontainers; OPC UA servers in process with asyncua) and build each gateway pod from
+the environment exactly like `ingestor/app.py` does.
+
+## Requirements
+
+- Docker (for testcontainers), with the reaper disabled once per machine:
+  `echo "ryuk.disabled=true" >> ~/.testcontainers.properties` (see [scenarios.md](scenarios.md)).
+- Python dev dependencies: `pip install -r requirements.txt -r requirements-dev.txt`
+
+## Run locally
+
+```bash
+source ./venv/bin/activate
+pytest e2e/ -o testpaths=e2e -m integration
+```
+
+One topic, or stop on first failure:
+
+```bash
+pytest e2e/test_writes.py -o testpaths=e2e -m integration
+pytest e2e/ -o testpaths=e2e -m integration -x
+```
+
+The default `pytest` run only collects `tests/` (`testpaths`), so the E2E suite never runs there.
+
+## Layout
+
+| Path | Content |
+|---|---|
+| `conftest.py` | Containers (session), environment + state reset (per test), factories: `opc_servers`, `pods`, `put_slot`, `publish_command`, `client_certificate`, `opc_wire` |
+| `helpers.py` | `Pod` (one gateway pod, `tick()` = one main loop iteration), `load_scenario_input`, `wait_until`/`stays_false`, Mongo/Postgres/Redis queries, DataValue mask |
+| `opc_server.py` | In-process OPC UA server (`ns=2;s=<name>` variables, restart, secured mode, received writes) |
+| `db_schema.sql` | `sientia_data.predictions` DDL, mirrored from production |
+| `scenario_inputs/` | Slots (v2), connector and write command used by the scenarios |
+| `test_*.py` | One file per topic, `test_scenario_<topic>_<group>_<n>_*` |
+
+## Coverage (separate from unit tests)
+
+```bash
+COVERAGE_FILE=.coverage.e2e pytest e2e/ -o testpaths=e2e -m integration --cov=ingestor --cov-branch
+```
+
+## Scenario catalog
+
+See [scenarios.md](scenarios.md) for the numbered scenarios and which test implements each one.

e2e/conftest.py

@@ -0,0 +1,355 @@
+"""Pytest configuration and fixtures for the gateway E2E tests.
+
+Every external dependency runs for real: MongoDB, Redis, PostgreSQL, MinIO and NATS
+via testcontainers (session-scoped), OPC UA servers in process (``e2e/opc_server.py``,
+function-scoped). Gateway code under ``ingestor/**`` is not mocked: pods are built from
+the environment exactly like ``ingestor/app.py`` builds them (``e2e/helpers.Pod``).
+State is reset before every test.
+"""
+
+import io
+import json
+import os
+from pathlib import Path
+
+import nats
+import pytest
+import pytest_asyncio
+from asyncua import ua
+from asyncua.client import ua_client
+from minio import Minio
+from pymongo import MongoClient
+from redis import Redis
+from sqlalchemy import create_engine, text
+from testcontainers.community.minio import MinioContainer
+from testcontainers.community.mongodb import MongoDbContainer
+from testcontainers.community.postgres import PostgresContainer
+from testcontainers.community.redis import RedisContainer
+from testcontainers.core.container import DockerContainer
+from testcontainers.core.wait_strategies import LogMessageWaitStrategy
+
+from e2e.helpers import CERT_BUCKET, Pod
+from e2e.opc_server import OpcTestServer, free_port, make_certificate
+
+DB_SCHEMA_SQL_PATH = Path(__file__).parent / 'db_schema.sql'
+MONGO_USER = MONGO_PASSWORD = 'sientia'
+MONGO_DATABASE = 'sientia_e2e'
+WRITE_SUBJECT = 'opc.write'
+
+
+# --------------------------------------------------------------------------------------
+# Session infrastructure
+# --------------------------------------------------------------------------------------
+
+
+@pytest.fixture(scope='session')
+def mongo_container():
+    """MongoDB with root credentials: the gateway always connects as user:password@url."""
+    mongo = MongoDbContainer('mongo:7', username=MONGO_USER, password=MONGO_PASSWORD)
+    mongo.start()
+    yield mongo
+    mongo.stop()
+
+
+@pytest.fixture(scope='session')
+def redis_container():
+    redis = RedisContainer('redis:7-alpine')
+    redis.start()
+    yield redis
+    redis.stop()
+
+
+@pytest.fixture(scope='session')
+def postgres_container():
+    postgres = PostgresContainer(
+        'postgres:15', username='sientia', password='sientia', dbname='sientia'
+    )
+    postgres.start()
+    yield postgres
+    postgres.stop()
+
+
+@pytest.fixture(scope='session')
+def minio_container():
+    """
+    MinIO holding the OPC client certificates. Same Bitnami "legacy" image as the
+    Laborious E2E suite and production: Docker Hub no longer serves ``minio/minio``.
+    """
+    minio = MinioContainer(image='docker.io/bitnamilegacy/minio:2025.7.23-debian-12-r3')
+    minio.with_env('MINIO_ROOT_USER', minio.access_key)
+    minio.with_env('MINIO_ROOT_PASSWORD', minio.secret_key)
+    minio.with_kwargs(user='root')
+    minio.start()
+    yield minio
+    minio.stop()
+
+
+NATS_IMAGE = 'nats:2.10-alpine'
+
+
+def nats_server_container(host_port: int | None = None) -> DockerContainer:
+    """NATS server; ``host_port`` pins the published port (to start it after the gateway)."""
+    container = DockerContainer(NATS_IMAGE).waiting_for(LogMessageWaitStrategy('Server is ready'))
+    if host_port is None:
+        return container.with_exposed_ports(4222)
+    return container.with_bind_ports(4222, host_port)
+
+
+@pytest.fixture(scope='session')
+def nats_container():
+    nats_server = nats_server_container()
+    nats_server.start()
+    yield nats_server
+    nats_server.stop()
+
+
+@pytest.fixture(scope='session')
+def mongo_client(mongo_container):
+    port = mongo_container.get_exposed_port(27017)
+    client = MongoClient(f'mongodb://{MONGO_USER}:{MONGO_PASSWORD}@localhost:{port}')
+    yield client
+    client.close()
+
+
+@pytest.fixture(scope='session')
+def postgres_engine(postgres_container):
+    engine = create_engine(postgres_container.get_connection_url())
+    yield engine
+    engine.dispose()
+
+
+@pytest.fixture(scope='session')
+def redis_client(redis_container):
+    client = Redis(
+        host=redis_container.get_container_host_ip(),
+        port=int(redis_container.get_exposed_port(6379)),
+        decode_responses=True,
+    )
+    yield client
+    client.close()
+
+
+@pytest.fixture(scope='session')
+def minio_client(minio_container):
+    return minio_container.get_client()
+
+
+@pytest.fixture(scope='session')
+def nats_url(nats_container) -> str:
+    host = nats_container.get_container_host_ip()
+    return f'nats://{host}:{nats_container.get_exposed_port(4222)}'
+
+
+# --------------------------------------------------------------------------------------
+# Per-test environment and state reset
+# --------------------------------------------------------------------------------------
+
+
+@pytest.fixture(autouse=True)
+def gateway_env(
+    monkeypatch,
+    tmp_path,
+    mongo_container,
+    redis_container,
+    postgres_container,
+    minio_container,
+    nats_url,
+):
+    """Point every gateway setting at the containers, with the app's defaults otherwise."""
+    minio_cfg = minio_container.get_config()
+    env = {
+        'HOSTNAME': 'pod-a',
+        'REDIS_HOST': redis_container.get_container_host_ip(),
+        'REDIS_PORT': str(redis_container.get_exposed_port(6379)),
+        'LEASE_TTL': '10',
+        'HEARTBEAT_TTL': '20',
+        'POLL_INTERVAL': '1',
+        'MONGODB_URL': f'localhost:{mongo_container.get_exposed_port(27017)}',
+        'MONGODB_USERNAME': MONGO_USER,
+        'MONGODB_PASSWORD': MONGO_PASSWORD,
+        'MONGODB_DATABASE': MONGO_DATABASE,
+        'POSTGRES_HOST': postgres_container.get_container_host_ip(),
+        'POSTGRES_PORT': str(postgres_container.get_exposed_port(5432)),
+        'POSTGRES_USER': 'sientia',
+        'POSTGRES_PASSWORD': 'sientia',
+        'POSTGRES_DBNAME': 'sientia',
+        'POSTGRES_MIN_CONNECTIONS': '1',
+        'POSTGRES_MAX_CONNECTIONS': '2',
+        'MINIO_ENDPOINT': minio_cfg['endpoint'],
+        'MINIO_ACCESS_KEY': minio_cfg['access_key'],
+        'MINIO_SECRET_KEY': minio_cfg['secret_key'],
+        'MINIO_SECURE': 'false',
+        'NATS_URL': nats_url,
+        'NATS_WRITE_SUBJECT': WRITE_SUBJECT,
+        'NATS_QUEUE': 'gateway-writers',
+        'GRPC_ENABLED': 'false',
+        'GRPC_PORT': str(free_port()),
+        'CERT_CACHE_DIR': str(tmp_path / 'cert-cache'),
+        'WRITE_MIN_PAUSE_S': '0',
+        'IDLE_CONN_MAX_S': '300',
+    }
+    for name, value in env.items():
+        monkeypatch.setenv(name, value)
+    for name in ('REDIS_USERNAME', 'REDIS_PASSWORD', 'WRITE_TIMESTAMP', 'WRITE_QUALITY'):
+        monkeypatch.delenv(name, raising=False)
+    return env
+
+
+@pytest.fixture(autouse=True)
+def reset_state(redis_client, mongo_client, postgres_engine, minio_client):
+    """Known-empty baseline: Redis flushed, Mongo database dropped, Postgres schema
+    recreated from ``e2e/db_schema.sql``, certificate bucket emptied."""
+    redis_client.flushdb()
+    mongo_client.drop_database(MONGO_DATABASE)
+    with postgres_engine.begin() as conn:
+        conn.execute(text('DROP SCHEMA IF EXISTS sientia_data CASCADE'))
+        conn.exec_driver_sql(DB_SCHEMA_SQL_PATH.read_text(encoding='utf-8'))
+    if minio_client.bucket_exists(CERT_BUCKET):
+        for obj in minio_client.list_objects(CERT_BUCKET, recursive=True):
+            minio_client.remove_object(CERT_BUCKET, obj.object_name)
+    else:
+        minio_client.make_bucket(CERT_BUCKET)
+    yield
+
+
+@pytest.fixture
+def mongo_db(mongo_client):
+    return mongo_client[MONGO_DATABASE]
+
+
+# --------------------------------------------------------------------------------------
+# Factories: OPC servers, pods, slots, certificates, NATS commands
+# --------------------------------------------------------------------------------------
+
+
+@pytest_asyncio.fixture
+async def opc_servers(tmp_path):
+    """
+    Factory of started in-process OPC servers.
+
+    ``await opc_servers('plant-a', {'Temperature': 20.0}, secured=False)`` declares the
+    variables (``{name: value}`` or ``{name: (value, data_type, writable)}``) and starts it.
+    """
+    started: dict[str, OpcTestServer] = {}
+
+    async def start(name: str, variables: dict, secured: bool = False) -> OpcTestServer:
+        server = OpcTestServer(name, cert_dir=tmp_path / 'server-certs', secured=secured)
+        for var, spec in variables.items():
+            value, data_type, writable = spec if isinstance(spec, tuple) else (spec, 'float', True)
+            server.add_variable(var, value, data_type, writable)
+        await server.start()
+        started[name] = server
+        return server
+
+    yield start
+    for server in started.values():
+        await server.stop()
+
+
+@pytest_asyncio.fixture
+async def pods(monkeypatch):
+    """
+    Factory of started gateway pods: ``await pods('pod-a', runtime=True, **env)``.
+
+    Extra keyword arguments are environment overrides applied before the pod is built
+    (e.g. ``WRITE_TIMESTAMP='false'``). Every pod is stopped at teardown.
+    """
+    started: list[Pod] = []
+
+    async def start(name: str = 'pod-a', runtime: bool = True, **env: str) -> Pod:
+        for key, value in env.items():
+            monkeypatch.setenv(key, value)
+        pod = Pod(name, runtime=runtime)
+        started.append(pod)
+        return await pod.start()
+
+    yield start
+    for pod in reversed(started):
+        await pod.stop()
+
+
+@pytest.fixture
+def put_slot(redis_client):
+    """Write a slot v2 to Redis (``slot:opc_tags:<n>``), as the Orchestrator does."""
+
+    def put(number: int, slot: dict) -> None:
+        redis_client.set(f'slot:opc_tags:{number}', json.dumps(slot))
+
+    return put
+
+
+@pytest_asyncio.fixture
+async def publish_command(nats_url):
+    """Publish C2 write commands (dicts) or raw payloads (bytes) on the write subject."""
+    client = await nats.connect(nats_url)
+
+    async def publish(payload) -> None:
+        data = payload if isinstance(payload, bytes) else json.dumps(payload).encode()
+        await client.publish(WRITE_SUBJECT, data)
+        await client.flush()
+
+    yield publish
+    await client.drain()
+
+
+@pytest_asyncio.fixture
+async def client_certificate(tmp_path, minio_client: Minio, mongo_db):
+    """
+    Create an OPC client certificate the way the platform stores it: cert (DER) and
+    private key (PEM) uploaded to MinIO, and an ``opc_certificates`` document (active,
+    kind client). Returns the certificate in the slot format (contract C1).
+    """
+
+    async def create(
+        certificate_id: int,
+        upload: bool = True,
+        status: str = 'active',
+        app_uri: str | None = None,
+    ) -> dict:
+        app_uri = app_uri or f'urn:sientia:e2e:client:{certificate_id}'
+        cert, key = await make_certificate(
+            tmp_path / 'client-certs', f'client-{certificate_id}', app_uri, server=False
+        )
+        objects = {
+            'cert': {'bucket': CERT_BUCKET, 'object_name': f'{certificate_id}/client.der'},
+            'private_key': {'bucket': CERT_BUCKET, 'object_name': f'{certificate_id}/client.pem'},
+        }
+        if upload:
+            for path, field in ((cert, 'cert'), (key, 'private_key')):
+                data = path.read_bytes()
+                minio_client.put_object(
+                    CERT_BUCKET, objects[field]['object_name'], io.BytesIO(data), len(data)
+                )
+        mongo_db['opc_certificates'].insert_one(
+            {
+                'certificate_id': certificate_id,
+                'kind': 'client',
+                'status': status,
+                'application_uri': app_uri,
+                **objects,
+            }
+        )
+        return {'certificate_id': certificate_id, 'application_uri': app_uri, **objects}
+
+    return create
+
+
+@pytest.fixture
+def cert_cache_dir() -> Path:
+    return Path(os.environ['CERT_CACHE_DIR'])
+
+
+@pytest.fixture
+def opc_wire(monkeypatch):
+    """Serialized WriteRequests, exactly as the gateway's OPC client sends them."""
+    sent: list[bytes] = []
+    original = ua_client.struct_to_binary
+
+    def capture(obj):
+        data = original(obj)
+        if isinstance(obj, ua.WriteRequest):
+            sent.append(data)
+        return data
+
+    monkeypatch.setattr(ua_client, 'struct_to_binary', capture)
+    return sent

e2e/db_schema.sql

@@ -0,0 +1,33 @@
+-- =============================================================================
+-- E2E test database schema for the ``sientia_data`` namespace.
+--
+-- Mirrors the production DDL one-to-one so any change in production can be
+-- pasted directly into this file. The conftest fixture drops the schema and
+-- loads this SQL into the testcontainers Postgres before every test.
+--
+-- The gateway only touches ``sientia_data.predictions``: it updates
+-- ``write_status`` (contract C3, SIENTIAPDE-1975) on the row the Laborious
+-- inserted. Same DDL as ``sientia-dataops-laborious/e2e/db_schema.sql``.
+-- =============================================================================
+
+CREATE SCHEMA IF NOT EXISTS sientia_data;
+
+-- -----------------------------------------------------------------------------
+-- sientia_data.predictions
+-- -----------------------------------------------------------------------------
+CREATE TABLE IF NOT EXISTS sientia_data.predictions (
+    model_id              int4 NOT NULL,
+    prediction            numeric NULL,
+    prediction_confidence numeric NOT NULL,
+    response_time         numeric NOT NULL,
+    prediction_status     text NOT NULL,
+    "timestamp"           timestamptz NOT NULL,
+    created_at            timestamptz DEFAULT CURRENT_TIMESTAMP NOT NULL,
+    "comments"            text NULL,
+    metadata_id           varchar(24) NULL,
+    write_status          text NULL,
+    CONSTRAINT unique_model_id_timestamp
+        UNIQUE (model_id, "timestamp"),
+    CONSTRAINT chk_predictions_write_status
+        CHECK (write_status IN ('pending', 'ok', 'error', 'session_bad'))
+);

e2e/helpers.py

@@ -0,0 +1,243 @@
+"""Shared helpers for the gateway E2E tests (OPC UA + Redis + MongoDB + Postgres + MinIO + NATS)."""
+
+import asyncio
+import copy
+import inspect
+import json
+import os
+import time
+from collections.abc import Awaitable, Callable
+from pathlib import Path
+from typing import Any
+
+from asyncua import ua
+from asyncua.ua.ua_binary import Primitives, nodeid_to_binary
+from pymongo.database import Database
+from sqlalchemy import text
+from sqlalchemy.engine import Engine
+
+from ingestor.config import GatewayConfig
+from ingestor.gateway_runtime import GatewayRuntime
+from ingestor.ingestor import Ingestor
+
+SCENARIO_INPUTS_DIR = Path(__file__).parent / 'scenario_inputs'
+
+# Collections the gateway reads (connectors, opc_certificates) or writes
+# (readings, notification_queue). Dropped before every test with the whole database.
+NOTIFICATIONS = 'notification_queue'
+CERT_BUCKET = 'opc-certificates'
+PREDICTIONS_TABLE = 'predictions'
+
+
+def _resolve_markers(value: Any, servers: dict) -> Any:
+    """Replace ``@server:<name>`` with the URL of that in-process OPC server."""
+    if isinstance(value, dict):
+        return {k: _resolve_markers(v, servers) for k, v in value.items()}
+    if isinstance(value, list):
+        return [_resolve_markers(v, servers) for v in value]
+    if isinstance(value, str) and value.startswith('@server:'):
+        return servers[value.removeprefix('@server:')].url
+    return value
+
+
+def load_scenario_input(name: str, servers: dict | None = None, **overrides: Any) -> Any:
+    """
+    Load a JSON scenario input from ``e2e/scenario_inputs``.
+
+    Args:
+        name: File name (e.g. ``slot_single_server.json``).
+        servers: ``{name: OpcTestServer}`` used to resolve ``@server:<name>`` markers.
+        **overrides: Top-level keys replaced in the loaded dict.
+
+    Return:
+        Any: The resolved JSON content.
+    """
+    data = json.loads((SCENARIO_INPUTS_DIR / name).read_text(encoding='utf-8'))
+    data = _resolve_markers(data, servers or {})
+    if overrides:
+        data = {**data, **copy.deepcopy(overrides)}
+    return data
+
+
+async def wait_until(
+    predicate: Callable[[], Any | Awaitable[Any]], timeout: float = 15.0, interval: float = 0.1
+) -> Any:
+    """
+    Poll ``predicate`` (sync or async) until it returns a truthy value.
+
+    Sleeps on the event loop between attempts, so OPC subscription callbacks and NATS
+    handlers keep running while the test waits.
+
+    Raises:
+        AssertionError: When the predicate is still falsy after ``timeout`` seconds.
+    """
+    deadline = time.monotonic() + timeout
+    while True:
+        result = predicate()
+        if inspect.isawaitable(result):
+            result = await result
+        if result:
+            return result
+        if time.monotonic() > deadline:
+            raise AssertionError(f'condition not met within {timeout}s')
+        await asyncio.sleep(interval)
+
+
+async def stays_false(
+    predicate: Callable[[], Any | Awaitable[Any]], duration: float = 1.5, interval: float = 0.1
+) -> bool:
+    """True when ``predicate`` never becomes truthy during ``duration`` seconds."""
+    deadline = time.monotonic() + duration
+    while time.monotonic() < deadline:
+        result = predicate()
+        if inspect.isawaitable(result):
+            result = await result
+        if result:
+            return False
+        await asyncio.sleep(interval)
+    return True
+
+
+class Pod:
+    """
+    One gateway pod, wired exactly as ``ingestor/app.py`` does (minus the Prometheus
+    HTTP server and the sleep between iterations): ``Ingestor.prepare_ingestor``, then
+    ``GatewayRuntime`` on its data manager and connection pool. ``tick`` runs one main
+    loop iteration (``Ingestor.loop`` + ``GatewayRuntime.idle_sweep``).
+
+    Every component reads its settings from the environment at construction time, so
+    the caller sets the env (``HOSTNAME`` included) before ``start``.
+    """
+
+    def __init__(self, name: str, runtime: bool = True):
+        self.name = name
+        self.with_runtime = runtime
+        self.ingestor: Ingestor | None = None
+        self.runtime: GatewayRuntime | None = None
+
+    async def start(self) -> 'Pod':
+        os.environ['HOSTNAME'] = self.name
+        self.ingestor = Ingestor()
+        await self.ingestor.prepare_ingestor()
+        if self.with_runtime:
+            manager = self.ingestor.ingestor_manager
+            assert manager is not None
+            self.runtime = GatewayRuntime(
+                config=GatewayConfig.from_env(),
+                data_manager=manager.data_manager,
+                pool=manager.pool,
+                logger=self.ingestor.logger,
+                notification_handler=self.ingestor.notification_handler,
+                metrics_controller=self.ingestor.metrics_controller,
+                metadata=self.ingestor.metadata,
+            )
+            await self.runtime.start()
+            consumer = self.runtime.nats_consumer
+            if consumer.nc is not None:
+                # PING/PONG: the server has processed the SUB, so a command published
+                # right after start is not lost for lack of a subscriber.
+                await consumer.nc.flush()
+        return self
+
+    @property
+    def manager(self):
+        assert self.ingestor is not None and self.ingestor.ingestor_manager is not None
+        return self.ingestor.ingestor_manager
+
+    @property
+    def slots(self) -> set[str]:
+        """Slots this pod currently manages."""
+        return set(self.manager.managed_tags)
+
+    async def tick(self, times: int = 1) -> None:
+        assert self.ingestor is not None
+        for _ in range(times):
+            await self.ingestor.loop()
+            if self.runtime is not None:
+                await self.runtime.idle_sweep()
+
+    async def stop(self) -> None:
+        if self.runtime is not None:
+            await self.runtime.stop()
+            self.runtime = None
+        if self.ingestor is not None:
+            await self.ingestor.shutdown()
+            self.ingestor.notification_handler.shutdown()
+            self.ingestor = None
+
+
+def redis_json(redis_client, key: str) -> Any:
+    """Value stored by the gateway's RedisRepository (JSON-encoded), or None."""
+    raw = redis_client.get(key)
+    return None if raw is None else json.loads(raw)
+
+
+def readings(db: Database, collection: str, **query: Any) -> list[dict]:
+    """Documents the read path persisted into ``collection`` (oldest first)."""
+    return list(db[collection].find(query, {'_id': 0}).sort('inserted_at', 1))
+
+
+def notifications(db: Database, prefix: str = '') -> list[dict]:
+    """Notifications sent by the gateway whose ``notification_id`` starts with ``prefix``."""
+    return [
+        n
+        for n in db[NOTIFICATIONS].find({}, {'_id': 0})
+        if str(n.get('notification_id', '')).startswith(prefix)
+    ]
+
+
+def insert_prediction(engine: Engine, model_id: int, timestamp: str, write_status: str | None):
+    """One ``sientia_data.predictions`` row, as the Laborious inserts it before publishing C2."""
+    with engine.begin() as conn:
+        conn.execute(
+            text(
+                'INSERT INTO sientia_data.predictions (model_id, prediction, '
+                'prediction_confidence, response_time, prediction_status, "timestamp", '
+                'write_status) VALUES (:model_id, 1.5, 0.9, 0.1, :status, :ts, :write_status)'
+            ),
+            {
+                'model_id': model_id,
+                'status': 'success',
+                'ts': timestamp,
+                'write_status': write_status,
+            },
+        )
+
+
+def write_status(engine: Engine, model_id: int, timestamp: str) -> str | None:
+    """``write_status`` of a prediction row (``'<missing>'`` when the row does not exist)."""
+    with engine.begin() as conn:
+        row = conn.execute(
+            text(
+                'SELECT write_status FROM sientia_data.predictions '
+                'WHERE model_id = :model_id AND "timestamp" = :ts'
+            ),
+            {'model_id': model_id, 'ts': timestamp},
+        ).first()
+    return '<missing>' if row is None else row[0]
+
+
+def prediction_count(engine: Engine) -> int:
+    with engine.begin() as conn:
+        return conn.execute(text('SELECT count(*) FROM sientia_data.predictions')).scalar_one()
+
+
+# DataValue encoding mask bits (OPC UA Part 6, 5.2.2.17).
+STATUS_CODE_BIT = 0x02
+SOURCE_TIMESTAMP_BIT = 0x04
+
+
+def datavalue_mask(request: bytes, addr: str) -> int:
+    """
+    Encoding mask of the DataValue written to ``addr`` in a serialized WriteRequest.
+
+    An omitted StatusCode decodes as Good on the server (OPC UA default), so whether
+    the gateway sent the quality is only visible on the wire. WriteValue = NodeId,
+    AttributeId, IndexRange, DataValue: the byte right after the first three is the mask.
+    """
+    prefix = (
+        nodeid_to_binary(ua.NodeId.from_string(addr))
+        + Primitives.UInt32.pack(ua.AttributeIds.Value)
+        + Primitives.String.pack(None)
+    )
+    return request[request.index(prefix) + len(prefix)]

e2e/opc_server.py

@@ -0,0 +1,134 @@
+"""In-process OPC UA servers for the E2E suite (asyncua `Server`).
+
+Each `OpcTestServer` listens on its own localhost port and exposes string NodeIds
+under namespace 2 (`ns=2;s=<name>`), so a slot can address them the same way the
+Orchestrator addresses a real server. Writes received from the gateway are recorded
+(decoded `WriteValue`s) through the server's PreWrite callback.
+"""
+
+import socket
+import time
+from pathlib import Path
+
+from asyncua import Server, ua
+from asyncua.common.callback import CallbackType
+from asyncua.crypto.cert_gen import setup_self_signed_certificate
+from cryptography.x509.oid import ExtendedKeyUsageOID
+
+NAMESPACE_URI = 'urn:sientia:e2e'
+
+_VARIANT_TYPES = {
+    'float': ua.VariantType.Float,
+    'double': ua.VariantType.Double,
+    'int': ua.VariantType.Int32,
+    'bool': ua.VariantType.Boolean,
+    'string': ua.VariantType.String,
+}
+
+
+def free_port() -> int:
+    with socket.socket() as s:
+        s.bind(('127.0.0.1', 0))
+        return s.getsockname()[1]
+
+
+def address(name: str) -> str:
+    """NodeId string of a variable created by `OpcTestServer.add_variable`."""
+    return f'ns=2;s={name}'
+
+
+async def make_certificate(
+    folder: Path, name: str, app_uri: str, server: bool
+) -> tuple[Path, Path]:
+    """Self-signed application certificate (DER) + private key (PEM) with `app_uri` as
+    the SAN URI, as asyncua expects from both ends of a secure channel."""
+    folder.mkdir(parents=True, exist_ok=True)
+    cert, key = folder / f'{name}.der', folder / f'{name}.pem'
+    usage = ExtendedKeyUsageOID.SERVER_AUTH if server else ExtendedKeyUsageOID.CLIENT_AUTH
+    await setup_self_signed_certificate(
+        key, cert, app_uri, 'localhost', [usage], {'commonName': name}
+    )
+    return cert, key
+
+
+class OpcTestServer:
+    """One asyncua server. `secured=True` exposes only Basic256Sha256 SignAndEncrypt."""
+
+    def __init__(self, name: str, cert_dir: Path | None = None, secured: bool = False):
+        self.name = name
+        self.port = free_port()
+        self.secured = secured
+        self.cert_dir = cert_dir
+        self.server: Server | None = None
+        self.variables: dict[str, tuple[object, str, bool]] = {}
+        self.writes: list[ua.WriteValue] = []
+        self.write_times: list[float] = []  # time.monotonic() of each received write
+
+    @property
+    def url(self) -> str:
+        return f'opc.tcp://127.0.0.1:{self.port}'
+
+    def add_variable(
+        self, name: str, value: object, data_type: str = 'float', writable: bool = True
+    ) -> str:
+        """Declare a variable (created on `start`, and again on every restart)."""
+        self.variables[name] = (value, data_type, writable)
+        return address(name)
+
+    async def start(self) -> None:
+        server = Server()
+        await server.init()
+        server.set_endpoint(self.url)
+        server.set_server_name(self.name)
+        if self.secured:
+            assert self.cert_dir is not None, 'a secured server needs a cert_dir'
+            cert, key = await make_certificate(
+                self.cert_dir, f'server-{self.name}', f'urn:sientia:e2e:{self.name}', True
+            )
+            await server.load_certificate(str(cert))
+            await server.load_private_key(str(key))
+            server.set_security_policy([ua.SecurityPolicyType.Basic256Sha256_SignAndEncrypt])
+        idx = await server.register_namespace(NAMESPACE_URI)
+        assert idx == 2, f'unexpected namespace index {idx}'
+        for name, (value, data_type, writable) in self.variables.items():
+            node = await server.nodes.objects.add_variable(
+                address(name), name, value, _VARIANT_TYPES[data_type]
+            )
+            if writable:
+                await node.set_writable()
+        server.subscribe_server_callback(CallbackType.PreWrite, self._record_write)
+        await server.start()
+        self.server = server
+
+    async def stop(self) -> None:
+        if self.server is not None:
+            await self.server.stop()
+            self.server = None
+
+    async def restart(self) -> None:
+        """Stop and start again on the same port (values reset to their initial ones)."""
+        await self.stop()
+        await self.start()
+
+    async def set(self, name: str, value: object) -> None:
+        """Change a value server-side (raises a data change for subscribed clients)."""
+        assert self.server is not None
+        _, data_type, _ = self.variables[name]
+        node = self.server.get_node(address(name))
+        await node.write_value(ua.Variant(value, _VARIANT_TYPES[data_type]))
+
+    async def read(self, name: str) -> ua.DataValue:
+        assert self.server is not None
+        return await self.server.get_node(address(name)).read_data_value()
+
+    def session_count(self) -> int:
+        """Client sessions currently open on this server."""
+        assert self.server is not None
+        return len(self.server.iserver._external_sessions)
+
+    async def _record_write(self, event, _dispatcher) -> None:
+        if not event.is_external:  # the server updates its own nodes (ServerStatus, ...)
+            return
+        for value in event.request_params.NodesToWrite:
+            self.writes.append(value)
+            self.write_times.append(time.monotonic())

e2e/scenario_inputs/connector_plant_a.json

@@ -0,0 +1,10 @@
+{
+  "connector_id": "1",
+  "type": "opc_ua",
+  "name": "plant-a",
+  "url": "@server:plant-a",
+  "status": "Active",
+  "subscription_period_ms": 100,
+  "security": {"mode": "None", "policy": "None", "client_certificate_id": null},
+  "legacy_opc_server_id": "1"
+}

e2e/scenario_inputs/slot_active_read.json

@@ -0,0 +1,25 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "server_id": "1",
+    "url": "@server:plant-a",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Level": {
+        "frequency": 1000,
+        "active_read": {"enabled": true, "cycle_multiple": 1},
+        "names": [
+          {"collection": "active_tank", "tag_name": "tank_level", "model_id": "30"},
+          {"collection": "active_mixer", "tag_name": "mixer_inlet_level", "model_id": "40"}
+        ]
+      },
+      "ns=2;s=Temperature": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [{"collection": "active_tank", "tag_name": "tank_temperature", "model_id": "30"}]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_data_types.json

@@ -0,0 +1,28 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "server_id": "1",
+    "url": "@server:plant-a",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Temperature": {
+        "frequency": 1000,
+        "names": [{"collection": "raw_types", "tag_name": "temperature", "model_id": "10"}]
+      },
+      "ns=2;s=Counter": {
+        "frequency": 1000,
+        "names": [{"collection": "raw_types", "tag_name": "counter", "model_id": "10"}]
+      },
+      "ns=2;s=Running": {
+        "frequency": 1000,
+        "names": [{"collection": "raw_types", "tag_name": "running", "model_id": "10"}]
+      },
+      "ns=2;s=Batch": {
+        "frequency": 1000,
+        "names": [{"collection": "raw_types", "tag_name": "batch", "model_id": "10"}]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_multi_name.json

@@ -0,0 +1,20 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "server_id": "1",
+    "url": "@server:plant-a",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Pressure": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [
+          {"collection": "raw_furnace", "tag_name": "furnace_pressure", "model_id": "10", "model_name": "furnace"},
+          {"collection": "raw_boiler", "tag_name": "boiler_inlet_pressure", "model_id": "20", "model_name": "boiler"}
+        ]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_secured.json

@@ -0,0 +1,19 @@
+{
+  "plant-s": {
+    "name": "plant-s",
+    "server_id": "7",
+    "url": "@server:plant-s",
+    "subscription_period_ms": 100,
+    "security": {"mode": "SignAndEncrypt", "policy": "Basic256Sha256"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Temperature": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [
+          {"collection": "raw_secured", "tag_name": "secured_temperature", "model_id": "70"}
+        ]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_single_server.json

@@ -0,0 +1,19 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "server_id": "1",
+    "url": "@server:plant-a",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Temperature": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [
+          {"collection": "raw_plant_a", "tag_name": "temperature", "model_id": "10", "model_name": "furnace"}
+        ]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_two_servers.json

@@ -0,0 +1,36 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "server_id": "1",
+    "url": "@server:plant-a",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Temperature": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [
+          {"collection": "raw_plant_a", "tag_name": "temperature", "model_id": "10", "model_name": "furnace"}
+        ]
+      }
+    }
+  },
+  "plant-b": {
+    "name": "plant-b",
+    "server_id": "2",
+    "url": "@server:plant-b",
+    "subscription_period_ms": 100,
+    "security": {"mode": "None", "policy": "None"},
+    "certificate": null,
+    "tags": {
+      "ns=2;s=Flow": {
+        "frequency": 1000,
+        "active_read": {"enabled": false},
+        "names": [
+          {"collection": "raw_plant_b", "tag_name": "flow", "model_id": "20", "model_name": "boiler"}
+        ]
+      }
+    }
+  }
+}

e2e/scenario_inputs/slot_v1_invalid.json

@@ -0,0 +1,10 @@
+{
+  "plant-a": {
+    "name": "plant-a",
+    "url": "@server:plant-a",
+    "server_uri": "http://opcua-server.simulator",
+    "tags": {
+      "ns=2;s=Temperature": {"tag_name": "Temperature", "frequency": 1000, "topics": ["raw_plant_a"]}
+    }
+  }
+}

e2e/scenario_inputs/write_command.json

@@ -0,0 +1,12 @@
+{
+  "server_id": "1",
+  "addr": "ns=2;s=Setpoint",
+  "value": 1.25,
+  "data_type": "float",
+  "tag_type": "prediction",
+  "model_id": "2",
+  "model_name": "sin-approx",
+  "schema": "sientia_data",
+  "table_name": "predictions",
+  "timestamp": "2026-10-13T12:00:00-03:00"
+}

e2e/scenarios.md

@@ -0,0 +1,584 @@
+# E2E Scenario Documentation — OPC Gateway
+
+Functional reference for the gateway end-to-end scenarios: slot leasing, subscription reads,
+NATS writes, gRPC reads, active reads, certificates and the pod lifecycle. Tests live under
+`e2e/`, are marked with `@pytest.mark.integration` and run with:
+
+```bash
+pytest e2e/ -o testpaths=e2e -m integration
+```
+
+**Every section below maps 1:1 to an actual test function** (or to one `pytest.param` id of a
+parametrized test) — this file describes what the suite verifies today. Adding a scenario here
+without a matching test (or vice versa) is a doc bug; fix the mismatch instead of leaving it
+for later.
+
+## Execution Context
+
+### One-time setup: disable the testcontainers reaper
+
+Same as the Laborious and Orchestrator suites. Once per machine:
+
+```bash
+echo "ryuk.disabled=true" >> ~/.testcontainers.properties
+```
+
+Under Docker Desktop on Linux the reaper ("Ryuk") cannot mount the Docker socket and every
+test errors at setup (`ERROR`, not `FAILED`). Every fixture stops its own containers in
+teardown; after a killed run, clean up by hand:
+
+```bash
+docker ps -a --filter "label=org.testcontainers=true" -q | xargs -r docker rm -f
+```
+
+### What runs for real
+
+| Dependency | How | Scope |
+|---|---|---|
+| MongoDB (`mongo:7`, user/password) | testcontainers | session |
+| Redis (`redis:7-alpine`) | testcontainers | session |
+| PostgreSQL (`postgres:15`, `e2e/db_schema.sql`) | testcontainers | session |
+| MinIO (`bitnamilegacy/minio`, client certificates) | testcontainers | session |
+| NATS (`nats:2.10-alpine`) | testcontainers | session |
+| OPC UA servers | in process (`e2e/opc_server.py`, asyncua `Server`) | per test |
+
+- Gateway code under `ingestor/**` is not mocked. A pod (`e2e/helpers.Pod`) is built from the
+  environment exactly like `ingestor/app.py` builds it — `Ingestor.prepare_ingestor`, then
+  `GatewayRuntime` on the same data manager and connection pool — minus the Prometheus HTTP
+  server. `Pod.tick()` runs one main loop iteration (`Ingestor.loop` + `GatewayRuntime.idle_sweep`)
+  without the `POLL_INTERVAL` sleep, so every scenario controls exactly how many iterations run.
+- The environment (`gateway_env` in `e2e/conftest.py`) points every setting at the containers;
+  scenarios override single variables per pod (`LEASE_TTL`, `WRITE_TIMESTAMP`, ...).
+- State is reset before every test: Redis `FLUSHDB`, Mongo database dropped, Postgres schema
+  recreated from `e2e/db_schema.sql`, certificate bucket emptied.
+- Inputs live in `e2e/scenario_inputs/*.json` and are loaded with `load_scenario_input`;
+  `@server:<name>` markers resolve to the URL of that test's in-process OPC server.
+- Default `POLL_INTERVAL=1` and tag `frequency=1000`: one OPC "cycle" per loop iteration.
+- Not covered by the default `pytest` run (`testpaths = ["tests"]`) nor by the unit coverage.
+  `--strict-markers` is on: a test without `@pytest.mark.integration` is not collected, and a run
+  that collects nothing still exits 0 — check the collected count.
+
+---
+
+## 1. Slot Leasing and Load Balancing
+Source: `e2e/test_slot_leasing.py`
+
+### 1.1.1 Single Pod Leases the Slot and Heartbeats
+**Summary**: A lone pod takes the only slot on its first loop iteration.
+
+**Description**:
+- Slot 1 reads `plant-a`; one pod starts and runs one iteration.
+
+**Expected Outcome**:
+- The pod manages slot `1`; `lease:opc_tags:1 = "pod-a"` with TTL ≤ `LEASE_TTL` (10 s).
+- `heartbeat:ingestor:pod-a = 1` with TTL ≤ `HEARTBEAT_TTL` (20 s).
+- Readings of the slot reach MongoDB.
+
+### 1.1.2 Idle Pod Takes a Slot Created After Startup
+**Summary**: A pod without slots picks up a slot the Orchestrator creates later.
+
+**Description**:
+- The pod starts with Redis empty and runs one iteration (nothing to lease).
+- Slot 1 is written; the pod runs another iteration.
+
+**Expected Outcome**:
+- The pod manages slot `1`, holds its lease and its readings reach MongoDB.
+
+### 1.2.1 Two Pods Split Two Slots
+**Summary**: The rebalancing hands one slot to each pod.
+
+**Description**:
+- Slot 1 reads `plant-a`, slot 2 reads `plant-b`. `pod-a` starts alone, then `pod-b` starts.
+- Iterations: `pod-a`, `pod-b`, `pod-a`, `pod-b`.
+
+**Expected Outcome**:
+- Alone, `pod-a` takes both slots; `pod-b` finds them leased.
+- `pod-a` sees a pod without slots and gives slot `2` back (unsubscribing first); `pod-b` takes it.
+- Leases: slot 1 → `pod-a`, slot 2 → `pod-b`; each pod only has the reader of its own server.
+- New values of both servers reach MongoDB.
+
+### 1.2.2 Extra Pod Stays Idle
+**Summary**: With more pods than slots, no slot is read twice.
+
+**Description**:
+- Two slots balanced between `pod-a` and `pod-b`; `pod-c` joins and every pod iterates twice.
+
+**Expected Outcome**:
+- `pod-c` manages nothing; `pod-a` and `pod-b` hold disjoint slots covering `{1, 2}`.
+- Leases belong to `pod-a` and `pod-b` only.
+
+### 1.2.3 Failover After Lease Expiry
+**Summary**: A slot left by a dead pod is taken over once its lease expires.
+
+**Description**:
+- `pod-a` (`LEASE_TTL=2`) reads slot 1; `pod-b` runs idle.
+- `pod-a` stops without releasing the lease (crash-like).
+
+**Expected Outcome**:
+- The lease still names `pod-a` right after the stop, then expires.
+- On its next iteration `pod-b` leases slot `1` and new values reach MongoDB.
+
+### 1.3.1 Deleted Slot Stops the Reads
+**Summary**: Removing a slot from Redis unsubscribes it.
+
+**Description**:
+- A pod reads slot 1; the slot key is deleted; the pod iterates.
+
+**Expected Outcome**:
+- The pod manages no slot and has no OPC reader.
+- A value changed afterwards is not persisted.
+
+### 1.3.2 Invalid Slot Is Notified and Not Read
+**Summary**: A slot v1 (`topics`, no `security`/`names`) is rejected.
+
+**Description**:
+- Slot 1 holds the legacy v1 shape (`slot_v1_invalid.json`).
+
+**Expected Outcome**:
+- Notification `OPC_SLOT_CONFIG_ERROR_1` in `notification_queue`.
+- The pod manages nothing; no reading is persisted.
+
+### 1.3.3 Fixed Slot Is Read Once Its Lease Expires
+**Summary**: Fixing an invalid slot takes effect after the lease of the failed acquisition expires.
+
+**Description**:
+- `pod-a` (`LEASE_TTL=2`) leases the invalid slot 1 (the lease is kept, the slot is not managed).
+- The slot is fixed; the pod iterates before and after the lease expires.
+
+**Expected Outcome**:
+- Before expiry the pod still manages nothing (its own lease blocks the re-acquisition).
+- After expiry the pod manages slot `1` and its readings reach MongoDB.
+
+---
+
+## 2. Subscription Reads (OPC UA → MongoDB)
+Source: `e2e/test_subscription_reads.py`
+
+### 2.1.1 Value Change Is Persisted
+**Summary**: Each data change becomes one document in the name's collection.
+
+**Description**:
+- Slot 1 subscribes `ns=2;s=Temperature` of `plant-a` into `raw_plant_a`; the value changes.
+
+**Expected Outcome**:
+- The initial value and the new one are persisted.
+- Document fields: `tag` (address), `name` (`tag_name`), `model_id`, `value`, `timestamp`
+  (source timestamp, `YYYY-MM-DD HH:MM:SS-0300`) and `inserted_at` — nothing else.
+
+### 2.1.2 One Address Fans Out to Every Name
+**Summary**: An address with several `names` is written to each collection.
+
+**Description**:
+- `ns=2;s=Pressure` has two names: `raw_furnace`/`furnace_pressure`/model 10 and
+  `raw_boiler`/`boiler_inlet_pressure`/model 20 (`slot_multi_name.json`).
+
+**Expected Outcome**:
+- One document per collection for the change, each with its own `name`/`model_id`, the same
+  `tag` and the same `timestamp`.
+
+### 2.1.3 Two Servers in One Slot
+**Summary**: A slot can hold several OPC servers.
+
+**Description**:
+- Slot 1 holds `plant-a` and `plant-b` (`slot_two_servers.json`); both values change.
+
+**Expected Outcome**:
+- Both changes are persisted; the pod has one reader per server.
+
+### 2.1.4 Values Keep Their OPC Type
+**Summary**: Double, Int32, Boolean and String values are stored with their native type.
+
+**Description**:
+- Four tags of different OPC types change value (`slot_data_types.json`).
+
+**Expected Outcome**:
+- Each document stores the value with the matching Python/BSON type (`float`, `int`, `bool`, `str`).
+
+### 2.2.1 Tag Added to the Slot Is Subscribed
+**Summary**: A new tag in the slot is subscribed on the next iteration.
+
+**Description**:
+- The Orchestrator adds `ns=2;s=Level` to slot 1; the pod iterates.
+
+**Expected Outcome**:
+- Changes of the new tag and of the existing one are persisted.
+
+### 2.2.2 Tag Removed from the Slot Is No Longer Read
+**Summary**: A tag removed from the slot stops being persisted.
+
+**Description**:
+- Slot 1 reads `Temperature` and `Level`; `Level` is removed; the pod iterates.
+
+**Expected Outcome**:
+- `Temperature` keeps being persisted; a new `Level` value is not.
+
+### 2.2.3 Name Added to a Tag Receives Its Readings
+**Summary**: A new name on an existing tag starts receiving the readings.
+
+**Description**:
+- A second name (`raw_dryer`/`dryer_temperature`/model 50) is added to `Temperature`.
+
+**Expected Outcome**:
+- The next change is persisted in both collections.
+
+### 2.2.4 Server URL Change Reconnects to the New Server
+**Summary**: Changing the connection settings of a server re-initializes its reader.
+
+**Description**:
+- Slot 1 points `plant-a` to a second server (same tags) and the pod iterates.
+
+**Expected Outcome**:
+- Values of the new server are persisted; the session on the old server is closed.
+- Changes on the old server are no longer persisted.
+
+### 2.3.1 Unreachable Server Does Not Stop the Others
+**Summary**: A server that cannot be reached is dropped; the other servers of the slot keep reading.
+
+**Description**:
+- Slot 1 holds `plant-a` and `plant-b`, whose URL has nothing listening.
+
+**Expected Outcome**:
+- Notification `OPC_CONNECTION_ERROR_plant-b`; the pod only has the `plant-a` reader.
+- `plant-a` values are persisted.
+
+### 2.3.2 Tag Without Data Raises a Warning
+**Summary**: A tag without data changes for 5 cycles is notified.
+
+**Description**:
+- The value does not change for 5 iterations.
+
+**Expected Outcome**:
+- One WARNING notification `TAG_ns=2;s=Temperature:temperature_LISTENNING_STOPPED`.
+
+### 2.3.3 Silent Server Is Reconnected After 15 Cycles
+**Summary**: A server without any data change for 15 cycles is treated as silently dead.
+
+**Description**:
+- The value does not change for 15 iterations, then the pod iterates once more.
+
+**Expected Outcome**:
+- Notifications `OPC_LISTENNING_STOPPED__1` and `OPC_CONNECTION_RETRY__1`; the reader is dropped
+  (pool connection evicted).
+- The next iteration re-initializes the reader with a new connection; changes are persisted again.
+
+### 2.3.4 Server Restart Resumes the Reads
+**Summary**: A server that goes down and comes back is read again.
+
+**Description**:
+- The server stops; the pod iterates 15 times (reader dropped) and once more while it is down;
+  the server starts again on the same port; the pod iterates twice.
+
+**Expected Outcome**:
+- While down, the reconnection fails with notification `OPC_CONNECTION_ERROR_plant-a`.
+- Once back, the reader is re-initialized and changes are persisted again.
+
+---
+
+## 3. Writes (NATS C2 → OPC UA → Postgres `write_status` C3)
+Source: `e2e/test_writes.py`
+
+Common setup: `plant-a` with a writable `Setpoint`, its connector in `connectors`
+(`connector_plant_a.json`, `connector_id "1"`) and a `pending` row in `sientia_data.predictions`
+(model 2, `2026-10-13T12:00:00-03:00`). Commands come from `write_command.json` and are published
+on `opc.write`; the gateway answers through the row's `write_status`.
+
+### 3.1 DataValue Parts: Timestamp and Quality (SIENTIAPDE-2202)
+**Summary**: The value is always written; the prediction timestamp (`SourceTimestamp`) and a Good
+`StatusCode` are written unless turned off. Each flag comes from the command, else from the env
+(`WRITE_TIMESTAMP` / `WRITE_QUALITY`), else `true`.
+
+**Description**:
+- `test_scenario_3_1_datavalue_parts`, one case per id. The timestamp is checked on the value the
+  server stored; the quality on the DataValue encoding mask of the WriteRequest the gateway sent
+  (an omitted StatusCode decodes as Good on the server, so only the wire tells them apart).
+
+| Id | Env | Command flags | SourceTimestamp | StatusCode |
+|---|---|---|---|---|
+| `3_1_1_defaults_on` | — | — | sent | sent |
+| `3_1_2_timestamp_off` | `WRITE_TIMESTAMP=false` | — | not sent | sent |
+| `3_1_3_quality_off` | `WRITE_QUALITY=false` | — | sent | not sent |
+| `3_1_4_both_off` | both `false` | — | not sent | not sent |
+| `3_1_5_command_overrides_env` | `WRITE_TIMESTAMP=true` | `write_timestamp: false` | not sent | sent |
+| `3_1_6_command_turns_on_over_env` | both `false` | both `true` | sent | sent |
+
+**Expected Outcome**:
+- `write_status = ok`; the server holds `1.25`.
+- When sent, the stored `SourceTimestamp` equals the command `timestamp`; otherwise it is empty.
+
+### 3.2.1 Pending Row Becomes Ok
+**Summary**: A successful write records `ok`.
+
+**Expected Outcome**:
+- `write_status = ok`; the server holds the command value.
+
+### 3.2.2 Null write_status Becomes Ok
+**Summary**: Rows without a status (inserted before the column existed) are updated too.
+
+**Expected Outcome**:
+- `write_status` goes from NULL to `ok`.
+
+### 3.2.3 Worse Outcome Is Kept
+**Summary**: `ok` never replaces a worse outcome (`ok` < `error` < `session_bad`).
+
+**Description**:
+- Parametrized: the row starts as `error` or `session_bad`; a successful command arrives.
+
+**Expected Outcome**:
+- The OPC write happens, the row keeps its worse status.
+
+### 3.2.4 Failure Replaces Ok
+**Summary**: A worse outcome replaces a better one.
+
+**Description**:
+- A successful command records `ok`; a second command for the same row fails (conversion).
+
+**Expected Outcome**:
+- `write_status = error`.
+
+### 3.2.5 Missing Row Is Not Created
+**Summary**: The gateway only updates rows; it never inserts one.
+
+**Description**:
+- The command targets model 3, which has no prediction row.
+
+**Expected Outcome**:
+- The OPC write happens; no row for model 3 exists afterwards.
+
+### 3.3.1 Unknown Server Is an Error
+**Summary**: A `server_id` with no live connection and no connector fails the write.
+
+**Expected Outcome**:
+- `write_status = error`; nothing is written to the server.
+
+### 3.3.2 Unusable Connector Is an Error
+**Summary**: Only active `opc_ua` connectors with a URL and full security are used.
+
+**Description**:
+- Parametrized: connector `inactive`, `not_opc_ua` (`type: modbus`), `no_policy`, `no_url`.
+
+**Expected Outcome**:
+- `write_status = error`; nothing is written to the server.
+
+### 3.3.3 Invalid Command Is an Error Without OPC Write
+**Summary**: Commands that cannot become a DataValue are rejected before touching the server.
+
+**Description**:
+- Parametrized: `conversion` (`"abc"` as `int`), `unknown_data_type` (`decimal128`), `missing_addr`.
+
+**Expected Outcome**:
+- `write_status = error`; nothing is written to the server.
+
+### 3.3.4 Bad Timestamp Skips the Write and Keeps the Row
+**Summary**: A non-ISO `timestamp` (with the timestamp flag on) fails before the OPC write.
+
+**Description**:
+- The command carries `13/10/2026 12:00`; a marker command is used to know it was handled.
+
+**Expected Outcome**:
+- Only the marker reaches the server; the row stays `pending` — the status cannot be recorded
+  either, since the row is found by that same timestamp.
+
+### 3.3.5 OPC Rejection Is an Error
+**Summary**: A write the server refuses is recorded as `error`.
+
+**Description**:
+- Parametrized: `not_writable` (read-only `Locked`), `unknown_node` (`ns=2;s=Missing`).
+
+**Expected Outcome**:
+- `write_status = error`; `Locked` keeps its value.
+
+### 3.3.6 Malformed JSON Is Dropped and the Consumer Keeps Going
+**Summary**: A payload that is not JSON is discarded without stopping the consumer.
+
+**Expected Outcome**:
+- The next valid command is written and recorded as `ok`.
+
+### 3.4.1 Write Reuses the Read Connection
+**Summary**: A server read by the pod is written through the same pooled connection.
+
+**Description**:
+- `plant-a` is only known through slot 1 (no connector in Mongo).
+
+**Expected Outcome**:
+- `write_status = ok`; the server has a single session.
+
+### 3.4.2 Write-Only Server Gets Its Own Connection
+**Summary**: A server only known as a connector is connected on the first write.
+
+**Expected Outcome**:
+- No session before the command; one session after; the pool holds the connector's settings.
+
+### 3.5.1 Minimum Pause Between Writes
+**Summary**: `WRITE_MIN_PAUSE_S` spaces consecutive writes.
+
+**Description**:
+- `WRITE_MIN_PAUSE_S=0.5`; three commands are published back to back.
+
+**Expected Outcome**:
+- The server receives the three writes at least ~0.5 s apart.
+
+### 3.5.2 Queue Group Writes Each Command Once
+**Summary**: Pods share the `gateway-writers` queue: each command is handled by a single pod.
+
+**Description**:
+- Two pods with the runtime; six commands.
+
+**Expected Outcome**:
+- The server receives exactly six writes.
+
+### 3.6.1 NATS Down at Startup Connects Later
+**Summary**: The runtime starts without NATS and connects from the main loop once NATS is up.
+
+**Description**:
+- `NATS_URL` points to a port with nothing listening; the pod starts and iterates once.
+- A NATS server starts on that port; the pod iterates again.
+
+**Expected Outcome**:
+- One `GATEWAY_NATS_CONSUMER_START_FAILED` notification for the whole outage (not one per retry).
+- After NATS starts, the consumer connects and a published command is recorded as `ok`.
+
+---
+
+## 4. On-demand gRPC ReadTag
+Source: `e2e/test_grpc_read_tag.py`
+
+Common setup: `GRPC_ENABLED=true`; slot 1 reads `plant-a`, so the pod's pool holds a connection.
+
+### 4.1.1 Reads a Tag of a Connected Server
+**Expected Outcome**:
+- `value` (as text), `opc_status_code = Good`, `source_timestamp` / `server_timestamp` in
+  `YYYY-MM-DD HH:MM:SS-0300`.
+- `persisted = false` and no collection is created: the slot lookup of `ReadTag` is not wired yet.
+
+### 4.1.2 Reads the Current Value
+**Expected Outcome**:
+- After a server-side change, `ReadTag` returns the new value.
+
+### 4.2.1 Unknown Address Is an Internal Error
+**Expected Outcome**:
+- gRPC `INTERNAL` whose details carry `BadNodeIdUnknown`.
+
+### 4.2.2 Server Not Connected by the Reads Is an Internal Error
+**Summary**: `ReadTag` has no connection settings of its own: it only reads servers the read path
+already connected (documents the current limitation).
+
+**Description**:
+- `plant-a` only exists as a connector; no slot.
+
+**Expected Outcome**:
+- gRPC `INTERNAL`; no session is opened on the server.
+
+### 4.2.3 gRPC Disabled by Default
+**Expected Outcome**:
+- Without `GRPC_ENABLED`, nothing listens on `GRPC_PORT` (`UNAVAILABLE`/`DEADLINE_EXCEEDED`).
+
+---
+
+## 5. Scheduled Active Reads
+Source: `e2e/test_active_read.py`
+
+`GatewayRuntime` builds `ActiveReadEngine` on the pod's pool and sink, but no loop calls
+`scheduled_tick` yet; these scenarios call it on the running pod's engine with the parsed slot
+(`slot_active_read.json`).
+
+### 5.1.1 Enabled Tag Is Read into Every Name
+**Expected Outcome**:
+- `Level` (`active_read.enabled`) is persisted in `active_tank` (model 30) and `active_mixer`
+  (model 40); `Temperature` (disabled) is not read.
+
+### 5.1.2 cycle_multiple Reads Every Nth Tick
+**Description**:
+- `cycle_multiple = 3`; six ticks.
+
+**Expected Outcome**:
+- Persisted documents after each tick: `0, 0, 1, 1, 1, 2`.
+
+### 5.2.1 Unreachable Server Does Not Stop the Tick
+**Expected Outcome**:
+- The tick does not raise; the unreachable server's tag is not persisted, the other server's is.
+
+### 5.2.2 Active Read Uses the Slot Connection Settings
+**Expected Outcome**:
+- The first tick opens the connection with the slot settings; later ticks reuse it (one session);
+  each tick persists the current value.
+
+---
+
+## 6. Client Certificates and OPC Security
+Source: `e2e/test_certificates.py`
+
+Common setup: `plant-s` exposes only Basic256Sha256 SignAndEncrypt. Client certificates are created
+like the platform stores them: cert (DER) and key (PEM) in MinIO bucket `opc-certificates`, plus an
+`opc_certificates` document (`kind: client`).
+
+### 6.1.1 Secured Read with Certificate from MinIO
+**Expected Outcome**:
+- Readings are persisted; the certificate is cached as `<CERT_CACHE_DIR>/7/cert.der` and `key.pem`.
+- No connection error is notified.
+
+### 6.1.2 Secured Write Resolved from Connectors and Certificates
+**Description**:
+- No slot: the connector (`client_certificate_id: 7`) is joined with `opc_certificates`.
+
+**Expected Outcome**:
+- `write_status = ok`; the server holds the value.
+
+### 6.2.1 Certificate Missing in MinIO
+**Expected Outcome**:
+- Notification `OPC_CONNECTION_ERROR_plant-s`; no reader; nothing cached; no readings.
+
+### 6.2.2 Unsupported Security Policy
+**Expected Outcome**:
+- Notification `OPC_CONNECTION_ERROR_plant-s` whose message names the unsupported mode/policy.
+
+### 6.2.3 No Certificate Cannot Reach a Secured-only Server
+**Description**:
+- The slot has `certificate: null` (connect without security, D5).
+
+**Expected Outcome**:
+- Notification `OPC_CONNECTION_ERROR_plant-s`; no readings.
+
+### 6.2.4 Inactive Certificate Write Fails
+**Description**:
+- The connector's certificate is `revoked`: the write connects without security.
+
+**Expected Outcome**:
+- `write_status = error`; nothing is written to the server.
+
+### 6.3.1 Certificate Rotation Reconnects with the New One
+**Description**:
+- Slot 1 switches from certificate 7 to certificate 8; the pod iterates.
+
+**Expected Outcome**:
+- The pooled connection is replaced and opened with certificate 8 (cached under `8/`).
+- Readings continue; the server ends with a single session.
+
+---
+
+## 7. Pod Lifecycle
+Source: `e2e/test_lifecycle.py`
+
+### 7.1.1 Shutdown Closes Sessions and Stops Consuming
+**Expected Outcome**:
+- After `GatewayRuntime.stop` + `Ingestor.shutdown`, the OPC server has no session.
+- A command published afterwards is not handled (row stays `pending`); value changes are not persisted.
+
+### 7.1.2 Idle Write Connection Is Closed and Reopened
+**Description**:
+- `IDLE_CONN_MAX_S=1`; `plant-a` is read (slot), `plant-b` only written (connector `2`).
+
+**Expected Outcome**:
+- After the idle time, `idle_sweep` closes the `plant-b` session; the subscribed `plant-a`
+  connection is pinned and stays open.
+- The next write to `plant-b` reconnects and is recorded as `ok`.
+
+### 7.2.1 Redis Unreachable Fails the Startup
+**Expected Outcome**:
+- `prepare_ingestor` raises a connection error (`app.py` then stops the process).
+
+### 7.2.2 Restarted Pod Takes Its Slot Back
+**Description**:
+- `pod-a` (`LEASE_TTL=2`) stops; a new `pod-a` starts after the lease expired.
+
+**Expected Outcome**:
+- The restarted pod leases slot `1` and its readings reach MongoDB.

e2e/test_active_read.py

@@ -0,0 +1,84 @@
+"""E2E scenarios — 5. Scheduled active reads. See ``e2e/scenarios.md``.
+
+``GatewayRuntime`` builds the ``ActiveReadEngine`` with the pod's pool and sink, but no
+loop calls ``scheduled_tick`` yet (its wiring is pending in ``gateway_runtime.py``), so
+these scenarios call it on the running pod's engine with the parsed slot.
+"""
+
+import pytest
+
+from e2e.helpers import load_scenario_input, readings, stays_false, wait_until
+from e2e.opc_server import free_port
+from ingestor.io.slots import parse_slot
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+
+async def test_scenario_5_1_1_enabled_tag_is_read_into_every_name(opc_servers, pods, mongo_db):
+    server = await opc_servers('plant-a', {'Level': 2.5, 'Temperature': 20.0})
+    slot = parse_slot(load_scenario_input('slot_active_read.json', {'plant-a': server}))
+    pod = await pods('pod-a')
+
+    await pod.runtime.active_read.scheduled_tick(slot)
+
+    [tank] = readings(mongo_db, 'active_tank', name='tank_level')
+    [mixer] = readings(mongo_db, 'active_mixer', name='mixer_inlet_level')
+    assert tank['value'] == mixer['value'] == 2.5
+    assert (tank['model_id'], mixer['model_id']) == ('30', '40')
+    assert tank['tag'] == 'ns=2;s=Level'
+    assert readings(mongo_db, 'active_tank', name='tank_temperature') == []  # not enabled
+
+
+async def test_scenario_5_1_2_cycle_multiple_reads_every_nth_tick(opc_servers, pods, mongo_db):
+    server = await opc_servers('plant-a', {'Level': 2.5, 'Temperature': 20.0})
+    raw = load_scenario_input('slot_active_read.json', {'plant-a': server})
+    raw['plant-a']['tags']['ns=2;s=Level']['active_read']['cycle_multiple'] = 3
+    slot = parse_slot(raw)
+    pod = await pods('pod-a')
+
+    counts = []
+    for _ in range(6):
+        await pod.runtime.active_read.scheduled_tick(slot)
+        counts.append(len(readings(mongo_db, 'active_tank', name='tank_level')))
+
+    assert counts == [0, 0, 1, 1, 1, 2]
+
+
+async def test_scenario_5_2_1_unreachable_server_does_not_stop_the_tick(
+    opc_servers, pods, mongo_db
+):
+    server = await opc_servers('plant-a', {'Level': 2.5, 'Temperature': 20.0})
+    raw = load_scenario_input('slot_active_read.json', {'plant-a': server})
+    down = {**raw['plant-a'], 'name': 'plant-down', 'server_id': '9'}
+    down['url'] = f'opc.tcp://127.0.0.1:{free_port()}'
+    down['tags'] = {
+        'ns=2;s=Level': {
+            **raw['plant-a']['tags']['ns=2;s=Level'],
+            'names': [{'collection': 'active_down', 'tag_name': 'down_level', 'model_id': '90'}],
+        }
+    }
+    slot = parse_slot({'plant-down': down, 'plant-a': raw['plant-a']})
+    pod = await pods('pod-a')
+
+    await pod.runtime.active_read.scheduled_tick(slot)  # does not raise
+
+    assert readings(mongo_db, 'active_down') == []
+    await wait_until(lambda: readings(mongo_db, 'active_tank', name='tank_level'))
+
+
+async def test_scenario_5_2_2_active_read_uses_the_slot_connection_settings(
+    opc_servers, pods, mongo_db
+):
+    server = await opc_servers('plant-a', {'Level': 2.5, 'Temperature': 20.0})
+    slot = parse_slot(load_scenario_input('slot_active_read.json', {'plant-a': server}))
+    pod = await pods('pod-a')
+    assert pod.manager.pool.config_for('1') is None
+
+    await pod.runtime.active_read.scheduled_tick(slot)
+
+    assert pod.manager.pool.config_for('1')['url'] == server.url
+    assert server.session_count() == 1
+    await server.set('Level', 3.0)
+    await pod.runtime.active_read.scheduled_tick(slot)
+    assert await stays_false(lambda: server.session_count() != 1, duration=0.5)
+    assert [d['value'] for d in readings(mongo_db, 'active_tank', name='tank_level')] == [2.5, 3.0]

e2e/test_certificates.py

@@ -0,0 +1,165 @@
+"""E2E scenarios — 6. Client certificates and OPC security (MinIO + opc_certificates). See ``e2e/scenarios.md``."""
+
+import pytest
+import pytest_asyncio
+
+from e2e.helpers import (
+    insert_prediction,
+    load_scenario_input,
+    notifications,
+    readings,
+    stays_false,
+    wait_until,
+    write_status,
+)
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+TIMESTAMP = '2026-10-13T12:00:00-03:00'
+SECURED = {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'}
+
+
+@pytest_asyncio.fixture
+async def secured_server(opc_servers):
+    """plant-s: only Basic256Sha256 SignAndEncrypt endpoints, accepts any client certificate."""
+    return await opc_servers('plant-s', {'Temperature': 20.0, 'Setpoint': 0.0}, secured=True)
+
+
+def secured_slot(server, certificate, **security):
+    slot = load_scenario_input('slot_secured.json', {'plant-s': server})
+    slot['plant-s']['certificate'] = certificate
+    slot['plant-s']['security'] = {**SECURED, **security}
+    return slot
+
+
+def secured_connector(server, certificate_id):
+    return {
+        'connector_id': '7',
+        'type': 'opc_ua',
+        'name': 'plant-s',
+        'url': server.url,
+        'status': 'Active',
+        'subscription_period_ms': 100,
+        'security': {**SECURED, 'client_certificate_id': certificate_id},
+    }
+
+
+def write_command():
+    return load_scenario_input(
+        'write_command.json', server_id='7', model_id='2', timestamp=TIMESTAMP
+    )
+
+
+# 6.1 Secured connections ---------------------------------------------------------------
+
+
+async def test_scenario_6_1_1_secured_read_with_certificate_from_minio(
+    secured_server, client_certificate, pods, put_slot, mongo_db, cert_cache_dir
+):
+    certificate = await client_certificate(7)
+    put_slot(1, secured_slot(secured_server, certificate))
+    pod = await pods('pod-a')
+
+    await pod.tick()
+
+    await secured_server.set('Temperature', 21.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_secured', value=21.0))
+    assert sorted(p.name for p in (cert_cache_dir / '7').iterdir()) == ['cert.der', 'key.pem']
+    assert notifications(mongo_db, 'OPC_CONNECTION_ERROR') == []
+
+
+async def test_scenario_6_1_2_secured_write_resolved_from_connectors_and_certificates(
+    secured_server, client_certificate, pods, mongo_db, postgres_engine, publish_command
+):
+    await client_certificate(7)
+    mongo_db['connectors'].insert_one(secured_connector(secured_server, 7))
+    insert_prediction(postgres_engine, 2, TIMESTAMP, 'pending')
+    await pods('pod-a')
+
+    await publish_command(write_command())
+
+    await wait_until(lambda: write_status(postgres_engine, 2, TIMESTAMP) == 'ok')
+    assert (await secured_server.read('Setpoint')).Value.Value == 1.25
+
+
+# 6.2 Failures --------------------------------------------------------------------------
+
+
+async def test_scenario_6_2_1_certificate_missing_in_minio(
+    secured_server, client_certificate, pods, put_slot, mongo_db, cert_cache_dir
+):
+    certificate = await client_certificate(7, upload=False)
+    put_slot(1, secured_slot(secured_server, certificate))
+    pod = await pods('pod-a')
+
+    await pod.tick()
+
+    assert notifications(mongo_db, 'OPC_CONNECTION_ERROR_plant-s')
+    assert pod.manager.opc_managers == {}
+    assert not list((cert_cache_dir / '7').glob('*.der'))
+    assert await stays_false(lambda: readings(mongo_db, 'raw_secured'))
+
+
+async def test_scenario_6_2_2_unsupported_security_policy(
+    secured_server, client_certificate, pods, put_slot, mongo_db
+):
+    certificate = await client_certificate(7)
+    put_slot(1, secured_slot(secured_server, certificate, policy='Basic999'))
+    pod = await pods('pod-a')
+
+    await pod.tick()
+
+    [error] = notifications(mongo_db, 'OPC_CONNECTION_ERROR_plant-s')
+    assert 'Unsupported OPC security' in error['message']
+    assert pod.manager.opc_managers == {}
+
+
+async def test_scenario_6_2_3_no_certificate_cannot_reach_a_secured_only_server(
+    secured_server, pods, put_slot, mongo_db
+):
+    put_slot(1, secured_slot(secured_server, None))
+    pod = await pods('pod-a')
+
+    await pod.tick()
+
+    assert notifications(mongo_db, 'OPC_CONNECTION_ERROR_plant-s')
+    assert await stays_false(lambda: readings(mongo_db, 'raw_secured'))
+
+
+async def test_scenario_6_2_4_inactive_certificate_write_fails(
+    secured_server, client_certificate, pods, mongo_db, postgres_engine, publish_command
+):
+    await client_certificate(7, status='revoked')
+    mongo_db['connectors'].insert_one(secured_connector(secured_server, 7))
+    insert_prediction(postgres_engine, 2, TIMESTAMP, 'pending')
+    await pods('pod-a')
+
+    await publish_command(write_command())
+
+    await wait_until(lambda: write_status(postgres_engine, 2, TIMESTAMP) == 'error')
+    assert secured_server.writes == []
+
+
+# 6.3 Rotation --------------------------------------------------------------------------
+
+
+async def test_scenario_6_3_1_certificate_rotation_reconnects_with_the_new_one(
+    secured_server, client_certificate, pods, put_slot, mongo_db, cert_cache_dir
+):
+    first = await client_certificate(7)
+    put_slot(1, secured_slot(secured_server, first))
+    pod = await pods('pod-a')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_secured'))
+    first_client = pod.manager.pool._connections['7'][0]
+
+    second = await client_certificate(8)
+    put_slot(1, secured_slot(secured_server, second))
+    await pod.tick()
+
+    assert pod.manager.pool._connections['7'][0] is not first_client
+    assert pod.manager.pool.config_for('7')['certificate']['certificate_id'] == 8
+    assert (cert_cache_dir / '8' / 'cert.der').is_file()
+    await secured_server.set('Temperature', 22.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_secured', value=22.0))
+    await wait_until(lambda: secured_server.session_count() == 1)

e2e/test_grpc_read_tag.py

@@ -0,0 +1,113 @@
+"""E2E scenarios — 4. On-demand gRPC ReadTag. See ``e2e/scenarios.md``."""
+
+import os
+import re
+
+import grpc
+import pytest
+import pytest_asyncio
+
+from e2e.helpers import load_scenario_input, readings, wait_until
+from ingestor.proto import opc_gateway_pb2, opc_gateway_pb2_grpc
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+FORMATTED_TIMESTAMP = re.compile(r'^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}-0300$')
+
+
+@pytest_asyncio.fixture
+async def grpc_stub():
+    """Client of the gateway's gRPC server (GRPC_PORT of the test environment)."""
+    channel = grpc.aio.insecure_channel(f'127.0.0.1:{os.environ["GRPC_PORT"]}')
+    yield opc_gateway_pb2_grpc.OpcGatewayStub(channel)
+    await channel.close()
+
+
+async def _reading_pod(opc_servers, pods, put_slot, mongo_db):
+    server = await opc_servers('plant-a', {'Temperature': 20.0, 'Level': 3.25})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    pod = await pods('pod-a', GRPC_ENABLED='true')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+    return server, pod
+
+
+async def test_scenario_4_1_1_reads_a_tag_of_a_connected_server(
+    opc_servers, pods, put_slot, mongo_db, grpc_stub
+):
+    await _reading_pod(opc_servers, pods, put_slot, mongo_db)
+    persisted_before = mongo_db.list_collection_names()
+
+    response = await grpc_stub.ReadTag(
+        opc_gateway_pb2.ReadTagRequest(server_id='1', addr='ns=2;s=Level', data_type='float')
+    )
+
+    assert response.value == '3.25'
+    assert response.opc_status_code == 'Good'
+    assert FORMATTED_TIMESTAMP.match(response.source_timestamp), response.source_timestamp
+    assert FORMATTED_TIMESTAMP.match(response.server_timestamp), response.server_timestamp
+    assert response.persisted is False  # no slot lookup wired yet: nothing is written
+    assert mongo_db.list_collection_names() == persisted_before
+
+
+async def test_scenario_4_1_2_reads_the_current_value(
+    opc_servers, pods, put_slot, mongo_db, grpc_stub
+):
+    server, _ = await _reading_pod(opc_servers, pods, put_slot, mongo_db)
+    await server.set('Level', 4.5)
+
+    response = await grpc_stub.ReadTag(
+        opc_gateway_pb2.ReadTagRequest(server_id='1', addr='ns=2;s=Level', data_type='float')
+    )
+
+    assert response.value == '4.5'
+
+
+async def test_scenario_4_2_1_unknown_address_is_internal_error(
+    opc_servers, pods, put_slot, mongo_db, grpc_stub
+):
+    await _reading_pod(opc_servers, pods, put_slot, mongo_db)
+
+    with pytest.raises(grpc.aio.AioRpcError) as error:
+        await grpc_stub.ReadTag(
+            opc_gateway_pb2.ReadTagRequest(server_id='1', addr='ns=2;s=Missing', data_type='float')
+        )
+
+    assert error.value.code() == grpc.StatusCode.INTERNAL
+    assert 'BadNodeIdUnknown' in error.value.details()
+
+
+async def test_scenario_4_2_2_server_not_connected_by_the_reads_is_internal_error(
+    opc_servers, pods, mongo_db, grpc_stub
+):
+    server = await opc_servers('plant-a', {'Level': 3.25})
+    mongo_db['connectors'].insert_one(
+        load_scenario_input('connector_plant_a.json', {'plant-a': server})
+    )
+    await pods('pod-a', GRPC_ENABLED='true')  # no slot: the pool has no connection to plant-a
+
+    with pytest.raises(grpc.aio.AioRpcError) as error:
+        await grpc_stub.ReadTag(
+            opc_gateway_pb2.ReadTagRequest(server_id='1', addr='ns=2;s=Level', data_type='float')
+        )
+
+    assert error.value.code() == grpc.StatusCode.INTERNAL
+    assert server.session_count() == 0
+
+
+async def test_scenario_4_2_3_grpc_disabled_by_default(
+    opc_servers, pods, put_slot, mongo_db, grpc_stub
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    pod = await pods('pod-a')
+    await pod.tick()
+
+    with pytest.raises(grpc.aio.AioRpcError) as error:
+        await grpc_stub.ReadTag(
+            opc_gateway_pb2.ReadTagRequest(server_id='1', addr='ns=2;s=Temperature'),
+            timeout=2,
+        )
+
+    assert error.value.code() in (grpc.StatusCode.UNAVAILABLE, grpc.StatusCode.DEADLINE_EXCEEDED)
+    assert pod.runtime.grpc_server is None

e2e/test_lifecycle.py

@@ -0,0 +1,93 @@
+"""E2E scenarios — 7. Pod lifecycle: shutdown, idle connections, startup failures. See ``e2e/scenarios.md``."""
+
+import asyncio
+
+import pytest
+
+from e2e.helpers import (
+    Pod,
+    insert_prediction,
+    load_scenario_input,
+    readings,
+    stays_false,
+    wait_until,
+    write_status,
+)
+from e2e.opc_server import free_port
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+TIMESTAMP = '2026-10-13T12:00:00-03:00'
+
+
+async def test_scenario_7_1_1_shutdown_closes_sessions_and_stops_consuming(
+    opc_servers, pods, put_slot, mongo_db, postgres_engine, publish_command
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0, 'Setpoint': 0.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    insert_prediction(postgres_engine, 2, TIMESTAMP, 'pending')
+    pod = await pods('pod-a')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+    assert server.session_count() == 1
+
+    await pod.stop()
+
+    await wait_until(lambda: server.session_count() == 0)
+    await publish_command(load_scenario_input('write_command.json'))
+    assert await stays_false(lambda: write_status(postgres_engine, 2, TIMESTAMP) != 'pending')
+    await server.set('Temperature', 50.0)
+    assert await stays_false(lambda: readings(mongo_db, 'raw_plant_a', value=50.0))
+
+
+async def test_scenario_7_1_2_idle_write_connection_is_closed_and_reopened(
+    opc_servers, pods, put_slot, mongo_db, postgres_engine, publish_command
+):
+    reader = await opc_servers('plant-a', {'Temperature': 20.0})
+    writer = await opc_servers('plant-b', {'Setpoint': 0.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': reader}))
+    connector = load_scenario_input('connector_plant_a.json', {'plant-a': writer})
+    mongo_db['connectors'].insert_one({**connector, 'connector_id': '2', 'name': 'plant-b'})
+    insert_prediction(postgres_engine, 2, TIMESTAMP, 'pending')
+    pod = await pods('pod-a', IDLE_CONN_MAX_S='1')
+    await pod.tick()
+
+    await publish_command(load_scenario_input('write_command.json', server_id='2'))
+    await wait_until(lambda: write_status(postgres_engine, 2, TIMESTAMP) == 'ok')
+    assert writer.session_count() == 1
+
+    await asyncio.sleep(1.5)
+    await pod.tick()  # idle_sweep
+
+    await wait_until(lambda: writer.session_count() == 0)
+    assert reader.session_count() == 1  # subscribed: pinned, never idle
+
+    insert_prediction(postgres_engine, 3, TIMESTAMP, 'pending')
+    await publish_command(load_scenario_input('write_command.json', server_id='2', model_id='3'))
+    await wait_until(lambda: write_status(postgres_engine, 3, TIMESTAMP) == 'ok')
+    assert writer.session_count() == 1
+
+
+async def test_scenario_7_2_1_redis_unreachable_fails_the_startup(monkeypatch):
+    monkeypatch.setenv('REDIS_PORT', str(free_port()))
+
+    with pytest.raises(Exception, match='(?i)connect'):
+        await Pod('pod-a').start()
+
+
+async def test_scenario_7_2_2_restarted_pod_takes_its_slot_back(
+    opc_servers, pods, put_slot, mongo_db, redis_client
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    pod = await pods('pod-a', LEASE_TTL='2', HEARTBEAT_TTL='2')
+    await pod.tick()
+    await pod.stop()
+
+    await wait_until(lambda: redis_client.get('lease:opc_tags:1') is None, timeout=5)
+    restarted = await pods('pod-a', LEASE_TTL='2', HEARTBEAT_TTL='2')
+    await restarted.tick()
+
+    assert restarted.slots == {'1'}
+    await server.set('Temperature', 31.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=31.0))

e2e/test_slot_leasing.py

@@ -0,0 +1,193 @@
+"""E2E scenarios — 1. Slot leasing and load balancing (Redis). See ``e2e/scenarios.md``."""
+
+import asyncio
+
+import pytest
+
+from e2e.helpers import (
+    load_scenario_input,
+    notifications,
+    readings,
+    redis_json,
+    stays_false,
+    wait_until,
+)
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+
+async def _two_slots(opc_servers, put_slot):
+    """Slot 1 reads plant-a, slot 2 reads plant-b."""
+    plant_a = await opc_servers('plant-a', {'Temperature': 20.0})
+    plant_b = await opc_servers('plant-b', {'Flow': 3.0})
+    both = load_scenario_input('slot_two_servers.json', {'plant-a': plant_a, 'plant-b': plant_b})
+    put_slot(1, {'plant-a': both['plant-a']})
+    put_slot(2, {'plant-b': both['plant-b']})
+    return plant_a, plant_b
+
+
+# 1.1 Acquisition ----------------------------------------------------------------------
+
+
+async def test_scenario_1_1_1_single_pod_leases_the_slot_and_heartbeats(
+    opc_servers, pods, put_slot, redis_client, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+
+    pod = await pods('pod-a')
+    await pod.tick()
+
+    assert pod.slots == {'1'}
+    assert redis_json(redis_client, 'lease:opc_tags:1') == 'pod-a'
+    assert 0 < redis_client.ttl('lease:opc_tags:1') <= 10
+    assert redis_json(redis_client, 'heartbeat:ingestor:pod-a') == 1
+    assert 0 < redis_client.ttl('heartbeat:ingestor:pod-a') <= 20
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+
+async def test_scenario_1_1_2_idle_pod_takes_a_slot_created_after_startup(
+    opc_servers, pods, put_slot, redis_client, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    pod = await pods('pod-a')
+    await pod.tick()
+    assert pod.slots == set()
+
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    await pod.tick()
+
+    assert pod.slots == {'1'}
+    assert redis_json(redis_client, 'lease:opc_tags:1') == 'pod-a'
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+
+# 1.2 Balancing and failover ------------------------------------------------------------
+
+
+async def test_scenario_1_2_1_two_pods_split_two_slots(
+    opc_servers, pods, put_slot, redis_client, mongo_db
+):
+    plant_a, plant_b = await _two_slots(opc_servers, put_slot)
+
+    pod_a = await pods('pod-a')
+    await pod_a.tick()
+    assert pod_a.slots == {'1', '2'}  # alone: takes every slot
+
+    pod_b = await pods('pod-b')
+    await pod_b.tick()
+    assert pod_b.slots == set()  # every slot is leased
+    await pod_a.tick()  # pod-a now sees a pod without slot and gives one back
+    assert pod_a.slots == {'1'}
+    await pod_b.tick()
+    assert pod_b.slots == {'2'}
+
+    assert redis_json(redis_client, 'lease:opc_tags:1') == 'pod-a'
+    assert redis_json(redis_client, 'lease:opc_tags:2') == 'pod-b'
+    assert set(pod_a.manager.opc_managers) == {'plant-a'}
+    assert set(pod_b.manager.opc_managers) == {'plant-b'}
+    await plant_a.set('Temperature', 25.0)
+    await plant_b.set('Flow', 4.5)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=25.0))
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_b', value=4.5))
+
+
+async def test_scenario_1_2_2_extra_pod_stays_idle(opc_servers, pods, put_slot, redis_client):
+    await _two_slots(opc_servers, put_slot)
+    pod_a, pod_b = await pods('pod-a'), await pods('pod-b')
+    await pod_a.tick()
+    await pod_b.tick()
+    await pod_a.tick()
+    await pod_b.tick()
+
+    pod_c = await pods('pod-c')
+    for _ in range(2):
+        for pod in (pod_a, pod_b, pod_c):
+            await pod.tick()
+
+    assert pod_c.slots == set()
+    assert pod_a.slots | pod_b.slots == {'1', '2'}
+    assert pod_a.slots.isdisjoint(pod_b.slots)
+    assert {
+        redis_json(redis_client, 'lease:opc_tags:1'),
+        redis_json(redis_client, 'lease:opc_tags:2'),
+    } == {
+        'pod-a',
+        'pod-b',
+    }
+
+
+async def test_scenario_1_2_3_failover_after_lease_expiry(
+    opc_servers, pods, put_slot, redis_client, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    pod_a = await pods('pod-a', LEASE_TTL='2', HEARTBEAT_TTL='2')
+    await pod_a.tick()
+    pod_b = await pods('pod-b')
+    await pod_b.tick()
+    assert (pod_a.slots, pod_b.slots) == ({'1'}, set())
+
+    await pod_a.stop()  # crash-like: the lease is not released, it expires
+    assert redis_json(redis_client, 'lease:opc_tags:1') == 'pod-a'
+    await wait_until(lambda: redis_json(redis_client, 'lease:opc_tags:1') is None, timeout=5)
+    await pod_b.tick()
+
+    assert pod_b.slots == {'1'}
+    assert redis_json(redis_client, 'lease:opc_tags:1') == 'pod-b'
+    await server.set('Temperature', 30.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=30.0))
+
+
+# 1.3 Slot changes and invalid slots ----------------------------------------------------
+
+
+async def test_scenario_1_3_1_deleted_slot_stops_the_reads(
+    opc_servers, pods, put_slot, redis_client, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    pod = await pods('pod-a')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+    redis_client.delete('slot:opc_tags:1')
+    await pod.tick()
+
+    assert pod.slots == set()
+    assert pod.manager.opc_managers == {}
+    await server.set('Temperature', 99.0)
+    assert await stays_false(lambda: readings(mongo_db, 'raw_plant_a', value=99.0))
+
+
+async def test_scenario_1_3_2_invalid_slot_is_notified_and_not_read(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_v1_invalid.json', {'plant-a': server}))
+
+    pod = await pods('pod-a')
+    await pod.tick()
+
+    assert pod.slots == set()
+    assert notifications(mongo_db, 'OPC_SLOT_CONFIG_ERROR_1')
+    assert await stays_false(lambda: readings(mongo_db, 'raw_plant_a'))
+
+
+async def test_scenario_1_3_3_fixed_slot_is_read_once_its_lease_expires(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0})
+    put_slot(1, load_scenario_input('slot_v1_invalid.json', {'plant-a': server}))
+    pod = await pods('pod-a', LEASE_TTL='2')
+    await pod.tick()
+    assert pod.slots == set()
+
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    await pod.tick()
+    assert pod.slots == set()  # still leased by the failed acquisition
+
+    await asyncio.sleep(2.5)
+    await pod.tick()
+    assert pod.slots == {'1'}
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))

e2e/test_subscription_reads.py

@@ -0,0 +1,266 @@
+"""E2E scenarios — 2. Subscription reads (OPC UA → MongoDB). See ``e2e/scenarios.md``."""
+
+import re
+
+import pytest
+
+from e2e.helpers import load_scenario_input, notifications, readings, stays_false, wait_until
+from e2e.opc_server import free_port
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+# DATETIME_FORMAT_WITH_TZ in OPC_TIMEZONE (sientia_do), e.g. 2026-10-29 19:48:51-0300
+READING_TIMESTAMP = re.compile(r'^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}-0300$')
+
+
+async def _read_slot(opc_servers, pods, put_slot, slot_file, variables):
+    server = await opc_servers('plant-a', variables)
+    slot = load_scenario_input(slot_file, {'plant-a': server})
+    put_slot(1, slot)
+    pod = await pods('pod-a')
+    await pod.tick()
+    return server, slot, pod
+
+
+# 2.1 Persistence -----------------------------------------------------------------------
+
+
+async def test_scenario_2_1_1_value_change_is_persisted(opc_servers, pods, put_slot, mongo_db):
+    server, _, _ = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=20.0))  # initial value
+
+    await server.set('Temperature', 21.5)
+
+    [doc] = await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=21.5))
+    assert doc['tag'] == 'ns=2;s=Temperature'
+    assert doc['name'] == 'temperature'
+    assert doc['model_id'] == '10'
+    assert READING_TIMESTAMP.match(doc['timestamp']), doc['timestamp']
+    assert doc['inserted_at'] is not None
+    assert set(doc) == {'tag', 'name', 'model_id', 'timestamp', 'value', 'inserted_at'}
+
+
+async def test_scenario_2_1_2_one_address_fans_out_to_every_name(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server, _, _ = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_multi_name.json', {'Pressure': 1.0}
+    )
+
+    await server.set('Pressure', 2.5)
+
+    [furnace] = await wait_until(lambda: readings(mongo_db, 'raw_furnace', value=2.5))
+    [boiler] = await wait_until(lambda: readings(mongo_db, 'raw_boiler', value=2.5))
+    assert (furnace['name'], furnace['model_id']) == ('furnace_pressure', '10')
+    assert (boiler['name'], boiler['model_id']) == ('boiler_inlet_pressure', '20')
+    assert furnace['tag'] == boiler['tag'] == 'ns=2;s=Pressure'
+    assert furnace['timestamp'] == boiler['timestamp']
+
+
+async def test_scenario_2_1_3_two_servers_in_one_slot(opc_servers, pods, put_slot, mongo_db):
+    plant_a = await opc_servers('plant-a', {'Temperature': 20.0})
+    plant_b = await opc_servers('plant-b', {'Flow': 3.0})
+    put_slot(
+        1, load_scenario_input('slot_two_servers.json', {'plant-a': plant_a, 'plant-b': plant_b})
+    )
+    pod = await pods('pod-a')
+    await pod.tick()
+
+    await plant_a.set('Temperature', 22.0)
+    await plant_b.set('Flow', 3.5)
+
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=22.0))
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_b', value=3.5))
+    assert set(pod.manager.opc_managers) == {'plant-a', 'plant-b'}
+
+
+async def test_scenario_2_1_4_values_keep_their_opc_type(opc_servers, pods, put_slot, mongo_db):
+    variables = {
+        'Temperature': (20.0, 'double', True),
+        'Counter': (1, 'int', True),
+        'Running': (False, 'bool', True),
+        'Batch': ('B-001', 'string', True),
+    }
+    server, _, _ = await _read_slot(opc_servers, pods, put_slot, 'slot_data_types.json', variables)
+
+    await server.set('Temperature', 20.25)
+    await server.set('Counter', 7)
+    await server.set('Running', True)
+    await server.set('Batch', 'B-002')
+
+    expected = {'temperature': 20.25, 'counter': 7, 'running': True, 'batch': 'B-002'}
+    for name, value in expected.items():
+        [doc] = await wait_until(
+            lambda n=name, v=value: readings(mongo_db, 'raw_types', name=n, value=v)
+        )
+        assert type(doc['value']) is type(value)
+
+
+# 2.2 Slot changes ----------------------------------------------------------------------
+
+
+async def test_scenario_2_2_1_tag_added_to_the_slot_is_subscribed(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server, slot, pod = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0, 'Level': 1.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', name='temperature'))
+
+    slot['plant-a']['tags']['ns=2;s=Level'] = {
+        'frequency': 1000,
+        'names': [{'collection': 'raw_plant_a', 'tag_name': 'level', 'model_id': '10'}],
+    }
+    put_slot(1, slot)
+    await pod.tick()
+
+    await server.set('Level', 1.75)
+    await server.set('Temperature', 23.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', name='level', value=1.75))
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', name='temperature', value=23.0))
+
+
+async def test_scenario_2_2_2_tag_removed_from_the_slot_is_no_longer_read(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0, 'Level': 1.0})
+    slot = load_scenario_input('slot_single_server.json', {'plant-a': server})
+    slot['plant-a']['tags']['ns=2;s=Level'] = {
+        'frequency': 1000,
+        'names': [{'collection': 'raw_plant_a', 'tag_name': 'level', 'model_id': '10'}],
+    }
+    put_slot(1, slot)
+    pod = await pods('pod-a')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', name='level'))
+
+    del slot['plant-a']['tags']['ns=2;s=Level']
+    put_slot(1, slot)
+    await pod.tick()
+
+    await server.set('Level', 9.0)
+    await server.set('Temperature', 24.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', name='temperature', value=24.0))
+    assert await stays_false(lambda: readings(mongo_db, 'raw_plant_a', name='level', value=9.0))
+
+
+async def test_scenario_2_2_3_name_added_to_a_tag_receives_its_readings(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server, slot, pod = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+    slot['plant-a']['tags']['ns=2;s=Temperature']['names'].append(
+        {'collection': 'raw_dryer', 'tag_name': 'dryer_temperature', 'model_id': '50'}
+    )
+    put_slot(1, slot)
+    await pod.tick()
+
+    await server.set('Temperature', 26.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=26.0))
+    [doc] = await wait_until(lambda: readings(mongo_db, 'raw_dryer', value=26.0))
+    assert (doc['name'], doc['model_id']) == ('dryer_temperature', '50')
+
+
+async def test_scenario_2_2_4_server_url_change_reconnects_to_the_new_server(
+    opc_servers, pods, put_slot, mongo_db
+):
+    old = await opc_servers('plant-a', {'Temperature': 20.0})
+    new = await opc_servers('plant-a-new', {'Temperature': 40.0})
+    slot = load_scenario_input('slot_single_server.json', {'plant-a': old})
+    put_slot(1, slot)
+    pod = await pods('pod-a')
+    await pod.tick()
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=20.0))
+
+    slot['plant-a']['url'] = new.url
+    put_slot(1, slot)
+    await pod.tick()
+
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=40.0))
+    await new.set('Temperature', 41.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=41.0))
+    await wait_until(lambda: old.session_count() == 0)
+    await old.set('Temperature', 21.0)
+    assert await stays_false(lambda: readings(mongo_db, 'raw_plant_a', value=21.0))
+
+
+# 2.3 Failures and resilience -----------------------------------------------------------
+
+
+async def test_scenario_2_3_1_unreachable_server_does_not_stop_the_others(
+    opc_servers, pods, put_slot, mongo_db
+):
+    plant_a = await opc_servers('plant-a', {'Temperature': 20.0})
+    plant_b = await opc_servers('plant-b', {'Flow': 3.0})
+    slot = load_scenario_input('slot_two_servers.json', {'plant-a': plant_a, 'plant-b': plant_b})
+    slot['plant-b']['url'] = f'opc.tcp://127.0.0.1:{free_port()}'  # nothing listens there
+    put_slot(1, slot)
+
+    pod = await pods('pod-a')
+    await pod.tick()
+
+    assert notifications(mongo_db, 'OPC_CONNECTION_ERROR_plant-b')
+    assert set(pod.manager.opc_managers) == {'plant-a'}
+    await plant_a.set('Temperature', 27.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=27.0))
+
+
+async def test_scenario_2_3_2_tag_without_data_raises_a_warning(
+    opc_servers, pods, put_slot, mongo_db
+):
+    _, _, pod = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+    await pod.tick(5)  # POLL_INTERVAL 1 s / frequency 1000 ms: one cycle per iteration
+
+    [warning] = notifications(mongo_db, 'TAG_ns=2;s=Temperature:temperature_LISTENNING_STOPPED')
+    assert warning['level'] in ('WARNING', 'warning')
+
+
+async def test_scenario_2_3_3_silent_server_is_reconnected_after_15_cycles(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server, _, pod = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+    first_client = pod.manager.pool._connections['1'][0]
+
+    await pod.tick(15)
+    assert notifications(mongo_db, 'OPC_LISTENNING_STOPPED__1')
+    assert notifications(mongo_db, 'OPC_CONNECTION_RETRY__1')
+    assert 'plant-a' not in pod.manager.opc_managers
+    await pod.tick()
+
+    assert 'plant-a' in pod.manager.opc_managers
+    assert pod.manager.pool._connections['1'][0] is not first_client
+    await server.set('Temperature', 28.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=28.0))
+
+
+async def test_scenario_2_3_4_server_restart_resumes_the_reads(
+    opc_servers, pods, put_slot, mongo_db
+):
+    server, _, pod = await _read_slot(
+        opc_servers, pods, put_slot, 'slot_single_server.json', {'Temperature': 20.0}
+    )
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a'))
+
+    await server.stop()
+    await pod.tick(15)  # no data: the server is dropped
+    assert 'plant-a' not in pod.manager.opc_managers
+    await pod.tick()  # still down: reconnection fails and is notified
+    assert notifications(mongo_db, 'OPC_CONNECTION_ERROR_plant-a')
+
+    await server.start()
+    await pod.tick(2)
+    assert 'plant-a' in pod.manager.opc_managers
+    await server.set('Temperature', 29.0)
+    await wait_until(lambda: readings(mongo_db, 'raw_plant_a', value=29.0))

e2e/test_writes.py

@@ -0,0 +1,386 @@
+"""E2E scenarios — 3. Writes (NATS C2 → OPC UA → Postgres write_status C3). See ``e2e/scenarios.md``."""
+
+import json
+from datetime import datetime
+
+import nats
+import pytest
+import pytest_asyncio
+
+from e2e.conftest import WRITE_SUBJECT, nats_server_container
+from e2e.helpers import (
+    SOURCE_TIMESTAMP_BIT,
+    STATUS_CODE_BIT,
+    datavalue_mask,
+    insert_prediction,
+    load_scenario_input,
+    notifications,
+    prediction_count,
+    stays_false,
+    wait_until,
+    write_status,
+)
+from e2e.opc_server import free_port
+
+pytestmark = [pytest.mark.integration, pytest.mark.asyncio]
+
+TIMESTAMP = '2026-10-13T12:00:00-03:00'
+MODEL_ID = 2
+MARKER_MODEL_ID = 99
+
+
+@pytest_asyncio.fixture
+async def target(opc_servers, mongo_db, postgres_engine):
+    """plant-a with a writable Setpoint and a read-only Locked, its connector in Mongo
+    and a pending prediction row (model 2)."""
+    server = await opc_servers(
+        'plant-a',
+        {
+            'Setpoint': 0.0,
+            'Counter': (0, 'int', True),
+            'Locked': (5.0, 'float', False),
+            'Marker': 0.0,
+        },
+    )
+    mongo_db['connectors'].insert_one(
+        load_scenario_input('connector_plant_a.json', {'plant-a': server})
+    )
+    insert_prediction(postgres_engine, MODEL_ID, TIMESTAMP, 'pending')
+    return server
+
+
+def command(**overrides) -> dict:
+    return load_scenario_input('write_command.json', **overrides)
+
+
+async def processed(publish_command, postgres_engine) -> None:
+    """Wait until every command published so far was handled: NATS delivers the
+    messages of a subscription in order, so once a marker command (another row, the
+    ``Marker`` variable) is recorded, the previous ones are done."""
+    insert_prediction(postgres_engine, MARKER_MODEL_ID, TIMESTAMP, 'pending')
+    await publish_command(command(model_id=str(MARKER_MODEL_ID), addr='ns=2;s=Marker'))
+    await wait_until(lambda: write_status(postgres_engine, MARKER_MODEL_ID, TIMESTAMP) == 'ok')
+
+
+async def wait_status(postgres_engine, expected: str, model_id: int = MODEL_ID) -> None:
+    await wait_until(lambda: write_status(postgres_engine, model_id, TIMESTAMP) == expected)
+
+
+# 3.1 DataValue parts: timestamp and quality (SIENTIAPDE-2202) ------------------------
+
+DATAVALUE_CASES = [
+    pytest.param({}, {}, True, True, id='3_1_1_defaults_on'),
+    pytest.param({'WRITE_TIMESTAMP': 'false'}, {}, False, True, id='3_1_2_timestamp_off'),
+    pytest.param({'WRITE_QUALITY': 'false'}, {}, True, False, id='3_1_3_quality_off'),
+    pytest.param(
+        {'WRITE_TIMESTAMP': 'false', 'WRITE_QUALITY': 'false'},
+        {},
+        False,
+        False,
+        id='3_1_4_both_off',
+    ),
+    pytest.param(
+        {'WRITE_TIMESTAMP': 'true'},
+        {'write_timestamp': False},
+        False,
+        True,
+        id='3_1_5_command_overrides_env',
+    ),
+    pytest.param(
+        {'WRITE_TIMESTAMP': 'false', 'WRITE_QUALITY': 'false'},
+        {'write_timestamp': True, 'write_quality': True},
+        True,
+        True,
+        id='3_1_6_command_turns_on_over_env',
+    ),
+]
+
+
+@pytest.mark.parametrize('env,flags,expect_timestamp,expect_quality', DATAVALUE_CASES)
+async def test_scenario_3_1_datavalue_parts(
+    target,
+    pods,
+    publish_command,
+    postgres_engine,
+    opc_wire,
+    env,
+    flags,
+    expect_timestamp,
+    expect_quality,
+):
+    await pods('pod-a', **env)
+
+    await publish_command(command(**flags))
+
+    await wait_status(postgres_engine, 'ok')
+    stored = await target.read('Setpoint')
+    assert stored.Value.Value == 1.25
+    if expect_timestamp:
+        assert stored.SourceTimestamp == datetime.fromisoformat(TIMESTAMP)
+    else:
+        assert stored.SourceTimestamp is None
+    [request] = opc_wire
+    mask = datavalue_mask(request, 'ns=2;s=Setpoint')
+    assert bool(mask & SOURCE_TIMESTAMP_BIT) is expect_timestamp
+    assert bool(mask & STATUS_CODE_BIT) is expect_quality
+
+
+# 3.2 write_status (C3) -----------------------------------------------------------------
+
+
+async def test_scenario_3_2_1_pending_row_becomes_ok(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+
+    await publish_command(command(value=3.5))
+
+    await wait_status(postgres_engine, 'ok')
+    assert (await target.read('Setpoint')).Value.Value == 3.5
+
+
+async def test_scenario_3_2_2_null_write_status_becomes_ok(
+    opc_servers, mongo_db, pods, publish_command, postgres_engine
+):
+    server = await opc_servers('plant-a', {'Setpoint': 0.0})
+    mongo_db['connectors'].insert_one(
+        load_scenario_input('connector_plant_a.json', {'plant-a': server})
+    )
+    insert_prediction(postgres_engine, MODEL_ID, TIMESTAMP, None)  # row from before the column
+    await pods('pod-a')
+
+    await publish_command(command())
+
+    await wait_status(postgres_engine, 'ok')
+
+
+@pytest.mark.parametrize('worse', ['error', 'session_bad'])
+async def test_scenario_3_2_3_worse_outcome_is_kept(
+    opc_servers, mongo_db, pods, publish_command, postgres_engine, worse
+):
+    server = await opc_servers('plant-a', {'Setpoint': 0.0, 'Marker': 0.0})
+    mongo_db['connectors'].insert_one(
+        load_scenario_input('connector_plant_a.json', {'plant-a': server})
+    )
+    insert_prediction(postgres_engine, MODEL_ID, TIMESTAMP, worse)
+    await pods('pod-a')
+
+    await publish_command(command(value=4.0))
+    await processed(publish_command, postgres_engine)
+
+    assert (await server.read('Setpoint')).Value.Value == 4.0  # the OPC write happened
+    assert write_status(postgres_engine, MODEL_ID, TIMESTAMP) == worse
+
+
+async def test_scenario_3_2_4_failure_replaces_ok(target, pods, publish_command, postgres_engine):
+    await pods('pod-a')
+    await publish_command(command())
+    await wait_status(postgres_engine, 'ok')
+
+    await publish_command(command(value='not-a-number'))
+
+    await wait_status(postgres_engine, 'error')
+
+
+async def test_scenario_3_2_5_missing_row_is_not_created(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+
+    await publish_command(command(model_id='3', value=6.0))
+    await processed(publish_command, postgres_engine)
+
+    assert (await target.read('Setpoint')).Value.Value == 6.0
+    assert write_status(postgres_engine, 3, TIMESTAMP) == '<missing>'
+    assert prediction_count(postgres_engine) == 2  # model 2 + marker
+
+
+# 3.3 Failed commands -------------------------------------------------------------------
+
+
+async def test_scenario_3_3_1_unknown_server_is_an_error(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+
+    await publish_command(command(server_id='404'))
+
+    await wait_status(postgres_engine, 'error')
+    assert target.writes == []
+
+
+@pytest.mark.parametrize(
+    'connector_change',
+    [
+        pytest.param({'status': 'Inactive'}, id='inactive'),
+        pytest.param({'type': 'modbus'}, id='not_opc_ua'),
+        pytest.param({'security': {'mode': 'None'}}, id='no_policy'),
+        pytest.param({'url': ''}, id='no_url'),
+    ],
+)
+async def test_scenario_3_3_2_unusable_connector_is_an_error(
+    target, mongo_db, pods, publish_command, postgres_engine, connector_change
+):
+    mongo_db['connectors'].update_one({'connector_id': '1'}, {'$set': connector_change})
+    await pods('pod-a')
+
+    await publish_command(command())
+
+    await wait_status(postgres_engine, 'error')
+    assert target.writes == []
+
+
+@pytest.mark.parametrize(
+    'overrides',
+    [
+        pytest.param(
+            {'value': 'abc', 'data_type': 'int', 'addr': 'ns=2;s=Counter'}, id='conversion'
+        ),
+        pytest.param({'data_type': 'decimal128'}, id='unknown_data_type'),
+        pytest.param({'addr': None}, id='missing_addr'),
+    ],
+)
+async def test_scenario_3_3_3_invalid_command_is_an_error_without_opc_write(
+    target, pods, publish_command, postgres_engine, overrides
+):
+    await pods('pod-a')
+    cmd = command(**overrides)
+    if overrides.get('addr', '') is None:
+        del cmd['addr']
+
+    await publish_command(cmd)
+
+    await wait_status(postgres_engine, 'error')
+    assert target.writes == []
+
+
+async def test_scenario_3_3_4_bad_timestamp_skips_the_write_and_keeps_the_row(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+
+    await publish_command(command(timestamp='13/10/2026 12:00'))
+    await processed(publish_command, postgres_engine)
+
+    assert [w.NodeId.Identifier for w in target.writes] == ['Marker']
+    assert write_status(postgres_engine, MODEL_ID, TIMESTAMP) == 'pending'
+
+
+@pytest.mark.parametrize(
+    'addr',
+    [
+        pytest.param('ns=2;s=Locked', id='not_writable'),
+        pytest.param('ns=2;s=Missing', id='unknown_node'),
+    ],
+)
+async def test_scenario_3_3_5_opc_rejection_is_an_error(
+    target, pods, publish_command, postgres_engine, addr
+):
+    await pods('pod-a')
+
+    await publish_command(command(addr=addr))
+
+    await wait_status(postgres_engine, 'error')
+    assert (await target.read('Locked')).Value.Value == 5.0
+
+
+async def test_scenario_3_3_6_malformed_json_is_dropped_and_the_consumer_keeps_going(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+
+    await publish_command(b'{"server_id": "1", "value": ')
+    await publish_command(command(value=7.0))
+
+    await wait_status(postgres_engine, 'ok')
+    assert (await target.read('Setpoint')).Value.Value == 7.0
+
+
+# 3.4 Connections -----------------------------------------------------------------------
+
+
+async def test_scenario_3_4_1_write_reuses_the_read_connection(
+    opc_servers, pods, put_slot, publish_command, postgres_engine, mongo_db
+):
+    server = await opc_servers('plant-a', {'Temperature': 20.0, 'Setpoint': 0.0})
+    put_slot(1, load_scenario_input('slot_single_server.json', {'plant-a': server}))
+    insert_prediction(postgres_engine, MODEL_ID, TIMESTAMP, 'pending')
+    pod = await pods('pod-a')
+    await pod.tick()
+    assert mongo_db['connectors'].count_documents({}) == 0  # only the slot knows plant-a
+
+    await publish_command(command())
+
+    await wait_status(postgres_engine, 'ok')
+    assert server.session_count() == 1
+
+
+async def test_scenario_3_4_2_write_only_server_gets_its_own_connection(
+    target, pods, publish_command, postgres_engine
+):
+    pod = await pods('pod-a')
+    assert target.session_count() == 0
+
+    await publish_command(command())
+
+    await wait_status(postgres_engine, 'ok')
+    assert target.session_count() == 1
+    assert pod.manager.pool.config_for('1')['url'] == target.url
+
+
+# 3.5 Throughput and scaling ------------------------------------------------------------
+
+
+async def test_scenario_3_5_1_min_pause_between_writes(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a', WRITE_MIN_PAUSE_S='0.5')
+
+    for value in (1.0, 2.0, 3.0):
+        await publish_command(command(value=value))
+
+    await wait_until(lambda: len(target.writes) == 3)
+    gaps = [b - a for a, b in zip(target.write_times, target.write_times[1:], strict=False)]
+    assert all(gap >= 0.45 for gap in gaps), gaps
+
+
+async def test_scenario_3_5_2_queue_group_writes_each_command_once(
+    target, pods, publish_command, postgres_engine
+):
+    await pods('pod-a')
+    await pods('pod-b')
+
+    for value in range(6):
+        await publish_command(command(value=float(value)))
+
+    await wait_until(lambda: len(target.writes) == 6)
+    assert await stays_false(lambda: len(target.writes) > 6)
+
+
+# 3.6 NATS availability -----------------------------------------------------------------
+
+
+async def test_scenario_3_6_1_nats_down_at_startup_connects_later(
+    target, pods, postgres_engine, mongo_db
+):
+    port = free_port()
+    url = f'nats://127.0.0.1:{port}'
+    pod = await pods('pod-a', NATS_URL=url)  # nothing listens yet
+    await pod.tick()  # retried by idle_sweep, notified once per outage
+
+    assert len(notifications(mongo_db, 'GATEWAY_NATS_CONSUMER_START_FAILED')) == 1
+    nats_server = nats_server_container(host_port=port)
+    nats_server.start()
+    try:
+        await pod.tick()
+        assert pod.runtime._nats_started
+
+        client = await nats.connect(url)
+        cmd = load_scenario_input('write_command.json')
+        await client.publish(WRITE_SUBJECT, json.dumps(cmd).encode())
+        await client.flush()
+        await wait_status(postgres_engine, 'ok')
+        await client.drain()
+    finally:
+        await pod.stop()
+        nats_server.stop()

ingestor/adapters/nats_consumer.py

@@ -3,12 +3,14 @@
 Thin adapter: decode the message JSON and hand the dict to WriteEngine,
 which is already raise-safe against malformed commands. No metrics of its
 own — the engine records write metrics; a malformed-JSON drop is logged
-here. No reconnect logic — nats-py handles reconnection internally.
+here. Once connected, nats-py reconnects by itself, forever.
 """
 
+import asyncio
 import json
+import math
+import traceback
 
-import nats
 from nats.aio.client import Client
 from nats.aio.subscription import Subscription
 from sientia_do.observability.logger import Logger
@@ -24,18 +26,55 @@ class NatsWriteConsumer:
         logger: Logger,
         subject: str = 'opc.write',
         queue: str = 'gateway-writers',
+        connect_timeout_s: float = 5.0,
     ):
         self.nats_url = nats_url
         self.write_engine = write_engine
         self.logger = logger
         self.subject = subject
         self.queue = queue
+        self.connect_timeout_s = connect_timeout_s
         self.nc: Client | None = None
         self.sub: Subscription | None = None
 
+    @property
+    def closed(self) -> bool:
+        """True when there is no connection, or it was closed for good."""
+        return self.nc is None or self.nc.is_closed
+
     async def start(self) -> None:
-        self.nc = await nats.connect(servers=self.nats_url)
-        self.sub = await self.nc.subscribe(self.subject, queue=self.queue, cb=self._handle)
+        """Connect and subscribe, giving up after ``connect_timeout_s``.
+
+        It runs from the main loop (startup and ``GatewayRuntime.idle_sweep``), so it
+        must never block it: nats-py's defaults retry the first connection 60 times,
+        about 2 minutes, longer than the heartbeat TTL, and with
+        ``max_reconnect_attempts=-1`` they would retry it forever. Once connected,
+        reconnection is unbounded, so an outage never closes the connection for good.
+
+        Raises:
+            Exception: When the connection or the subscription failed; nothing is left
+                open in that case.
+        """
+        nc = Client()
+        try:
+            await asyncio.wait_for(
+                nc.connect(
+                    servers=self.nats_url,
+                    connect_timeout=math.ceil(self.connect_timeout_s),
+                    max_reconnect_attempts=-1,
+                    name='opc-gateway',
+                    # One log line per event instead of nats-py's traceback per attempt.
+                    error_cb=self._on_error,
+                    disconnected_cb=self._on_disconnected,
+                    reconnected_cb=self._on_reconnected,
+                ),
+                timeout=self.connect_timeout_s,
+            )
+            self.sub = await nc.subscribe(self.subject, queue=self.queue, cb=self._handle)
+        except (Exception, asyncio.CancelledError):
+            await self._discard(nc)
+            raise
+        self.nc = nc
         self.logger.info(f'NatsWriteConsumer started: subject={self.subject} queue={self.queue}')
 
     async def _handle(self, msg) -> None:
@@ -45,11 +84,41 @@ class NatsWriteConsumer:
             preview = msg.data[:200]
             self.logger.error(f'NatsWriteConsumer dropped malformed JSON ({e}): {preview!r}')
             return
-        await self.write_engine.write(payload)
+        try:
+            await self.write_engine.write(payload)
+        except Exception as e:
+            # The engine is raise-safe; this only keeps an unexpected bug from going to
+            # nats-py's error callback without context.
+            self.logger.error(
+                f'NatsWriteConsumer: unexpected error handling a write command ({e}):\n'
+                f'{traceback.format_exc()}'
+            )
+
+    # These stay async with nothing to await: nats-py rejects callbacks that are not
+    # coroutine functions (InvalidCallbackTypeError on connect).
+    async def _on_error(self, e: Exception) -> None:
+        self.logger.warning(f'NATS error: {type(e).__name__} {e}')
+
+    async def _on_disconnected(self) -> None:
+        self.logger.warning('Disconnected from NATS; reconnecting')
+
+    async def _on_reconnected(self) -> None:
+        self.logger.info('Reconnected to NATS')
+
+    async def _discard(self, nc: Client) -> None:
+        try:
+            await nc.close()
+        except Exception as e:
+            self.logger.warning(f'Error closing a failed NATS connection: {e}')
 
     async def stop(self) -> None:
         if self.nc is None:
             return
+        if self.nc.is_closed:
+            # Closed for good already: unsubscribe/drain would raise ConnectionClosedError
+            # and abort the shutdown sequence.
+            self.nc = None
+            return
         if self.sub is not None:
             await self.sub.unsubscribe()
         await self.nc.drain()

ingestor/config.py

@@ -22,9 +22,8 @@ class GatewayConfig:
     nats_queue: str = 'gateway-writers'
     grpc_enabled: bool = False
     grpc_port: int = 50051
-    # Legacy frontend bucket the platform already provisions (SIENTIAPDE-1974 D7);
-    # the design's `sientia-dataops` bucket does not exist in the platform MinIO.
-    cert_bucket: str = 'streamlit-connectors'
+    # The certificate bucket and objects come from the slot / the write lookup
+    # (opc_certificates, SIENTIAPDE-1974); only the local cache dir is configured here.
     cert_cache_dir: str = '/tmp/opc-certs'  # noqa: S108 # nosec B108 - default is spec'd, overridable via env
     write_timestamp: bool = True
     write_quality: bool = True
@@ -36,10 +35,7 @@ class GatewayConfig:
         """Only the certificate settings — what the read path needs. Plain strings,
         no number parsing, so a malformed write/gRPC env var (GRPC_PORT,
         WRITE_MIN_PAUSE_S, ...) can only disable the runtime, never the reads."""
-        return cls(
-            cert_bucket=getenv('CERT_BUCKET', cls.cert_bucket),
-            cert_cache_dir=getenv('CERT_CACHE_DIR', cls.cert_cache_dir),
-        )
+        return cls(cert_cache_dir=getenv('CERT_CACHE_DIR', cls.cert_cache_dir))
 
     @classmethod
     def from_env(cls) -> 'GatewayConfig':
@@ -49,7 +45,6 @@ class GatewayConfig:
             nats_queue=getenv('NATS_QUEUE', cls.nats_queue),
             grpc_enabled=_env_bool('GRPC_ENABLED', cls.grpc_enabled),
             grpc_port=int(getenv('GRPC_PORT', cls.grpc_port)),
-            cert_bucket=getenv('CERT_BUCKET', cls.cert_bucket),
             cert_cache_dir=getenv('CERT_CACHE_DIR', cls.cert_cache_dir),
             write_timestamp=_env_bool('WRITE_TIMESTAMP', cls.write_timestamp),
             write_quality=_env_bool('WRITE_QUALITY', cls.write_quality),

ingestor/connection/certificates.py

@@ -0,0 +1,92 @@
+"""Client certificate of a tag database connector (SIENTIAPDE-1974 D5).
+
+Mirrors the Orchestrator's `tag_database.resolve_certificate`, which puts the
+certificate in the read slot: the write lookup (ServerConfigResolver, D1) resolves a
+server that is not in the pool with the same rule, so a write uses the certificate the
+slot would have. Keep both in sync.
+"""
+
+from typing import Any
+
+# security fields of an OPC UA connector: the source of its OPC security (D4)
+SECURITY_FIELDS = ('mode', 'policy')
+CERTIFICATE_FIELDS = ('certificate_id', 'application_uri')
+CERTIFICATE_OBJECTS = ('cert', 'private_key')
+STORED_OBJECT_FIELDS = ('bucket', 'object_name')
+
+# opc_certificates lookup of a connectors aggregation: the certificate the connector's
+# security.client_certificate_id points to, only when it is active and of kind client.
+CERTIFICATE_LOOKUP = {
+    '$lookup': {
+        'from': 'opc_certificates',
+        'let': {'certificate_id': '$security.client_certificate_id'},
+        'pipeline': [
+            {
+                '$match': {
+                    '$expr': {'$eq': ['$certificate_id', '$$certificate_id']},
+                    'status': 'active',
+                    'kind': 'client',
+                }
+            },
+            {
+                '$project': {
+                    '_id': 0,
+                    'certificate_id': 1,
+                    'application_uri': 1,
+                    'cert.bucket': 1,
+                    'cert.object_name': 1,
+                    'private_key.bucket': 1,
+                    'private_key.object_name': 1,
+                }
+            },
+        ],
+        'as': 'certificates',
+    }
+}
+
+
+def _is_complete(document: Any, fields: tuple[str, ...]) -> bool:
+    return isinstance(document, dict) and all(
+        document.get(field) not in (None, '') for field in fields
+    )
+
+
+def _is_usable_certificate(certificate: Any) -> bool:
+    return _is_complete(certificate, CERTIFICATE_FIELDS) and all(
+        _is_complete(certificate.get(name), STORED_OBJECT_FIELDS) for name in CERTIFICATE_OBJECTS
+    )
+
+
+def client_certificate_id(connector: dict[str, Any]) -> Any:
+    """The connector's security.client_certificate_id (None when it has none)."""
+    security = connector.get('security')
+    return security.get('client_certificate_id') if isinstance(security, dict) else None
+
+
+def has_security(connector: dict[str, Any]) -> bool:
+    """Whether the connector has security.mode and security.policy (D4)."""
+    return _is_complete(connector.get('security'), SECURITY_FIELDS)
+
+
+def resolve_certificate(connector: dict[str, Any]) -> dict[str, Any] | None:
+    """
+    The client certificate of a connector from CERTIFICATE_LOOKUP, or None (D5).
+
+    None means no certificate: the connection is opened without security. A connector
+    whose client_certificate_id is set but has no usable certificate is most likely a
+    registration error; the caller reports it (see client_certificate_id).
+
+    Returns:
+        dict[str, Any] | None: certificate_id, application_uri, and cert and private_key
+            as {bucket, object_name}, as in the slot
+    """
+    for certificate in connector.get('certificates') or []:
+        if _is_usable_certificate(certificate):
+            return {
+                **{field: certificate[field] for field in CERTIFICATE_FIELDS},
+                **{
+                    name: {field: certificate[name][field] for field in STORED_OBJECT_FIELDS}
+                    for name in CERTIFICATE_OBJECTS
+                },
+            }
+    return None

ingestor/connection/certs.py

@@ -7,63 +7,88 @@ from sientia_do.repository.minio_repository import MinioRepository
 
 from ingestor.config import _env_bool
 
-COLLECTION_NAME = 'platform_certificates'
+# The two objects of a client certificate, and the local file each one is saved as
+CERTIFICATE_OBJECTS = (('cert', 'cert'), ('private_key', 'key'))
 
 
 class CertificateNotConfiguredError(RuntimeError):
-    """No usable platform OPC client certificate is registered (Mongo + MinIO)."""
+    """The certificate of a server does not name its MinIO objects (opc_certificates)."""
+
+
+def _objects(certificate: dict) -> tuple[tuple[str, str], ...]:
+    """(bucket, object_name) of the cert and the private key, in CERTIFICATE_OBJECTS order."""
+    try:
+        return tuple(
+            (str(certificate[field]['bucket']), str(certificate[field]['object_name']))
+            for field, _ in CERTIFICATE_OBJECTS
+        )
+    except (KeyError, TypeError) as e:
+        raise CertificateNotConfiguredError(
+            f'OPC client certificate {certificate!r} does not name the MinIO bucket and '
+            f'object of its cert and private_key (opc_certificates)'
+        ) from e
+
+
+def _certificate_id(certificate: dict) -> str:
+    """certificate_id as the name of its cache folder: an integer, never a path."""
+    try:
+        return str(int(certificate['certificate_id']))
+    except (KeyError, TypeError, ValueError) as e:
+        raise CertificateNotConfiguredError(
+            f'OPC client certificate {certificate!r} has no integer certificate_id'
+        ) from e
 
 
 class CertProvider:
-    """Downloads the platform's client cert + private key (Mongo metadata,
-    MinIO bytes) into a writable cache dir — pod root FS is read-only (§12),
-    so `cache_dir` must be an emptyDir/tmpfs mount.
+    """Downloads the client cert + private key of a connection (the MinIO objects its
+    slot server or write lookup names, SIENTIAPDE-1974) into a writable cache dir — pod
+    root FS is read-only (§12), so `cache_dir` must be an emptyDir/tmpfs mount.
 
-    The certificate is single and shared by every connection (reads, writes,
-    gRPC), so it is downloaded once and cached; `invalidate()` forces a fresh
-    download (the pool calls it when a secured connection fails, e.g. after the
-    certificate was replaced in MinIO). The lock serializes downloads so two
-    connections never rewrite the cache files at the same time."""
+    Each certificate (`certificate_id`) has its own folder (`<cache_dir>/<certificate_id>/`),
+    cache entry and lock, so two connections never rewrite the same files at the same
+    time. A cached certificate is reused while it names the same objects; when the slot
+    names other objects for the same id (the certificate was replaced), it is downloaded
+    again. `invalidate(certificate_id)` forces a fresh download (the pool calls it when a
+    secured connection fails, e.g. after the objects were replaced in MinIO)."""
 
-    def __init__(self, mongo, minio, cache_dir: str, bucket: str, metadata: dict | None = None):
-        self.mongo = mongo
+    def __init__(self, minio, cache_dir: str, metadata: dict | None = None):
         self.minio = minio
         self.cache_dir = cache_dir
-        self.bucket = bucket
         self.metadata = metadata or {}
-        self._lock = asyncio.Lock()
-        self._paths: tuple[str, str] | None = None
+        # ponytail: one Lock per certificate, never cleaned up — the set is small.
+        self._locks: dict[str, asyncio.Lock] = {}
+        self._paths: dict[str, tuple[tuple[tuple[str, str], ...], tuple[str, str]]] = {}
 
-    async def fetch(self) -> tuple[str, str]:
-        async with self._lock:
-            if self._paths is None:
-                self._paths = await self._download_all()
-            return self._paths
+    async def fetch(self, certificate: dict) -> tuple[str, str]:
+        """Local paths of the cert and private key of `certificate` (slot format)."""
+        certificate_id = _certificate_id(certificate)
+        objects = _objects(certificate)
+        async with self._locks.setdefault(certificate_id, asyncio.Lock()):
+            cached = self._paths.get(certificate_id)
+            if cached is None or cached[0] != objects:
+                self._paths[certificate_id] = (
+                    objects,
+                    await self._download_all(certificate_id, objects),
+                )
+            return self._paths[certificate_id][1]
 
-    def invalidate(self) -> None:
-        self._paths = None
+    def invalidate(self, certificate_id) -> None:
+        self._paths.pop(str(certificate_id), None)
 
-    async def _download_all(self) -> tuple[str, str]:
-        doc = await self.mongo.find_one(COLLECTION_NAME, {}, self.metadata)
-        try:
-            cert_object = doc['client_cert']['minio_object_name']
-            key_object = doc['private_key']['minio_object_name']
-        except (KeyError, TypeError) as e:
-            raise CertificateNotConfiguredError(
-                f'No OPC client certificate configured: the Mongo collection '
-                f"'{COLLECTION_NAME}' needs a document with client_cert.minio_object_name "
-                f'and private_key.minio_object_name (objects in the MinIO bucket '
-                f"'{self.bucket}'). Register the platform certificate before using "
-                f'secured OPC servers.'
-            ) from e
-        Path(self.cache_dir).mkdir(parents=True, exist_ok=True)
-        cert_path = await self._download(cert_object)
-        key_path = await self._download(key_object)
+    async def _download_all(
+        self, certificate_id: str, objects: tuple[tuple[str, str], ...]
+    ) -> tuple[str, str]:
+        folder = Path(self.cache_dir) / certificate_id
+        folder.mkdir(parents=True, exist_ok=True)
+        (cert_bucket, cert_object), (key_bucket, key_object) = objects
+        cert_path = await self._download(cert_bucket, cert_object, folder / 'cert')
+        key_path = await self._download(key_bucket, key_object, folder / 'key')
         return cert_path, key_path
 
-    async def _download(self, object_name: str) -> str:
-        data = await self.minio.download_file(object_name, self.bucket, self.metadata)
-        local_path = Path(self.cache_dir) / Path(object_name).name
+    async def _download(self, bucket: str, object_name: str, stem: Path) -> str:
+        data = await self.minio.download_file(object_name, bucket, self.metadata)
+        # The extension tells asyncua the format (.pem / .der)
+        local_path = stem.with_suffix(Path(object_name).suffix)
         # Atomic replace: a connection loading the previous file never sees it half-written.
         tmp_path = local_path.with_name(local_path.name + '.tmp')
         tmp_path.write_bytes(data)
@@ -72,43 +97,43 @@ class CertProvider:
 
 
 class LazyMinio:
-    """Builds the MinIO client on first use. MinioRepository's constructor hits the
-    network (bucket check), so building it eagerly would let a MinIO outage at pod
-    start take the whole read path down. Built lazily, only the servers that need a
-    certificate fail — and they are retried on the next loop."""
+    """Builds one MinIO client per bucket on first use. MinioRepository's constructor
+    hits the network (bucket check), so building it eagerly would let a MinIO outage at
+    pod start take the whole read path down. Built lazily, only the servers that need a
+    certificate fail — and they are retried on the next loop. One client per bucket,
+    because the constructor creates its bucket when missing: it is only ever given a
+    bucket a certificate names."""
 
     def __init__(self, factory):
         self._factory = factory
-        self._client = None
+        self._clients: dict[str, MinioRepository] = {}
 
     async def download_file(self, object_name: str, bucket: str, metadata: dict):
-        if self._client is None:
-            self._client = self._factory()
-        return await self._client.download_file(object_name, bucket, metadata)
+        if bucket not in self._clients:
+            self._clients[bucket] = self._factory(bucket)
+        return await self._clients[bucket].download_file(object_name, bucket, metadata)
 
 
 def build_cert_provider(
-    mongo, config, logger, notification_handler, metrics_controller, metadata=None
+    config, logger, notification_handler, metrics_controller, metadata=None
 ) -> CertProvider:
     """CertProvider shared by the read path (IngestorManager) and the write path
-    (GatewayRuntime): one certificate source — MinIO + Mongo — for every connection."""
+    (GatewayRuntime): one certificate cache for every connection."""
 
-    def minio_factory() -> MinioRepository:
+    def minio_factory(bucket: str) -> MinioRepository:
         return MinioRepository(
             endpoint=getenv('MINIO_ENDPOINT', 'localhost:9000'),
             access_key=getenv('MINIO_ACCESS_KEY', 'minioadmin'),
             secret_key=getenv('MINIO_SECRET_KEY', 'minioadmin'),
             secure=_env_bool('MINIO_SECURE', True),
-            bucket=config.cert_bucket,
+            bucket=bucket,
             logger=logger,
             notification_handler=notification_handler,
             metrics_controller=metrics_controller,
         )
 
     return CertProvider(
-        mongo=mongo,
         minio=LazyMinio(minio_factory),
         cache_dir=config.cert_cache_dir,
-        bucket=config.cert_bucket,
         metadata=metadata,
     )

ingestor/connection/pool.py

@@ -9,7 +9,7 @@ from sientia_do.observability.sientia_monitoring import SientiaMonitoring
 import ingestor.metrics as metrics
 from ingestor.connection.certs import CertProvider
 from ingestor.connection.clock import MonotonicClock
-from ingestor.connection.security import apply_security
+from ingestor.connection.security import apply_security, is_secured
 
 
 class OpcConnectionPool(SientiaMonitoring):
@@ -65,17 +65,26 @@ class OpcConnectionPool(SientiaMonitoring):
         """Warn when a caller asks for a server with other connection settings than
         the pooled client was opened with. The client is reused as is: reconnecting
         on every mismatch would let one malformed write command drop the reads.
-        Config changes from the slot evict the client first (ServerReader.shutdown)."""
+        Config changes from the slot (security, certificate) evict the client first:
+        the IngestorManager re-initializes the reader (ServerReader.shutdown)."""
         opened = self._configs.get(server_id, {})
-        diff = [
-            k for k in ('url', 'server_uri', 'use_security') if opened.get(k) != server_cfg.get(k)
-        ]
+        diff = [k for k in ('url', 'security', 'certificate') if opened.get(k) != server_cfg.get(k)]
         if diff:
             self.logger.warning(
                 f'OPC server {server_id}: reusing the pooled connection, but {diff} differ '
                 f'from the settings it was opened with'
             )
 
+    def config_for(self, server_id: str) -> dict | None:
+        """Connection settings of the pooled client for `server_id`, or None when the
+        server has no live pooled connection. Lets a writer reuse exactly the settings
+        the read path opened the connection with."""
+        server_id = str(server_id)
+        if server_id not in self._connections:
+            return None
+        cfg = self._configs.get(server_id)
+        return dict(cfg) if cfg is not None else None
+
     def _cached(self, server_id: str) -> Client | None:
         entry = self._connections.get(server_id)
         if entry is None:
@@ -88,10 +97,10 @@ class OpcConnectionPool(SientiaMonitoring):
         try:
             client = await self._connect(server_cfg)
         except Exception:
-            if server_cfg.get('use_security'):
+            if is_secured(server_cfg):
                 # The cached certificate may be the cause (replaced in MinIO,
                 # rejected by the server): download it again on the next attempt.
-                self.cert_provider.invalidate()
+                self.cert_provider.invalidate(server_cfg['certificate']['certificate_id'])
             await self.emit_metric(
                 metric_object=metrics.OPC_CONNECTIONS_FAILED,
                 tags={'pod_id': self.pod_id, 'server_name': server_id},
@@ -113,13 +122,12 @@ class OpcConnectionPool(SientiaMonitoring):
         pod_uri = self.pod_id.replace('-', ':')
         client.product_uri = pod_uri
         client.application_uri = pod_uri
-        server_uri = server_cfg.get('server_uri')
-        if server_uri:
-            # Must match the certificate's SAN URI (KEPServer: BadCertificateUriInvalid).
-            client.application_uri = server_uri
-        if server_cfg.get('use_security'):
-            cert, key = await self.cert_provider.fetch()
-            await apply_security(client, server_cfg.get('server_uri'), cert, key, None)
+        # Security only with a client certificate (SIENTIAPDE-1974 D5); apply_security
+        # sets the certificate's application URI, which must match its SAN URI.
+        if is_secured(server_cfg):
+            certificate = server_cfg['certificate']
+            cert, key = await self.cert_provider.fetch(certificate)
+            await apply_security(client, server_cfg['security'], certificate, cert, key)
         await client.connect()
         return client
 

ingestor/connection/security.py

@@ -1,17 +1,65 @@
-from asyncua.crypto.security_policies import SecurityPolicyBasic256Sha256
+from asyncua import ua
+from asyncua.crypto.security_policies import (
+    SecurityPolicyAes128Sha256RsaOaep,
+    SecurityPolicyAes256Sha256RsaPss,
+    SecurityPolicyBasic128Rsa15,
+    SecurityPolicyBasic256,
+    SecurityPolicyBasic256Sha256,
+)
 
 SESSION_TIMEOUT_MS = 600_000  # 10 min; tune per server (Samarco: long sessions degrade)
 
+# connectors.security.policy / .mode (SIENTIAPDE-1974 D4) to the asyncua classes
+POLICIES = {
+    'Basic256Sha256': SecurityPolicyBasic256Sha256,
+    'Aes128Sha256RsaOaep': SecurityPolicyAes128Sha256RsaOaep,
+    'Aes256Sha256RsaPss': SecurityPolicyAes256Sha256RsaPss,
+    'Basic256': SecurityPolicyBasic256,
+    'Basic128Rsa15': SecurityPolicyBasic128Rsa15,
+}
+MODES = {
+    'Sign': ua.MessageSecurityMode.Sign,
+    'SignAndEncrypt': ua.MessageSecurityMode.SignAndEncrypt,
+}
 
-async def apply_security(client, server_uri, cert_path, private_key_path, server_cert_path):
-    """Apply Basic256Sha256 + certificate auth (1879 §1) and set channel > session
-    lifetime (1879 §3: secure_channel_timeout = session_timeout * 1.25)."""
-    client.application_uri = server_uri
+
+class UnsupportedSecurityError(ValueError):
+    """The server's security mode or policy has no asyncua counterpart."""
+
+
+def is_secured(server_cfg: dict) -> bool:
+    """Whether a connection applies security: only with a client certificate (D5), and
+    not when its mode is 'None'. Without one, it connects without security, and a server
+    that requires a certificate refuses the connection."""
+    security = server_cfg.get('security') or {}
+    return server_cfg.get('certificate') is not None and security.get('mode') != 'None'
+
+
+async def apply_security(client, security, certificate, cert_path, private_key_path):
+    """Apply the server's mode + policy with the connector's client certificate, and set
+    channel > session lifetime (1879 §3: secure_channel_timeout = session_timeout * 1.25).
+
+    The application URI is the certificate's (its SAN URI): the server rejects a
+    different one (KEPServer: BadCertificateUriInvalid).
+
+    Raises:
+        UnsupportedSecurityError: When the mode or policy is unknown.
+    """
+    policy = POLICIES.get(security.get('policy'))
+    mode = MODES.get(security.get('mode'))
+    if policy is None or mode is None:
+        raise UnsupportedSecurityError(
+            f'Unsupported OPC security mode={security.get("mode")!r} '
+            f'policy={security.get("policy")!r} (modes: {", ".join(MODES)}; '
+            f'policies: {", ".join(POLICIES)})'
+        )
+    client.application_uri = certificate['application_uri']
     await client.set_security(
-        SecurityPolicyBasic256Sha256,
+        policy,
         certificate=cert_path,
         private_key=private_key_path,
-        server_certificate=server_cert_path,
+        server_certificate=None,
+        mode=mode,
     )
     client.session_timeout = SESSION_TIMEOUT_MS
     client.secure_channel_timeout = int(SESSION_TIMEOUT_MS * 1.25)

ingestor/connection/servers.py

@@ -0,0 +1,126 @@
+"""Connection settings of the OPC server a write command targets (SIENTIAPDE-1975 GW1).
+
+The Laborious only knows the `server_id` of a write tag (pipeline `write_tags`); the
+connection (url, security, certificate) belongs to the gateway, which owns every OPC
+session. A server already in the pool is written through that connection. Otherwise it
+is resolved from the tag database (`connectors` → `opc_certificates`) with the rule the
+Orchestrator uses to build the read slots (SIENTIAPDE-1974 D1), in the slot format.
+"""
+
+from typing import Any
+
+from sientia_do.observability.logger import Logger
+
+from ingestor.connection.certificates import (
+    CERTIFICATE_LOOKUP,
+    client_certificate_id,
+    has_security,
+    resolve_certificate,
+)
+from ingestor.connection.clock import MonotonicClock
+from ingestor.connection.pool import OpcConnectionPool
+
+CONNECTORS = 'connectors'
+
+
+def _connector_pipeline(server_id: str) -> list[dict[str, Any]]:
+    """The active OPC UA connector `server_id` (connector_id is its slug), with its
+    certificate. Only the fields used are projected."""
+    return [
+        {'$match': {'connector_id': server_id, 'type': 'opc_ua', 'status': 'Active'}},
+        {'$limit': 1},
+        CERTIFICATE_LOOKUP,
+        {
+            '$project': {
+                '_id': 0,
+                'connector_id': 1,
+                'url': 1,
+                'subscription_period_ms': 1,
+                'security.mode': 1,
+                'security.policy': 1,
+                'security.client_certificate_id': 1,
+                'certificates': 1,
+            }
+        },
+    ]
+
+
+class ServerConfigResolver:
+    """Resolve and cache the connection settings of an OPC server by `server_id`.
+
+    Order: the live pooled connection (what the read path opened, so writes never fight
+    the reads over settings), then MongoDB. Lookups are cached for `ttl_s`; a server
+    that is not found, for `missing_ttl_s`, so a pipeline pointing at a removed server
+    does not query MongoDB on every command.
+
+    # ponytail: the MongoDB fallback goes away once write commands are routed to the pod
+    # that owns the connection (SIENTIAPDE-1974 D1, new card).
+    """
+
+    def __init__(
+        self,
+        pool: OpcConnectionPool,
+        mongo,
+        logger: Logger,
+        ttl_s: float = 60.0,
+        missing_ttl_s: float = 10.0,
+        metadata: dict | None = None,
+    ):
+        self.pool = pool
+        self.mongo = mongo
+        self.logger = logger
+        self.ttl_s = ttl_s
+        self.missing_ttl_s = missing_ttl_s
+        self.metadata = metadata or {}
+        self.clock = MonotonicClock()
+        self._cache: dict[str, tuple[dict[str, Any] | None, float]] = {}
+
+    async def resolve(self, server_id: str) -> dict[str, Any] | None:
+        """Connection settings for `server_id`, or None when no source knows it.
+
+        Raises:
+            Exception: When MongoDB cannot be read (the caller reports the write as
+                failed).
+        """
+        server_id = str(server_id)
+        pooled = self.pool.config_for(server_id)
+        if pooled is not None:
+            return pooled
+        now = self.clock.elapsed()
+        cached = self._cache.get(server_id)
+        if cached is not None:
+            cfg, cached_at = cached
+            if now - cached_at < (self.ttl_s if cfg is not None else self.missing_ttl_s):
+                return dict(cfg) if cfg is not None else None
+        cfg = await self._lookup(server_id)
+        self._cache[server_id] = (cfg, now)
+        return dict(cfg) if cfg is not None else None
+
+    async def _lookup(self, server_id: str) -> dict[str, Any] | None:
+        connectors = await self.mongo.aggregate(
+            CONNECTORS, _connector_pipeline(server_id), self.metadata
+        )
+        connector = connectors[0] if connectors else None
+        if connector is None or not connector.get('url') or not has_security(connector):
+            self.logger.warning(
+                f'OPC server {server_id} not found, not active or incomplete (url, '
+                f'security.mode, security.policy) in {CONNECTORS}'
+            )
+            return None
+        certificate = resolve_certificate(connector)
+        if certificate is None and client_certificate_id(connector) is not None:
+            self.logger.warning(
+                f'OPC server {server_id}: client_certificate_id '
+                f'{client_certificate_id(connector)} has no active client certificate in '
+                f'opc_certificates; connecting without security'
+            )
+        return {
+            'server_id': server_id,
+            'url': connector['url'],
+            'subscription_period_ms': connector.get('subscription_period_ms'),
+            'security': {
+                'mode': connector['security']['mode'],
+                'policy': connector['security']['policy'],
+            },
+            'certificate': certificate,
+        }

ingestor/engines/write.py

@@ -18,6 +18,7 @@ from sientia_do.observability.sientia_monitoring import SientiaMonitoring
 import ingestor.metrics as metrics
 from ingestor.connection.clock import MonotonicClock
 from ingestor.connection.pool import OpcConnectionPool
+from ingestor.connection.servers import ServerConfigResolver
 from ingestor.converters import ConversionError, to_typed_value
 from ingestor.io.data_sink import DataSink
 
@@ -77,9 +78,13 @@ class WriteEngine(SientiaMonitoring):
         write_timestamp: bool = True,
         write_quality: bool = True,
         min_pause_s: float = 0.0,
+        servers: ServerConfigResolver | None = None,
     ):
         self.pool = pool
         self.sink = sink
+        # Resolves the server connection by server_id (SIENTIAPDE-1975 GW1). Without it,
+        # no server is known and every write fails as server_not_found.
+        self.servers = servers
         self.write_timestamp = write_timestamp
         self.write_quality = write_quality
         self.min_pause_s = min_pause_s
@@ -105,11 +110,24 @@ class WriteEngine(SientiaMonitoring):
         except ConversionError as e:
             return await self._emit_error(cmd, 'conversion', str(e), 'error')
 
-        dv = self._build_datavalue(cmd, typed)
+        try:
+            dv = self._build_datavalue(cmd, typed)
+        except (KeyError, TypeError, ValueError) as e:
+            # write_timestamp on with a missing or non-ISO timestamp.
+            return await self._emit_error(cmd, 'bad_timestamp', repr(e), 'error')
+
+        try:
+            server_cfg = await self._server_cfg(cmd)
+        except Exception as e:
+            return await self._emit_error(cmd, 'server_lookup', str(e), 'error')
+        if server_cfg is None:
+            return await self._emit_error(
+                cmd, 'server_not_found', f'OPC server {cmd["server_id"]} is not configured', 'error'
+            )
 
         start = self.clock.elapsed()
         try:
-            client = await self.pool.get(cmd['server_id'], self._server_cfg(cmd))
+            client = await self.pool.get(cmd['server_id'], server_cfg)
             node = client.get_node(cmd['addr'])
             await node.write_value(dv)
         except Exception as e:
@@ -127,15 +145,13 @@ class WriteEngine(SientiaMonitoring):
                 now = self.clock.elapsed()
         self._last_write_at = now
 
-    def _server_cfg(self, cmd: dict) -> dict:
-        # ponytail: minimal cfg built straight from the C2 message. Resolving
-        # the full connector config (url/security) from the connectors DB by
-        # server_id is F4 wiring, not this task — pool is mocked in tests.
-        return {
-            'url': cmd.get('url'),
-            'use_security': cmd.get('use_security', False),
-            'server_uri': cmd.get('server_uri'),
-        }
+    async def _server_cfg(self, cmd: dict) -> dict | None:
+        """Connection settings of the target server, resolved by server_id (live pooled
+        connection, then connectors → opc_certificates). The command carries only the
+        server_id (C2)."""
+        if self.servers is None:
+            return None
+        return await self.servers.resolve(str(cmd['server_id']))
 
     def _variant_type(self, data_type: str) -> ua.VariantType:
         # direct index: unknown dtypes already became ConversionError in to_typed_value
@@ -156,6 +172,12 @@ class WriteEngine(SientiaMonitoring):
         return isinstance(exc, UaStatusCodeError) and type(exc).__name__ in _SESSION_BAD_NAMES
 
     async def _emit_error(self, cmd: dict, error_type: str, message: str, status: str):
+        # The reason only lives here: the row gets write_status alone (SIENTIAPDE-1975).
+        self.logger.error(
+            f'OPC write failed ({status}, {error_type}): server={cmd.get("server_id")} '
+            f'addr={cmd.get("addr")} model_id={cmd.get("model_id")} '
+            f'timestamp={cmd.get("timestamp")}: {message}'
+        )
         tags = {'pod_id': self.pod_id, 'server_name': cmd.get('server_id', 'unknown')}
         await self.emit_metric(
             metric_object=metrics.OPC_ERROR_BY_TYPE, tags={**tags, 'error_type': error_type}
@@ -164,6 +186,17 @@ class WriteEngine(SientiaMonitoring):
             metric_object=metrics.OPC_WRITE_TOTAL,
             tags={**tags, 'model_id': cmd.get('model_id', 'unknown'), 'result': 'error'},
         )
+        # Same series as a success (status='ok'), so it always shows the last outcome.
+        await self.emit_metric(
+            metric_object=metrics.OPC_WRITE_STATUS_BY_MODEL,
+            method='set',
+            value=0,
+            tags={
+                'pod_id': self.pod_id,
+                'model_id': cmd.get('model_id', 'unknown'),
+                'status': 'ok',
+            },
+        )
         result = WriteResult(ok=False, status=status, opc_status_code=error_type, message=message)
         await self.sink.update_write_status(cmd, result)
         return result

ingestor/gateway_runtime.py

@@ -2,8 +2,8 @@
 object graph and wires it into the app's lifecycle.
 
 Reuses the existing ingestor's logger/notification_handler/metrics_controller and
-its already-connected DataManager. The OpcConnectionPool (and its CertProvider,
-MinIO + Mongo) belongs to the read path in IngestorManager (SIENTIAPDE-1974):
+its already-connected DataManager. The OpcConnectionPool (and its CertProvider, which
+downloads each server's client certificate from MinIO) belongs to the read path in IngestorManager (SIENTIAPDE-1974):
 reads start in prepare_ingestor, before this runtime exists, and must keep running
 if anything here fails. The runtime only borrows the pool for writes and gRPC.
 
@@ -22,6 +22,7 @@ from ingestor.adapters.grpc_server import GrpcServer
 from ingestor.adapters.nats_consumer import NatsWriteConsumer
 from ingestor.config import GatewayConfig
 from ingestor.connection.pool import OpcConnectionPool
+from ingestor.connection.servers import ServerConfigResolver
 from ingestor.engines.active_read import ActiveReadEngine
 from ingestor.engines.write import WriteEngine
 from ingestor.io.data_sink import DataSink
@@ -61,6 +62,13 @@ class GatewayRuntime(SientiaMonitoring):
         )
         self.sink = DataSink(data_manager, postgres)
 
+        # Write commands carry only the server_id (SIENTIAPDE-1975): the connection is
+        # resolved here, from the live pooled connection or the connectors →
+        # opc_certificates documents, with the rule the orchestrator uses for the read
+        # slots (SIENTIAPDE-1974 D1).
+        self.servers = ServerConfigResolver(
+            self.pool, data_manager.mongo_repository, logger, metadata=self.metadata
+        )
         self.write_engine = WriteEngine(
             self.pool,
             self.sink,
@@ -70,6 +78,7 @@ class GatewayRuntime(SientiaMonitoring):
             write_timestamp=config.write_timestamp,
             write_quality=config.write_quality,
             min_pause_s=config.write_min_pause_s,
+            servers=self.servers,
         )
         self.nats_consumer = NatsWriteConsumer(
             config.nats_url,
@@ -110,6 +119,11 @@ class GatewayRuntime(SientiaMonitoring):
 
     async def idle_sweep(self) -> None:
         await self.pool.release_idle(self.config.idle_conn_max_s)
+        if self._nats_started and self.nats_consumer.closed:
+            # Reconnection is unbounded once connected; a closed connection means it
+            # was closed for good (e.g. by the server), so subscribe again.
+            self.logger.warning('GatewayRuntime: NATS connection closed; starting again')
+            self._nats_started = False
         if not self._nats_started:
             await self._start_nats()
 

ingestor/io/data_sink.py

@@ -1,6 +1,7 @@
+import asyncio
 import re
 
-from sqlalchemy import text
+from sqlalchemy import Select, Update, case, column, select, table, update
 
 import ingestor.metrics as metrics
 
@@ -8,6 +9,34 @@ import ingestor.metrics as metrics
 # match before a trailing '\n', which is not what we want for a SQL identifier.
 _IDENTIFIER_RE = re.compile(r'\w+', re.ASCII)
 
+# Worst-wins precedence of predictions.write_status (SIENTIAPDE-1975), from best to worst;
+# NULL, 'pending' and unknown values rank 0. The gateway is the only writer that updates the
+# column: the Laborious only sets the value of the rows it inserts ('pending', PI outcome).
+STATUS_RANK = {'ok': 1, 'error': 2, 'session_bad': 3}
+
+
+def write_status_statements(
+    schema: str, table_name: str, status: str, timestamp, model_id
+) -> tuple[Update, Select]:
+    """The UPDATE that records `status` unless the row has a worse one, and the SELECT that
+    tells whether the row exists. Built with SQLAlchemy Core: identifiers and values are
+    never formatted into the SQL text."""
+    predictions = table(
+        table_name,
+        column('write_status'),
+        column('timestamp'),
+        column('model_id'),
+        schema=schema,
+    )
+    row = (predictions.c.timestamp == timestamp) & (predictions.c.model_id == model_id)
+    current_rank = case(STATUS_RANK, value=predictions.c.write_status, else_=0)
+    return (
+        update(predictions)
+        .where(row, current_rank <= STATUS_RANK.get(status, 0))
+        .values(write_status=status),
+        select(1).select_from(predictions).where(row),
+    )
+
 
 class DataSink:
     """Gateway egress wrapper: fans a reading out to every configured name/collection."""
@@ -23,14 +52,16 @@ class DataSink:
     async def publish_reading(self, tag: str, value, timestamp, names: list[dict]) -> None:
         """Publish one MongoDB document per name entry and record its tag value metric.
 
-        `model_id` is only written when the name carries one: names converted from a
-        slot v1 have none, and their documents must stay identical to the legacy ones."""
+        Every name of the slot v2 carries collection, tag_name and model_id (parse_slot
+        checks it)."""
         for name in names:
-            doc = {'tag': tag, 'name': name['tag_name']}
-            if 'model_id' in name:
-                doc['model_id'] = name['model_id']
-            doc['timestamp'] = timestamp
-            doc['value'] = value
+            doc = {
+                'tag': tag,
+                'name': name['tag_name'],
+                'model_id': name['model_id'],
+                'timestamp': timestamp,
+                'value': value,
+            }
             await self.data_manager.publish(name['collection'], doc)
             await self.emit_metric(
                 metric_object=metrics.OPC_TAG_VALUE,
@@ -39,37 +70,76 @@ class DataSink:
                 tags={
                     'pod_id': self.data_manager.pod_id,
                     'tag_name': name['tag_name'],
-                    'model_id': name.get('model_id', ''),
+                    'model_id': name['model_id'],
                 },
             )
 
-    async def update_write_status(self, cmd: dict, result) -> None:  # NOSONAR
-        """UPDATE the per-model prediction row's write_status (C3), by timestamp+model_id.
+    async def update_write_status(self, cmd: dict, result) -> str:
+        """Record a write outcome on the prediction row (C3), keeping the worst one.
 
-        schema/table_name are per-model SQL identifiers, not values — they can't be
-        bound params, so they're checked against an allowlist before interpolation.
-        status/timestamp/model_id ARE bound params, never f-stringed.
+        The row is found by timestamp + model_id. A prediction is written to several
+        tags, each answered by its own command, so a better outcome never replaces a
+        worse one: ``ok`` < ``error`` < ``session_bad``, and ``pending``/NULL are
+        replaced by any answer, so the order of the answers does not matter. Only the
+        gateway updates the column (SIENTIAPDE-1975): the Laborious publishes the commands
+        and sets ``pending`` (merged with its PI Web API outcome) on the row it inserts.
+
+        Never raises: a failure here must not reach the NATS callback nor hide the OPC
+        write itself, which already happened. The outcome is logged and counted instead.
+
+        Return:
+            str: ``updated``, ``kept`` (the row already has a worse outcome),
+            ``row_not_found`` (e.g. the Laborious INSERT failed), ``invalid`` (bad or
+            missing schema/table/timestamp/model_id) or ``error``.
         """
-        schema = self._validate_identifier(cmd['schema'])
-        table = self._validate_identifier(cmd['table_name'])
-        # schema/table are allowlist-validated identifiers above; status/timestamp/model_id
-        # are bound params below, never interpolated — not a real injection vector.
-        stmt = text(
-            f'UPDATE {schema}.{table} SET write_status = :status '  # noqa: S608 # nosec B608
-            'WHERE timestamp = :timestamp AND model_id = :model_id'
+        try:
+            schema = self._validate_identifier(cmd.get('schema'))
+            table = self._validate_identifier(cmd.get('table_name'))
+            if cmd.get('timestamp') is None or cmd.get('model_id') is None:
+                raise ValueError('missing timestamp or model_id')
+        except ValueError as e:
+            return await self._status_outcome('invalid', cmd, f'write_status not recorded: {e}')
+
+        statements = write_status_statements(
+            schema, table, result.status, cmd['timestamp'], cmd['model_id']
         )
-        params = {
-            'status': result.status,
-            'timestamp': cmd['timestamp'],
-            'model_id': cmd['model_id'],
-        }
-        # ponytail: sync engine call inside async def — same pattern sientia_do's own
-        # Postgres activities use (e.g. export_data_to_postgres); no async pg driver here.
+        try:
+            # The engine is synchronous (no async pg driver here): run it off the event
+            # loop, which also serves the subscriptions of the read path.
+            outcome = await asyncio.to_thread(self._update_sync, *statements)
+        except Exception as e:
+            return await self._status_outcome('error', cmd, f'write_status UPDATE failed: {e}')
+        detail = {
+            'updated': f'write_status={result.status} recorded',
+            'kept': f'write_status={result.status} not recorded: the row has a worse outcome',
+            'row_not_found': f'write_status={result.status} not recorded: no prediction row',
+        }[outcome]
+        return await self._status_outcome(outcome, cmd, detail)
+
+    def _update_sync(self, update_stmt: Update, exists_stmt: Select) -> str:
         with self.postgres.engine.begin() as connection:
-            connection.execute(stmt, params)
+            if connection.execute(update_stmt).rowcount:
+                return 'updated'
+            row = connection.execute(exists_stmt).first()
+        return 'kept' if row is not None else 'row_not_found'
+
+    async def _status_outcome(self, outcome: str, cmd: dict, detail: str) -> str:
+        message = (
+            f'{detail} (server={cmd.get("server_id")} addr={cmd.get("addr")} '
+            f'model_id={cmd.get("model_id")} timestamp={cmd.get("timestamp")})'
+        )
+        if outcome in ('updated', 'kept'):
+            self.data_manager.logger.debug(message)
+        else:
+            self.data_manager.logger.warning(message)
+        await self.emit_metric(
+            metric_object=metrics.OPC_WRITE_STATUS_UPDATE_TOTAL,
+            tags={'pod_id': self.data_manager.pod_id, 'result': outcome},
+        )
+        return outcome
 
     @staticmethod
-    def _validate_identifier(name: str) -> str:
+    def _validate_identifier(name: object) -> str:
         if not isinstance(name, str) or not _IDENTIFIER_RE.fullmatch(name):
             raise ValueError(f'invalid SQL identifier: {name!r}')
         return name

ingestor/io/slots.py

@@ -1,28 +1,27 @@
-"""Parse the slot written by the Orchestrator to Redis into the slot v2 structure (contract C1).
+"""Parse the slot v2 the Orchestrator writes to Redis (contract C1, SIENTIAPDE-1974).
 
-Both shapes are accepted so the gateway and the Orchestrator can be deployed in
-any order (SIENTIAPDE-1974):
-
-- v2: each tag carries `names` (one entry per collection / tag name / model);
-- v1 (legacy): each tag carries `tag_name` + `topics`, and the server carries the
-  file-based `cert_path`. v1 is converted to v2: one `names` entry per topic, and
-  `use_security` is true when the server had a certificate path (the certificate
-  itself now always comes from MinIO via CertProvider, never from that path).
+Each server carries its connection (`url`, `subscription_period_ms`), its OPC security
+(`security`: mode + policy) and its client certificate (`certificate`: certificate_id,
+application_uri and the MinIO objects of the cert and the private key; None = connect
+without security, D5). Each tag carries `names`: one entry per collection / tag name /
+model the reading is written to.
 """
 
-SERVER_FIELDS = ('server_id', 'url', 'server_uri', 'use_security', 'subscription_period_ms')
+SERVER_FIELDS = ('server_id', 'url', 'subscription_period_ms', 'security', 'certificate')
 # What a connection/subscription needs (the pool keys clients by server_id itself).
 CONNECTION_FIELDS = tuple(f for f in SERVER_FIELDS if f != 'server_id')
+NAME_FIELDS = ('collection', 'tag_name', 'model_id')
 
 
 def _parse_names(address: str, tag: dict) -> list[dict]:
     names = tag.get('names')
-    if names:
-        return names
-    topics = tag.get('topics')
-    if topics and tag.get('tag_name'):
-        return [{'collection': topic, 'tag_name': tag['tag_name']} for topic in topics]
-    raise ValueError(f'tag {address!r} has no names')
+    if not names:
+        raise ValueError(f'tag {address!r} has no names')
+    for name in names:
+        missing = [field for field in NAME_FIELDS if field not in name]
+        if missing:
+            raise ValueError(f'tag {address!r} has a name without {missing}')
+    return names
 
 
 def _parse_tag(address: str, tag: dict) -> dict:
@@ -34,14 +33,19 @@ def _parse_tag(address: str, tag: dict) -> dict:
 
 
 def _parse_server(name: str, server: dict) -> dict:
-    parsed = {field: server[field] for field in SERVER_FIELDS if field in server}
+    if not isinstance(server.get('security'), dict):
+        raise ValueError(f'server {name!r} has no security')
+    parsed = {field: server.get(field) for field in SERVER_FIELDS}
     parsed['name'] = server.get('name', name)
-    if 'use_security' not in parsed:
-        parsed['use_security'] = bool(server.get('cert_path'))
     parsed['tags'] = {addr: _parse_tag(addr, tag) for addr, tag in server['tags'].items()}
     return parsed
 
 
 def parse_slot(raw: dict) -> dict:
-    """Normalize a raw slot (v1 or v2) into `{server_name: {..., tags: {addr: tag}}}`."""
+    """Normalize a raw slot v2 into `{server_name: {..., tags: {addr: tag}}}`.
+
+    Raises:
+        KeyError | TypeError | ValueError: When the slot is not a valid slot v2 (e.g. a
+            slot v1 with `topics`).
+    """
     return {name: _parse_server(name, server) for name, server in raw.items()}

ingestor/managers/ingestor_manager.py

@@ -1,6 +1,5 @@
 import traceback
 from copy import deepcopy
-from os import getenv
 
 from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
 from sientia_do.notifications.models import NotificationLevel
@@ -15,16 +14,9 @@ from ingestor.connection.pool import OpcConnectionPool
 from ingestor.io.data_sink import DataSink
 from ingestor.io.slots import parse_slot
 from ingestor.managers.data_manager import DataManager
-from ingestor.managers.opc_manager import OpcManager
 from ingestor.managers.resource_manager import ResourceManager
 from ingestor.managers.server_reader import ServerReader
 
-# READ_ENGINE (SIENTIAPDE-1974): 'v2' = ServerReader/SubscriptionEngine over the shared
-# pool, certificate from MinIO (default). 'legacy' = plan B: the untouched rc3
-# OpcManager, slot v1 only, certificate files from the Gitea clone (cert_path). Kept
-# for validation until the end of 1974; remove once unused and the tests pass without it.
-READ_ENGINES = ('v2', 'legacy')
-
 
 class IngestorManager(SientiaMonitoring):
     """
@@ -85,7 +77,6 @@ class IngestorManager(SientiaMonitoring):
         notification_handler: NotificationHandler,
         metrics_controller: MetricsController,
         gateway_config: GatewayConfig | None = None,
-        read_engine: str | None = None,
     ):
         redis_host: str = redis_data['host']
         redis_port: int = int(redis_data['port'])
@@ -108,12 +99,12 @@ class IngestorManager(SientiaMonitoring):
             metrics_controller=metrics_controller,
         )
         self.opc_managers: dict = {}
-        # Read path (SIENTIAPDE-1974): pooled connections with the certificate from
-        # MinIO. Nothing here touches the network at construction (MinIO is lazy), so
-        # a MinIO/Postgres/NATS outage can't stop the reads before they start.
+        # Read path (SIENTIAPDE-1974): pooled connections with each server's client
+        # certificate (named in the slot) from MinIO. Nothing here touches the network at
+        # construction (MinIO is lazy), so a MinIO/Postgres/NATS outage can't stop the
+        # reads before they start.
         config = gateway_config or GatewayConfig.certs_from_env()
         self.cert_provider = build_cert_provider(
-            mongo=self.data_manager.mongo_repository,
             config=config,
             logger=logger,
             notification_handler=notification_handler,
@@ -124,10 +115,6 @@ class IngestorManager(SientiaMonitoring):
             self.cert_provider, logger, notification_handler, metrics_controller
         )
         self.sink = DataSink(self.data_manager, None)
-        self._server_cert_warned: set[str] = set()
-        self.read_engine = self._resolve_read_engine(
-            read_engine or getenv('READ_ENGINE') or 'v2', logger
-        )
         self.resource_manager = ResourceManager(
             host=redis_host,
             port=redis_port,
@@ -147,32 +134,7 @@ class IngestorManager(SientiaMonitoring):
 
         self.metadata = metadata
 
-    @staticmethod
-    def _resolve_read_engine(value: str, logger: Logger) -> str:
-        engine = value.strip().lower()
-        if engine not in READ_ENGINES:
-            logger.warning(f'Invalid READ_ENGINE {value!r}, using v2 ({"|".join(READ_ENGINES)})')
-            engine = 'v2'
-        logger.info(f'OPC read engine: {engine}')
-        return engine
-
-    def _build_reader(self, server_config: dict) -> ServerReader | OpcManager:
-        if self.read_engine == 'legacy':
-            # Plan B: the rc3 OpcManager, unchanged (own connection, cert files).
-            return OpcManager(
-                name=server_config['name'],
-                url=server_config['url'],
-                subscription_period_ms=server_config['subscription_period_ms'],
-                data_manager=self.data_manager,
-                logger=self.logger,
-                server_uri=server_config['server_uri'],
-                notification_handler=self.notification_handler,
-                metadata=self.metadata,
-                cert_path=server_config.get('cert_path'),
-                private_key_path=server_config.get('private_key_path'),
-                server_cert_path=server_config.get('server_cert_path'),
-                metrics_controller=self.metrics_controller,
-            )
+    def _build_reader(self, server_config: dict) -> ServerReader:
         return ServerReader(
             name=server_config['name'],
             server_config=server_config,
@@ -184,24 +146,21 @@ class IngestorManager(SientiaMonitoring):
             metadata=self.metadata,
         )
 
-    async def initialize_opc_from_config(
-        self, server_config: dict
-    ) -> ServerReader | OpcManager | None:
+    async def initialize_opc_from_config(self, server_config: dict) -> ServerReader | None:
         """
         Initializes the reader of one OPC UA server from its slot configuration.
 
-        With READ_ENGINE=v2 (default) creates a ServerReader and opens its pooled
-        connection; with `use_security`, the certificate comes from MinIO. With
-        READ_ENGINE=legacy (plan B) creates the rc3 OpcManager, which connects on its
-        own with the certificate files of the slot v1 (`cert_path`).
+        Creates a ServerReader and opens its pooled connection. With a `certificate`, the
+        connection uses the slot's security mode and policy, with the certificate
+        downloaded from MinIO; without one, it connects without security (D5).
 
         Args:
-            server_config (dict): The server configuration of the slot, without the
-                'tags' key. v2: 'name', 'server_id', 'url', 'server_uri',
-                'use_security', 'subscription_period_ms'. legacy: the slot v1 fields.
+            server_config (dict): The server configuration of the slot v2, without the
+                'tags' key: 'name', 'server_id', 'url', 'subscription_period_ms',
+                'security' and 'certificate'.
 
         Returns:
-            ServerReader | OpcManager | None: The connected reader, or None if the
+            ServerReader | None: The connected reader, or None if the
             connection fails (logged and notified, so the other servers keep working).
         """
 
@@ -254,11 +213,7 @@ class IngestorManager(SientiaMonitoring):
                 the shared connection stays for writes/gRPC until the idle sweep.
         """
         if server in self.opc_managers:
-            if self.read_engine == 'legacy':
-                # OpcManager owns its connection: shutdown always disconnects it.
-                await self.opc_managers[server].shutdown()
-            else:
-                await self.opc_managers[server].shutdown(evict=evict)
+            await self.opc_managers[server].shutdown(evict=evict)
             del self.opc_managers[server]
         for slot, _config in self.managed_tags.items():
             self.managed_tags[slot].pop(server, None)
@@ -567,14 +522,11 @@ class IngestorManager(SientiaMonitoring):
             if slot in reader.subscriptions:
                 await self._unsubscribe_reader(server, reader, slot)
 
-    async def _unsubscribe_reader(
-        self, server: str, reader: ServerReader | OpcManager, slot: str
-    ) -> None:
+    async def _unsubscribe_reader(self, server: str, reader: ServerReader, slot: str) -> None:
         """
         Unsubscribe one reader from a slot without letting a failure stop the main loop.
 
-        A failure (e.g. the legacy OpcManager, whose delete() raises when the server
-        session is gone) increments OPC_SUBSCRIPTION_ERRORS, sends
+        A failure (e.g. delete() raising when the server session is gone) increments OPC_SUBSCRIPTION_ERRORS, sends
         OPC_UNSUBSCRIBE_ERROR_<slot>:<server> and is logged. The slot is dropped from the
         reader's books, as the v2 engine already does, so it can be subscribed again.
 
@@ -584,7 +536,7 @@ class IngestorManager(SientiaMonitoring):
 
         Args:
             server (str): The reader's key in opc_managers
-            reader (ServerReader | OpcManager): The OPC reader
+            reader (ServerReader): The OPC reader
             slot (str): The slot to unsubscribe
         """
         try:
@@ -664,22 +616,17 @@ class IngestorManager(SientiaMonitoring):
 
     def parse_slot_config(self, slot: str, raw: dict) -> dict | None:
         """
-        Normalizes the raw slot read from Redis to the slot v2 structure.
+        Normalizes the raw slot read from Redis to the slot v2 structure (contract C1).
 
-        Accepts slot v1 (`topics`) and v2 (`names`), so the gateway and the
-        Orchestrator can be deployed in any order (SIENTIAPDE-1974). With
-        READ_ENGINE=legacy the raw slot v1 is kept as is (what OpcManager reads), and
-        a slot v2 is rejected.
+        Only the slot v2 is accepted (SIENTIAPDE-1974): the gateway and the Orchestrator
+        are deployed together, and a slot v1 (`topics`, no `security`) is rejected.
 
         Returns:
             dict | None: The parsed slot, or None when the config is malformed
             (logged and notified).
         """
         try:
-            if self.read_engine == 'legacy':
-                self._validate_slot_v1(raw)
-                return raw
-            parsed = parse_slot(raw)
+            return parse_slot(raw)
         except (AttributeError, KeyError, TypeError, ValueError) as e:
             self.send_notification(
                 metadata=self.metadata,
@@ -690,32 +637,6 @@ class IngestorManager(SientiaMonitoring):
             )
             self.logger.error(f'Slot {slot} has an invalid configuration: {e!r}')
             return None
-        self._warn_server_cert_path(raw)
-        return parsed
-
-    @staticmethod
-    def _validate_slot_v1(raw: dict) -> None:
-        """READ_ENGINE=legacy: OpcManager only understands slot v1 (`tag_name` +
-        `topics` per tag); a v2 slot (`names`) would fail in its datachange callback."""
-        for name, server in raw.items():
-            for address, tag in server['tags'].items():
-                if 'topics' not in tag or 'tag_name' not in tag or 'frequency' not in tag:
-                    raise ValueError(
-                        f'READ_ENGINE=legacy needs a slot v1 (tag_name + topics); '
-                        f'server {name!r}, tag {address!r} is not'
-                    )
-
-    def _warn_server_cert_path(self, raw: dict) -> None:
-        """Logs once per server when a slot still pins a server certificate
-        (`server_cert_path`): connections now come from the pool with the platform
-        certificate from MinIO, and that file-based pin is no longer applied."""
-        for name, server in raw.items():
-            if server.get('server_cert_path') and name not in self._server_cert_warned:
-                self._server_cert_warned.add(name)
-                self.logger.warning(
-                    f'OPC server {name}: server_cert_path is set in the slot but is no '
-                    f'longer applied (server certificate validation is disabled)'
-                )
 
     async def drop_slot_leases(self, ids: list[str]) -> None:
         """

ingestor/managers/opc_manager.py

@@ -1,588 +0,0 @@
-import asyncio
-import json
-import traceback
-from pathlib import Path
-
-from asyncua import Client
-from asyncua.crypto.security_policies import SecurityPolicyBasic256
-from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
-from sientia_do.notifications.models import NotificationLevel
-from sientia_do.observability.logger import Logger
-from sientia_do.observability.metrics_controller import MetricsController
-from sientia_do.observability.sientia_monitoring import SientiaMonitoring
-from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ, OPC_TIMEZONE
-
-import ingestor.metrics as metrics
-from ingestor.managers.data_manager import DataManager
-
-
-class OpcManager(SientiaMonitoring):
-    """
-    Manages OPC UA server connections and tag subscriptions.
-
-    The OpcManager is responsible for:
-    - Establishing and maintaining secure connections to OPC UA servers
-    - Managing tag subscriptions and data collection
-    - Handling server reconnection and error recovery
-    - Processing OPC data and forwarding it to the data manager
-    - Monitoring connection health and performance metrics
-
-    The manager supports both secure and unsecured connections, with optional
-    certificate-based authentication for enhanced security.
-
-    Args:
-        name (str): Unique identifier for the OPC server
-        url (str): OPC UA server endpoint URL
-        data_manager (DataManager): Manager for data persistence and export
-        logger (Logger): Logger instance for application logging
-        server_uri (str): OPC UA server application URI
-        notification_handler (NotificationHandler): Handler for sending notifications
-        metadata (dict): Application metadata for notifications and tracking
-        cert_path (str, optional): Path to client certificate file for secure connections
-        private_key_path (str, optional): Path to client private key file
-        server_cert_path (str, optional): Path to server certificate file for validation
-
-    Attributes:
-        url (str): OPC UA server endpoint URL
-        name (str): Unique identifier for the OPC server
-        server_uri (str): OPC UA server application URI
-        data_queue (dict): Queue for buffering OPC data before processing
-        non_receive_count (int): Counter for cycles without data reception
-        client (Client): OPC UA client instance
-        cert_path (str): Path to client certificate file
-        private_key_path (str): Path to client private key file
-        server_cert_path (str): Path to server certificate file
-        nodes (dict): Dictionary of OPC node references
-        subscriptions (dict): Active OPC subscriptions
-        data_manager (DataManager): Manager for data persistence and export
-        metadata (dict): Application metadata
-    """
-
-    def __init__(
-        self,
-        name: str,
-        url: str,
-        subscription_period_ms: int,
-        data_manager: DataManager,
-        logger: Logger,
-        server_uri: str,
-        notification_handler: NotificationHandler,
-        metrics_controller: MetricsController,
-        metadata: dict,
-        cert_path: str | None = None,
-        private_key_path: str | None = None,
-        server_cert_path: str | None = None,
-    ):
-        self.url = url
-        self.name = name
-        self.server_uri = server_uri
-        self.data_queue: dict = {}
-        self.non_receive_count = 0
-        self.client: Client | None = None
-        self.subscription_period_ms = subscription_period_ms
-        self.cert_path = cert_path
-        self.private_key_path = private_key_path
-        self.server_cert_path = server_cert_path
-        self.nodes: dict = {}
-        self.subscriptions: dict = {}
-        self.data_manager = data_manager
-        self.metadata = metadata
-
-        SientiaMonitoring.__init__(
-            self,
-            logger=logger,
-            notification_handler=notification_handler,
-            metrics_controller=metrics_controller,
-        )
-
-        metrics.OPC_CONNECTION_STATUS.labels(
-            pod_id=self.pod_id, server_name=self.name, server_url=self.url
-        ).set(0)
-        metrics.OPC_TAGS_SUBSCRIBED.labels(pod_id=self.pod_id, server_name=self.name).set(0)
-
-    def __str__(self):
-        """
-        String representation of the OPC Manager.
-
-        Returns:
-            str: Human-readable representation showing server details and current state.
-        """
-        return (
-            f'OpcManager(name={self.name}, url={self.url}, server_uri={self.server_uri})\n'
-            f'nodes={self.nodes}, subscriptions={self.subscriptions}'
-        )
-
-    async def shutdown(self):
-        """
-        Comprehensive cleanup method for graceful shutdown.
-
-        This method ensures proper cleanup of all OPC UA resources:
-        - Closes active subscriptions
-        - Disconnects from the OPC server
-        - Releases allocated resources
-
-        Should be called before the application terminates to prevent resource leaks
-        and ensure clean disconnection from OPC servers.
-        """
-        try:
-            await self.disconnect()
-        except Exception as e:
-            self.logger.error(f'Error during cleanup: {e}')
-
-    async def set_security(self):
-        """
-        Configures the security settings for the OPC UA client.
-
-        This method sets up the security policy, certificates, and timeouts
-        required for establishing a secure connection with the OPC UA server.
-        It implements Basic256 security policy with certificate-based authentication.
-
-        Raises:
-            ValueError: If either the certificate path or private key path is not provided.
-
-        Security Settings:
-            - Security Policy: Basic256
-            - Secure Channel Timeout: 10,000,000 ms
-            - Session Timeout: 10,000,000 ms
-
-        The method configures:
-            - Client application URI
-            - Certificate-based authentication
-            - Server certificate validation (if provided)
-            - Connection timeouts for stability
-        """
-
-        if not all([self.cert_path, self.private_key_path]):
-            raise ValueError(
-                'Certificate and private key paths must be provided for secure connection.'
-            )
-        cert = str(Path(self.cert_path)) if self.cert_path else None
-        private_key = str(Path(self.private_key_path)) if self.private_key_path else None
-        server_cert = str(Path(self.server_cert_path)) if self.server_cert_path else None
-        assert cert is not None and private_key is not None
-
-        if self.client:
-            self.client.application_uri = self.server_uri
-            self.logger.info('Setting security...')
-            await self.client.set_security(
-                SecurityPolicyBasic256,
-                certificate=cert,
-                private_key=private_key,
-                server_certificate=server_cert,
-            )
-            self.client.secure_channel_timeout = 10000000
-            self.client.session_timeout = 10000000
-
-    async def connect(self):
-        """
-        Establishes a connection to the OPC server.
-
-        This method initializes the OPC client using the provided URL and
-        sets up security if a certificate path is specified. It then
-        attempts to connect to the server and logs the connection status.
-
-        The connection process includes:
-        1. Client initialization with server URL
-        2. Security configuration (if certificates are provided)
-        3. Connection establishment
-        4. Metrics recording for monitoring
-
-        Raises:
-            Exception: If the connection to the OPC server fails.
-
-        Metrics:
-            - OPC_CONNECTIONS_TOTAL: Incremented on connection attempt
-            - OPC_CONNECTION_STATUS: Set to 1 on successful connection
-        """
-
-        await self.emit_metric(
-            metric_object=metrics.OPC_CONNECTIONS_TOTAL,
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-            },
-        )
-        try:
-            self.client = Client(self.url, timeout=10, watchdog_intervall=3600000)
-            assert self.client is not None  # Informa ao mypy que client não é None
-
-            self.client.name = self.pod_id
-            self.client.description = self.pod_id
-            pod_uri = self.pod_id.replace('-', ':')
-            self.client.application_uri = pod_uri
-            self.client.product_uri = pod_uri
-
-            if self.cert_path:
-                await self.set_security()
-            self.logger.info(f'Starting connection to {self.name}...')
-            await self.client.connect()
-            await self.emit_metric(
-                metric_object=metrics.OPC_CONNECTION_STATUS,
-                method='set',
-                value=1,
-                tags={
-                    'pod_id': self.pod_id,
-                    'server_name': self.name,
-                    'server_url': self.url,
-                },
-            )
-            self.logger.info(f'Connection to {self.name} successful.')
-        except Exception:
-            await self.disconnect()
-
-            raise
-
-    async def create_subscription(self, name: str):
-        """
-        Creates a subscription with the specified monitoring period.
-
-        This method establishes a subscription to monitor data changes or events
-        from the OPC UA server. If the client is not connected, an exception is raised.
-
-        Args:
-            name (str): The name identifier for the subscription
-            period (int, optional): The monitoring period in milliseconds. Defaults to 500 ms.
-
-        Raises:
-            ValueError: If the client is not connected.
-
-        Side Effects:
-            - Sets the `self.period` attribute to the specified or default period.
-            - Creates a subscription and assigns it to `self.subscriptions[name]`.
-            - Logs the creation of the subscription.
-            - Increments subscription creation metrics.
-        """
-
-        if not self.client:
-            raise ValueError('Client not connected. Call connect first.')
-        try:
-            self.subscriptions[name] = await self.client.create_subscription(
-                self.subscription_period_ms, self
-            )
-            self.logger.info(f'Subscription {name} created on {self.name}.')
-            await self.emit_metric(
-                metric_object=metrics.OPC_SUBSCRIPTIONS_CREATED,
-                method='inc',
-                value=1,
-                tags={
-                    'pod_id': self.pod_id,
-                    'server_name': self.name,
-                    'slot_name': name,
-                },
-            )
-        except Exception as e:
-            self.logger.error(f'Failed to create subscription {name} on {self.name}: {e}')
-            raise
-
-    async def subscribe(self, subscription: str, nodes: dict, collect_period: int):
-        """
-        Subscribes to a set of OPC UA nodes for data change notifications.
-
-        This method adds the specified nodes to the subscription and configures
-        their data collection rules based on the provided collection period and
-        node-specific frequency.
-
-        Args:
-            subscription (str): The name of the subscription to use
-            nodes (dict): A dictionary where keys are node identifiers and values are
-                configurations for each node. Each configuration must include a 'frequency'
-                key indicating the frequency of data collection in Hz.
-            collect_period (int): The data collection period in seconds.
-
-        Raises:
-            ValueError: If the subscription has not been created by calling
-                `create_subscription` prior to this method.
-
-        Side Effects:
-            - Updates internal node tracking and cycle rules
-            - Establishes data change monitoring for specified nodes
-            - Updates metrics for subscribed tags count
-        """
-
-        if not self.subscriptions.get(subscription):
-            raise ValueError('Subscription not created. Call create_subscription first.')
-
-        self.logger.info(f'Subscribing to {subscription} on {self.name}...')
-        self.logger.info(f'Subscribing to nodes: {nodes}')
-        assert self.client is not None  # Informa ao mypy que client não é None
-        addr_nodes = [self.client.get_node(n) for n in nodes]
-        self.logger.debug(f'Addr nodes: {addr_nodes}')
-        self.nodes.update(nodes)
-        self.logger.debug(f'Nodes: {self.nodes}')
-
-        self.collect_period = collect_period
-
-        for node, config in self.nodes.items():
-            self.nodes[node]['cycle_rule'] = {
-                'cycle_increment': collect_period * 1000 / float(config['frequency']),
-                'cycle_count': 0,
-            }
-
-        await self.subscriptions[subscription].subscribe_data_change(addr_nodes)
-
-        await self.emit_metric(
-            metric_object=metrics.OPC_TAGS_SUBSCRIBED,
-            method='set',
-            value=len(self.nodes),
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-            },
-        )
-
-    async def unsubscribe(self, subscription: str):
-        """
-        Unsubscribes from a given subscription.
-
-        This method removes the specified subscription and cleans up associated
-        resources. It handles cases where the subscription doesn't exist gracefully.
-
-        Args:
-            subscription (str): The name of the subscription to unsubscribe from.
-
-        Logs:
-            - A warning if the specified subscription does not exist.
-            - An info message upon successful unsubscription.
-
-        Behavior:
-            - If the subscription exists, it is deleted and removed from the
-              subscriptions dictionary.
-            - If the subscription does not exist, no action is taken.
-        """
-
-        if not self.subscriptions.get(subscription):
-            self.logger.warning(f"Subscription '{subscription}' not found. Cannot unsubscribe.")
-            return
-        await self.subscriptions[subscription].delete()
-        del self.subscriptions[subscription]
-        self.logger.info(f'Unsubscribed from {subscription}.')
-
-    async def disconnection_fallback(self) -> list:
-        """
-        Tries 5 times to disconnect from the OPC UA server, with a delay of 100ms x try.
-        """
-
-        assert self.client is not None
-        error_stack = []
-        for i in range(5):
-            try:
-                self.logger.info(f'Disconnecting from OPC UA server, attempt {i + 1} of 5')
-                await self.client.disconnect()
-                return []
-            except Exception as e:
-                self.logger.error(
-                    f'Failed to disconnect from OPC UA serve  in attempt {i + 1} of 5: {e}'
-                )
-                error_stack.append(
-                    {
-                        'attempt': i + 1,
-                        'error': str(e),
-                        'traceback': traceback.format_exc(),
-                    }
-                )
-                await asyncio.sleep(0.1 * i)
-        return error_stack
-
-    async def disconnect(self):
-        """
-        Disconnects from the OPC UA server.
-
-        This method handles the disconnection process by deleting all subscriptions
-        and disconnecting the client from the OPC UA server. It logs the disconnection
-        process and handles any exceptions that may occur during cleanup.
-
-        Raises:
-            Exception: If an error occurs while deleting the subscription or disconnecting
-                       from the OPC UA server, it logs the error details.
-
-        Side Effects:
-            - Deletes all active subscriptions
-            - Disconnects the OPC client
-            - Updates connection status metrics
-            - Clears internal client reference
-        """
-
-        self.logger.warning('Disconnecting from OPC server')
-        if self.client is None:
-            self.logger.warning('Client already disconnected.')
-            return
-        try:
-            for sub in self.subscriptions:
-                await self.subscriptions[sub].delete()
-            self.logger.warning('Deleted all subscriptions.')
-        except Exception as sub_error:
-            self.logger.error(f'Failed to clean up subscription: {sub_error}')
-
-        errors = await self.disconnection_fallback()
-
-        if errors:
-            await self.send_notification_async(
-                metadata=self.metadata,
-                notification_id=f'OPC_DISCONNECTION_ERROR_{self.name}',
-                message=f'Failed to disconnect from OPC UA server {self.name} after 5 attempts',
-                block='opc_manager',
-                level=NotificationLevel.ERROR,
-                attachment_content=json.dumps(errors, indent=4),
-            )
-        else:
-            self.logger.warning('Disconnected from OPC UA server.')
-
-        del self.client
-        self.client = None
-        await self.emit_metric(
-            metric_object=metrics.OPC_CONNECTION_STATUS,
-            method='set',
-            value=0,
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-                'server_url': self.url,
-            },
-        )
-        await self.emit_metric(
-            metric_object=metrics.OPC_TAGS_SUBSCRIBED,
-            method='set',
-            value=0,
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-            },
-        )
-
-    async def datachange_notification(self, node, _val, data):
-        """
-        Handles data change notifications for monitored OPC UA nodes.
-
-        This method is triggered when a monitored node's value changes. It processes
-        the notification, updates internal state, and publishes the data to the
-        appropriate topics.
-
-        Args:
-            node (NodeId): The OPC UA node that triggered the data change notification.
-            _val (Any): The new value of the node (unused in this implementation).
-            data (DataChangeNotification): The data change notification object containing
-                details about the change.
-
-        Behavior:
-            - Extracts the value and source timestamp from the monitored item.
-            - Resets the cycle count for the node's cycle rule.
-            - Resets the non-receive count.
-            - Constructs a data dictionary containing the tag, tag name, timestamp, and value.
-            - Publishes the data to all topics associated with the node.
-        """
-
-        # get data value
-        monitored_item = data.monitored_item
-        value = monitored_item.Value.Value.Value
-        # source_timestamp
-        source_timestamp = monitored_item.Value.SourceTimestamp.replace(tzinfo=OPC_TIMEZONE)
-        tag = str(node)
-
-        self.logger.debug(
-            f'Data change notification received for tag:'
-            f'{tag} after {self.nodes[tag]["cycle_rule"]["cycle_count"]} cycles'
-        )
-
-        data = {
-            'tag': tag,
-            'name': self.nodes[str(node)]['tag_name'],
-            'timestamp': source_timestamp.strftime(DATETIME_FORMAT_WITH_TZ),
-            'value': value,
-        }
-
-        for topic in self.nodes[tag]['topics']:
-            await self.data_manager.publish(topic, data)
-
-        self.nodes[tag]['cycle_rule']['cycle_count'] = 0
-        self.non_receive_count = 0
-        await self.emit_metric(
-            metric_object=metrics.OPC_CYCLES_WITHOUT_DATA,
-            method='set',
-            value=0,
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-            },
-        )
-
-    async def check_cycles(self):
-        """
-        Checks the cycle counts for all monitored nodes and sends
-        notifications if thresholds are exceeded.
-
-        This method iterates through all monitored nodes and updates their cycle counts based on
-        configured increments. If a node's cycle count exceeds a threshold (5 cycles), it triggers
-        a warning notification.
-
-        Side Effects:
-            - Updates cycle counts for all monitored nodes
-            - Sends warning notifications for nodes exceeding cycle thresholds
-        """
-        for node, config in self.nodes.items():
-            self.nodes[node]['cycle_rule']['cycle_count'] += config['cycle_rule']['cycle_increment']
-            if self.nodes[node]['cycle_rule']['cycle_count'] >= 5:
-                name = config['tag_name']
-                cycles = self.nodes[node]['cycle_rule']['cycle_count']
-                await self.send_notification_async(
-                    metadata=self.metadata,
-                    notification_id=f'TAG_{node}:{name}_LISTENNING_STOPPED',
-                    message=f'{cycles} cycles without receive from {node}:{name}',
-                    block='opc_manager',
-                    level=NotificationLevel.WARNING,
-                )
-
-    async def check_opc_listenning(self) -> bool:
-        """
-        Checks the OPC connection and triggers notifications if the connection is lost.
-
-        This method monitors the data reception health by tracking cycles without
-        data. It sends notifications at different thresholds and can trigger
-        reconnection attempts.
-
-        Returns:
-            bool: True if the connection is lost and reconnection should be attempted,
-                  False otherwise.
-
-        Side Effects:
-            - Increments non-receive count
-            - Updates metrics for cycles without data
-            - Sends warning notifications at 5 cycles
-            - Sends error notifications and triggers reconnection at 15 cycles
-        """
-
-        self.non_receive_count += 1
-        await self.emit_metric(
-            metric_object=metrics.OPC_CYCLES_WITHOUT_DATA,
-            method='set',
-            value=self.non_receive_count,
-            tags={
-                'pod_id': self.pod_id,
-                'server_name': self.name,
-            },
-        )
-        if self.non_receive_count >= 5:
-            await self.send_notification_async(
-                metadata=self.metadata,
-                notification_id=f'OPC_LISTENNING_STOPPED__{self.name}',
-                message=f'{self.non_receive_count} cycles without '
-                f'receive from OPC {self.name}. Tags: {json.dumps(self.nodes)}',
-                block='opc_manager',
-                level=NotificationLevel.ERROR,
-            )
-        if self.non_receive_count >= 15:
-            await self.emit_metric(
-                metric_object=metrics.OPC_RECONNECTIONS_TOTAL,
-                tags={
-                    'pod_id': self.pod_id,
-                    'server_name': self.name,
-                },
-            )
-            await self.send_notification_async(
-                metadata=self.metadata,
-                notification_id=f'OPC_CONNECTION_RETRY__{self.name}',
-                message=f'Retrying to connect to server {self.name}',
-                block='opc_manager',
-                level=NotificationLevel.ERROR,
-            )
-            return True
-        return False

ingestor/managers/server_reader.py

@@ -1,13 +1,11 @@
 """Per-server read path driven by the IngestorManager (SIENTIAPDE-1974).
 
-Replaces the legacy OpcManager behind the same interface the IngestorManager
-already uses (connect / create_subscription / subscribe / unsubscribe /
-check_cycles / check_opc_listenning / shutdown), so the slot lease loop is
-unchanged. The difference is underneath:
+Exposes the interface the IngestorManager drives (connect / create_subscription /
+subscribe / unsubscribe / check_cycles / check_opc_listenning / shutdown):
 
-- the connection comes from the shared OpcConnectionPool, so the certificate is
-  fetched from MinIO by CertProvider (Basic256Sha256) — never from a file shipped
-  in the Gitea repository;
+- the connection comes from the shared OpcConnectionPool, with the slot's security
+  mode and policy and the client certificate the slot names, which CertProvider
+  downloads from MinIO (no certificate: no security);
 - readings go through SubscriptionEngine, which fans each value out to every
   `names` entry of the slot v2 (one document per collection / tag name / model).
 """
@@ -58,7 +56,7 @@ class ServerReader:
 
     async def connect(self):
         """Open (or reuse) the pooled connection; raises if the server is unreachable
-        or the certificate can't be fetched, like OpcManager.connect did."""
+        or the certificate can't be fetched."""
         await self.pool.get(self.server_id, self.server_cfg)
 
     async def create_subscription(self, slot: str):

ingestor/metrics.py

@@ -156,6 +156,12 @@ OPC_WRITE_STATUS_BY_MODEL = Gauge(
     'Last write status per model (1=ok,0=error)',
     ['pod_id', 'model_id', 'status'],
 )
+OPC_WRITE_STATUS_UPDATE_TOTAL = Counter(
+    'opc_write_status_update_total',
+    'write_status UPDATEs on the prediction rows',
+    # result: updated|kept|row_not_found|invalid|error
+    ['pod_id', 'result'],
+)
 # --- Gateway: Active read metrics ---
 OPC_ACTIVE_READ_TOTAL = Counter(
     'opc_active_read_total',

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ingestor"
-version = "2.2.0-rc1"
+version = "2.1.0"
 description = "Sientia DataOps Ingestor - OPC Tag Ingestor"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -59,6 +59,11 @@ ignore = [
     "S105",  # hardcoded passwords ok in tests
     "S106",  # hardcoded passwords ok in tests
 ]
+"e2e/**/*.py" = [
+    "S101",  # assert allowed in tests
+    "S105",  # hardcoded passwords ok in tests
+    "S106",  # hardcoded passwords ok in tests
+]
 
 [tool.ruff.lint.mccabe]
 max-complexity = 15
@@ -129,7 +134,7 @@ addopts = [
 ]
 markers = [
     "asyncio: marks tests as async",
-    "integration: marks tests as integration tests",
+    "integration: marks tests as integration tests (the e2e/ suite: Docker required, run with -o testpaths=e2e -m integration)",
     "unit: marks tests as unit tests",
 ]
 

requirements-dev.txt

@@ -13,6 +13,8 @@ types-requests>=2.31.0   # Type stubs for requests
 pytest>=7.4.0            # Testing framework
 pytest-cov>=4.1.0        # Coverage plugin for pytest
 pytest-asyncio>=0.21.0   # Async test support (already in main requirements)
+testcontainers[postgres,minio,mongodb,redis]>=4.15.0  # E2E suite (e2e/): real MongoDB, Redis, PostgreSQL,
+                         # MinIO and NATS containers; `testcontainers.community.*` namespace
 
 # Development Tools
 ipython>=8.12.0          # Enhanced Python shell

requirements-local.txt

@@ -1,4 +1,4 @@
-asyncua==1.1.5
+asyncua>=2.0
 redis
 git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.12.2
 prometheus_client

requirements.txt

@@ -1,4 +1,6 @@
-asyncua
+# >=2.0: WriteEngine builds DataValue(StatusCode=...); 1.x names the field StatusCode_,
+# so every write would fail with TypeError (reported as bad_timestamp).
+asyncua>=2.0
 redis
 # 1.12.5 builds the Postgres engine with an explicit postgresql+psycopg2:// URL: SQLAlchemy 2.1
 # defaults postgresql:// to psycopg (v3), which is not installed ("No module named 'psycopg'").

scripts/generate-and-push-opc-cert.sh

@@ -1,95 +0,0 @@
-#!/usr/bin/env bash
-# Gera o certificado X.509 de cliente OPC UA do ingestor e sobe pro Gitea
-# in-cluster (repo que o pod clona no boot — nada muda no values/deployment,
-# só rollout restart depois do push).
-#
-# Uso:
-#   GITEA_PASSWORD='<senha>' ./scripts/generate-and-push-opc-cert.sh
-#
-# Vars (defaults pro cluster dev/gcp):
-#   GITEA_URL      default https://git.sientia.ai
-#   GITEA_USER     default gitea_admin
-#   GITEA_PASSWORD obrigatória
-#   GITEA_REPO     default gitea_admin/sientia-dataops-opc-ingestor
-#   BRANCH         default main
-#   APP_URI        default urn:sientia:opc-ingestor  (SAN URI do cert — TEM que
-#                  ser igual ao campo `uri` do documento na collection
-#                  OPC_servers: o ingestor usa esse valor como application_uri
-#                  e o KEPServer rejeita com BadCertificateUriInvalid se divergir)
-#   DAYS           default 3650
-#   FORCE=1        sobrescreve cert já existente no repo
-set -euo pipefail
-
-GITEA_URL=${GITEA_URL:-https://git.sientia.ai}
-GITEA_USER=${GITEA_USER:-gitea_admin}
-GITEA_PASSWORD=${GITEA_PASSWORD:?export GITEA_PASSWORD com a senha do Gitea}
-GITEA_REPO=${GITEA_REPO:-gitea_admin/sientia-dataops-opc-ingestor}
-BRANCH=${BRANCH:-main}
-APP_URI=${APP_URI:-urn:sientia:opc-ingestor}
-CN=${CN:-sientia-opc-ingestor}
-DAYS=${DAYS:-3650}
-
-CERT_DIR_IN_REPO="certs"
-CERT_NAME="opc-ingestor-cert.pem"
-KEY_NAME="opc-ingestor-key.pem"
-DER_NAME="opc-ingestor-cert.der"
-
-workdir=$(mktemp -d)
-trap 'rm -rf "$workdir"' EXIT
-
-echo ">> Gerando certificado (CN=${CN}, URI=${APP_URI}, ${DAYS} dias)..."
-# Extensões exigidas por OPC UA (KEPServer valida keyUsage/EKU e o SAN URI).
-openssl req -x509 -newkey rsa:2048 -sha256 -nodes -days "$DAYS" \
-  -keyout "$workdir/$KEY_NAME" -out "$workdir/$CERT_NAME" \
-  -subj "/CN=${CN}/O=Aignosi/OU=Sientia" \
-  -addext "subjectAltName=URI:${APP_URI},DNS:${CN}" \
-  -addext "keyUsage=critical,digitalSignature,nonRepudiation,keyEncipherment,dataEncipherment" \
-  -addext "extendedKeyUsage=critical,clientAuth,serverAuth" \
-  -addext "basicConstraints=critical,CA:FALSE"
-
-# Cópia DER — só referência p/ import manual no KEPServer (o trust normal é
-# aceitar o cert rejeitado na 1ª conexão).
-openssl x509 -in "$workdir/$CERT_NAME" -outform der -out "$workdir/$DER_NAME"
-
-echo ">> Clonando ${GITEA_REPO}@${BRANCH} do Gitea..."
-encoded_pass=$(python3 - <<EOF
-import urllib.parse; print(urllib.parse.quote('''${GITEA_PASSWORD}''', safe=''))
-EOF
-)
-clone_url="${GITEA_URL%%/}"
-clone_url="${clone_url/:\/\//:\/\/${GITEA_USER}:${encoded_pass}@}/${GITEA_REPO}.git"
-git clone --depth 1 --branch "$BRANCH" "$clone_url" "$workdir/repo" 2>&1 | sed "s#${encoded_pass}#***#g"
-
-if [[ -f "$workdir/repo/$CERT_DIR_IN_REPO/$CERT_NAME" && "${FORCE:-0}" != "1" ]]; then
-  echo "ERRO: $CERT_DIR_IN_REPO/$CERT_NAME já existe no repo. Re-rodar com FORCE=1 sobrescreve" >&2
-  echo "      (o cert antigo deixa de valer — retrust no KEPServer necessário)." >&2
-  exit 1
-fi
-
-mkdir -p "$workdir/repo/$CERT_DIR_IN_REPO"
-cp "$workdir/$CERT_NAME" "$workdir/$KEY_NAME" "$workdir/$DER_NAME" "$workdir/repo/$CERT_DIR_IN_REPO/"
-
-cd "$workdir/repo"
-git add "$CERT_DIR_IN_REPO"
-git -c user.name="opc-cert-script" -c user.email="platform@aignosi.com.br" \
-  commit -m "Add OPC UA client certificate for KEPServer connection (URI ${APP_URI})"
-git push origin "$BRANCH" 2>&1 | sed "s#${encoded_pass}#***#g"
-
-fingerprint=$(openssl x509 -in "$CERT_DIR_IN_REPO/$CERT_NAME" -noout -fingerprint -sha1)
-
-cat <<EOF
-
-== PRONTO ==
-Cert no Gitea: ${GITEA_REPO}@${BRANCH} -> ${CERT_DIR_IN_REPO}/{${CERT_NAME},${KEY_NAME},${DER_NAME}}
-${fingerprint}
-
-Paths dentro do pod (o entrypoint clona o repo em /app):
-  cert_path:        /app/${CERT_DIR_IN_REPO}/${CERT_NAME}
-  private_key_path: /app/${CERT_DIR_IN_REPO}/${KEY_NAME}
-
-Próximos passos:
-  1. Documento na collection OPC_servers com "uri": "${APP_URI}" (ver README/PR).
-  2. kubectl -n sientia rollout restart deployment/opc-ingestor   # re-clona o repo
-  3. Pod tenta conectar -> no KEPServer: OPC UA Configuration Manager ->
-     Trusted Clients -> cert '${CN}' rejeitado -> Trust -> restart runtime.
-EOF

scripts/seed_e2e.py

@@ -3,7 +3,7 @@
 Populates:
   1. Mongo `connectors` + `connector_tags` (each tag with `metadata: {}` — required
      for documentation, per the feature owner).
-  2. Redis slot v1 (`slot:opc_tags:1`) so the legacy subscription path collects them.
+  2. Redis slot v2 (`slot:opc_tags:1`, contract C1) so the subscription path collects them.
   3. Postgres test predictions table (with the `write_status` column) + one row the
      NATS write test can UPDATE (correlated by timestamp + model_id).
 
@@ -37,41 +37,53 @@ except ImportError:
 
 OPC_URL = os.getenv('OPC_SERVER_URL', 'opc.tcp://localhost:49320')
 
+# No client certificate: the gateway connects without security (SIENTIAPDE-1974 D5).
+# To test security, point client_certificate_id at an active client certificate of
+# opc_certificates and set mode/policy (e.g. SignAndEncrypt / Basic256Sha256).
+SECURITY = {'mode': 'None', 'policy': 'None', 'client_certificate_id': None}
+
 CONNECTOR = {
-    'connector_id': 9001,
+    'connector_id': 'e2e-kepserver',
     'type': 'opc_ua',
     'name': 'e2e-kepserver',
     'url': OPC_URL,
-    'server_uri': 'urn:e2e:gateway:test',
     'subscription_period_ms': 1000,
-    'use_security': False,  # round 1; flip after certs are in sientia-dataops
+    'security': SECURITY,
     'status': 'Active',
     'description': 'OPC Gateway e2e validation connector (SIENTIAPDE-1972)',
 }
 
 # metadata: {} on every tag — feature owner asked test tags to carry the field.
 TAGS = [
-    {'tag_id': 9101, 'connector_id': 9001, 'address': 'ns=2;s=Simulation Examples.Functions.Ramp1',
+    {'tag_id': 9101, 'connector_id': 'e2e-kepserver', 'address': 'ns=2;s=Simulation Examples.Functions.Ramp1',
      'tag_name': 'e2e_ramp', 'category': 'Read', 'data_type': 'float', 'unit': '-',
      'status': 'Active', 'description': 'e2e read tag', 'metadata': {}},
-    {'tag_id': 9102, 'connector_id': 9001, 'address': 'ns=2;s=Simulation Examples.Functions.User1',
+    {'tag_id': 9102, 'connector_id': 'e2e-kepserver', 'address': 'ns=2;s=Simulation Examples.Functions.User1',
      'tag_name': 'e2e_write_target', 'category': 'Write', 'data_type': 'float', 'unit': '-',
      'status': 'Active', 'description': 'e2e write tag', 'metadata': {}},
 ]
 
-# Slot v1 (legacy path the gateway still runs until SIENTIAPDE-1974 delivers slot v2).
-SLOT_V1 = {
+# Slot v2 (contract C1), as the Orchestrator writes it for the connector above.
+SLOT = {
     'e2e-kepserver': {
         'name': 'e2e-kepserver',
-        'server_id': '9001',
+        'server_id': 'e2e-kepserver',
         'url': OPC_URL,
-        'server_uri': 'urn:e2e:gateway:test',
         'subscription_period_ms': 1000,
+        'security': {'mode': SECURITY['mode'], 'policy': SECURITY['policy']},
+        'certificate': None,
         'tags': {
             TAGS[0]['address']: {
-                'tag_name': TAGS[0]['tag_name'],
-                'frequency': '5000',
-                'topics': ['raw_e2e-gateway-test'],
+                'frequency': 5000,
+                'active_read': {'enabled': False},
+                'names': [
+                    {
+                        'collection': 'raw_e2e-gateway-test',
+                        'tag_name': TAGS[0]['tag_name'],
+                        'model_id': '9001',
+                        'model_name': 'e2e-model',
+                    }
+                ],
             }
         },
     }
@@ -94,12 +106,11 @@ ON CONFLICT DO NOTHING;
 
 # The matching NATS write command for the row above (paste into `nats pub opc.write '...'`).
 NATS_CMD = {
-    'msg_id': 'e2e-0001', 'server_id': '9001', 'addr': TAGS[1]['address'],
+    'msg_id': 'e2e-0001', 'server_id': 'e2e-kepserver', 'addr': TAGS[1]['address'],
     'value': 42.5, 'data_type': 'float', 'tag_type': 'prediction',
     'model_id': '9001', 'model_name': 'e2e-model',
     'schema': 'sientia_data', 'table_name': 'e2e_predictions',
     'timestamp': '2026-07-15T12:00:00Z',
-    'url': OPC_URL, 'use_security': False, 'server_uri': 'urn:e2e:gateway:test',
 }
 
 
@@ -119,8 +130,8 @@ def seed_redis():
     import redis
 
     r = redis.Redis(host=os.getenv('REDIS_HOST', 'localhost'), port=int(os.getenv('REDIS_PORT', '6379')))
-    r.set('slot:opc_tags:1', json.dumps(SLOT_V1))
-    print('redis: wrote slot:opc_tags:1 (v1)')
+    r.set('slot:opc_tags:1', json.dumps(SLOT))
+    print('redis: wrote slot:opc_tags:1 (v2)')
 
 
 def seed_postgres():
@@ -144,7 +155,7 @@ def main() -> int:
     if args.print_only:
         print('connector:', json.dumps(CONNECTOR, indent=2))
         print('tags:', json.dumps(TAGS, indent=2))
-        print('slot v1:', json.dumps(SLOT_V1, indent=2))
+        print('slot v2:', json.dumps(SLOT, indent=2))
         print('sql:', PREDICTIONS_SQL)
         print('nats write cmd:', json.dumps(NATS_CMD, indent=2))
         return 0

tests/functional/conftest.py

@@ -1,31 +0,0 @@
-# import subprocess
-# from time import sleep
-# import pytest
-# from redis import Redis
-
-
-# @pytest.fixture(scope="session", autouse=True)
-# def docker_compose():
-#     """Sobe os containers antes dos testes e derruba depois."""
-#     print("\n🚀 Subindo Docker Compose...")
-#     subprocess.run(["docker", "compose", "up", "-d"], check=True)
-
-#     print("⏳ Aguardando containers ficarem prontos...")
-#     sleep(15)  # ajuste conforme necessário
-
-#     yield  # os testes rodam aqui
-
-#     print("\n🧹 Derrubando Docker Compose...")
-#     subprocess.run(["docker", "compose", "down"], check=True)
-
-
-# @pytest.fixture()
-# def redis_client():
-#     redis = Redis(host="localhost", port=6379, decode_responses=True)
-#     redis.flushdb()
-
-#     yield redis
-
-#     # Limpa o banco de dados após os testes
-#     redis.flushdb()
-#     redis.close()

tests/functional/test_single_node.py

@@ -1,93 +0,0 @@
-# import json
-# import subprocess
-# from time import sleep
-
-
-# new_data = {
-#     "slot:opc_tags:1": {
-#         "server1": {
-#             "name": "server1",
-#             "url": "opc.tcp://simulator:4840",
-#             "server_uri": "http://opcua-server.simulator",
-#             "tags": {
-#                 'ns=2;i=2': {
-#                     'tag_name': 'Counter',
-#                     'frequency': 1000,
-#                     'topics': [],
-#                 },
-#                 'ns=2;i=3': {
-#                     'tag_name': 'Rollout',
-#                     'frequency': 1000,
-#                     "topics": [],
-#                 },
-#                 'ns=2;i=4': {
-#                     'tag_name': 'Square',
-#                     'frequency': 1000,
-#                     "topics": [],
-#                 },
-#             }
-#         }
-#     },
-#     "slot:opc_tags:2": {
-#         "server2": {
-#             "name": "server2",
-#             "url": "opc.tcp://simulator:4840",
-#             "server_uri": "http://opcua-server.simulator",
-#             "tags": {
-#                 'ns=2;i=2': {
-#                     'tag_name': 'Counter',
-#                     'frequency': 1000,
-#                     'topics': [],
-#                 },
-#                 'ns=2;i=3': {
-#                     'tag_name': 'Rollout',
-#                     'frequency': 1000,
-#                     "topics": [],
-#                 },
-#                 'ns=2;i=4': {
-#                     'tag_name': 'Square',
-#                     'frequency': 1000,
-#                     "topics": [],
-#                 },
-#             }
-#         }
-#     }
-# }
-
-
-# def test_simple(redis_client):
-#     new_data['slot:opc_tags:1']['server1']['tags']['ns=2;i=2']['topics'] = [
-#         'test_topic_1']
-#     redis_client.set("slot:opc_tags:1",
-#                      json.dumps(new_data['slot:opc_tags:1']))
-
-#     sleep(20)  # Espera o Ingestor processar os dados
-
-#     # Check if lease is in Redis
-#     assert redis_client.get("lease:opc_tags:1") == 'ingestor'
-#     assert redis_client.get("heartbeat:ingestor:ingestor") == '1'
-
-
-# def test_simple_double_slot(redis_client):
-
-#     new_data['slot:opc_tags:1']['server1']['tags']['ns=2;i=2']['topics'] = [
-#         'test_topic_double_slot1']
-#     redis_client.set("slot:opc_tags:1",
-#                      json.dumps(new_data['slot:opc_tags:1']))
-
-#     sleep(20)  # Espera o Ingestor processar os dados
-
-#     assert redis_client.get("lease:opc_tags:1") == 'ingestor'
-#     assert redis_client.get("heartbeat:ingestor:ingestor") == '1'
-
-#     new_data['slot:opc_tags:2']['server2']['tags']['ns=2;i=2']['topics'] = [
-#         'test_topic_double_slot2']
-#     redis_client.set("slot:opc_tags:2",
-#                      json.dumps(new_data['slot:opc_tags:2']))
-
-#     sleep(20)  # Espera o Ingestor processar os dados
-
-#     # Check if lease is in Redis
-#     assert redis_client.get("lease:opc_tags:2") == 'ingestor'
-#     assert redis_client.get("lease:opc_tags:1") == 'ingestor'
-#     assert redis_client.get("heartbeat:ingestor:ingestor") == '1'

tests/unit/adapters/test_nats_consumer.py

@@ -1,3 +1,5 @@
+import asyncio
+import inspect
 import json
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -37,20 +39,99 @@ async def test_handle_invalid_json_drops_message_and_logs_error():
     consumer.logger.error.assert_called_once()
 
 
+CLIENT = 'ingestor.adapters.nats_consumer.Client'
+
+
+def _fake_nc(connect=None):
+    nc = MagicMock()
+    nc.connect = connect or AsyncMock()
+    nc.subscribe = AsyncMock()
+    nc.close = AsyncMock()
+    nc.drain = AsyncMock()
+    nc.is_closed = False
+    return nc
+
+
+async def _hang(*_args, **_kwargs):
+    await asyncio.sleep(10)
+
+
 @pytest.mark.asyncio
 async def test_start_subscribes_with_subject_and_queue():
     consumer = make_consumer(subject='opc.write', queue='gateway-writers')
-    mock_nc = AsyncMock()
-    mock_nc.subscribe = AsyncMock()
+    nc = _fake_nc()
 
-    with patch('ingestor.adapters.nats_consumer.nats') as mock_nats:
-        mock_nats.connect = AsyncMock(return_value=mock_nc)
+    with patch(CLIENT, return_value=nc):
         await consumer.start()
 
-    mock_nats.connect.assert_awaited_once_with(servers='nats://localhost:4222')
-    mock_nc.subscribe.assert_awaited_once_with(
-        'opc.write', queue='gateway-writers', cb=consumer._handle
-    )
+    kwargs = nc.connect.await_args.kwargs
+    assert kwargs['servers'] == 'nats://localhost:4222'
+    # Reconnection is unbounded once connected: an outage never closes it for good.
+    assert kwargs['max_reconnect_attempts'] == -1
+    nc.subscribe.assert_awaited_once_with('opc.write', queue='gateway-writers', cb=consumer._handle)
+    assert consumer.closed is False
+
+
+@pytest.mark.asyncio
+async def test_start_gives_up_after_the_connect_timeout():
+    """start() runs on the main loop: an unreachable NATS must not block it."""
+    consumer = make_consumer(connect_timeout_s=0.1)
+    nc = _fake_nc(connect=AsyncMock(side_effect=_hang))
+    # Outer guard: fails the test instead of hanging it if start() ignores its timeout.
+    start = asyncio.wait_for(consumer.start(), timeout=5)
+
+    with patch(CLIENT, return_value=nc):
+        with pytest.raises(TimeoutError):
+            await start
+
+    nc.close.assert_awaited_once()
+    assert consumer.closed is True
+
+
+@pytest.mark.asyncio
+async def test_start_closes_the_connection_when_subscribe_fails():
+    consumer = make_consumer()
+    nc = _fake_nc()
+    nc.subscribe.side_effect = RuntimeError('permissions violation')
+
+    with patch(CLIENT, return_value=nc), pytest.raises(RuntimeError):
+        await consumer.start()
+
+    nc.close.assert_awaited_once()
+    assert consumer.closed is True
+
+
+@pytest.mark.asyncio
+async def test_handle_unexpected_engine_error_is_logged_not_raised():
+    consumer = make_consumer()
+    consumer.write_engine.write.side_effect = RuntimeError('bug')
+    msg = MagicMock(data=json.dumps({'server_id': '1'}).encode())
+
+    await consumer._handle(msg)
+
+    assert 'bug' in consumer.logger.error.call_args.args[0]
+
+
+@pytest.mark.asyncio
+async def test_connection_events_are_logged_in_one_line():
+    consumer = make_consumer()
+    nc = _fake_nc()
+    with patch(CLIENT, return_value=nc):
+        await consumer.start()
+    callbacks = nc.connect.await_args.kwargs
+    # nats-py raises InvalidCallbackTypeError on connect for a non-coroutine callback.
+    for name in ('error_cb', 'disconnected_cb', 'reconnected_cb'):
+        assert inspect.iscoroutinefunction(callbacks[name]), name
+
+    await callbacks['error_cb'](OSError('connection refused'))
+    await callbacks['disconnected_cb']()
+    await callbacks['reconnected_cb']()
+
+    warnings = [c.args[0] for c in consumer.logger.warning.call_args_list]
+    assert warnings == [
+        'NATS error: OSError connection refused',
+        'Disconnected from NATS; reconnecting',
+    ]
 
 
 @pytest.mark.asyncio
@@ -63,14 +144,28 @@ async def test_stop_before_start_does_not_raise():
 @pytest.mark.asyncio
 async def test_stop_after_start_drains_and_unsubscribes():
     consumer = make_consumer()
-    mock_nc = AsyncMock()
-    mock_sub = AsyncMock()
-    mock_nc.subscribe = AsyncMock(return_value=mock_sub)
+    nc = _fake_nc()
+    sub = AsyncMock()
+    nc.subscribe = AsyncMock(return_value=sub)
 
-    with patch('ingestor.adapters.nats_consumer.nats') as mock_nats:
-        mock_nats.connect = AsyncMock(return_value=mock_nc)
+    with patch(CLIENT, return_value=nc):
         await consumer.start()
         await consumer.stop()
 
-    mock_sub.unsubscribe.assert_awaited_once()
-    mock_nc.drain.assert_awaited_once()
+    sub.unsubscribe.assert_awaited_once()
+    nc.drain.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_stop_on_a_connection_closed_for_good_does_not_raise():
+    consumer = make_consumer()
+    nc = _fake_nc()
+    with patch(CLIENT, return_value=nc):
+        await consumer.start()
+    nc.is_closed = True
+    consumer.sub.unsubscribe = AsyncMock(side_effect=RuntimeError('connection closed'))
+
+    await consumer.stop()  # no raise
+
+    nc.drain.assert_not_awaited()
+    assert consumer.closed is True

tests/unit/conftest.py

@@ -1,13 +1,13 @@
 from unittest.mock import AsyncMock, MagicMock
 
-from pytest import fixture
+import pytest
 
 
-@fixture
+@pytest.fixture
 def reader_double():
     """Factory of OPC reader doubles holding subscriptions for the given slots.
 
-    Like the real readers (ServerReader, OpcManager), `subscriptions` is keyed by slot
+    Like the real ServerReader, `subscriptions` is keyed by slot
     and `unsubscribe` drops the slot from it.
     """
 

tests/unit/connection/test_certificates.py

@@ -0,0 +1,67 @@
+import pytest
+
+from ingestor.connection.certificates import (
+    client_certificate_id,
+    has_security,
+    resolve_certificate,
+)
+
+LOOKED_UP = {
+    'certificate_id': 1,
+    'application_uri': 'urn:sientia:opc-ingestor',
+    'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+    'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+}
+
+
+def _connector(certificates, certificate_id=1):
+    return {
+        'connector_id': 'kepserver',
+        'url': 'opc.tcp://kep:49320',
+        'security': {
+            'mode': 'SignAndEncrypt',
+            'policy': 'Basic256Sha256',
+            'client_certificate_id': certificate_id,
+        },
+        'certificates': certificates,
+    }
+
+
+def test_resolve_certificate_keeps_only_the_slot_fields():
+    looked_up = {
+        **LOOKED_UP,
+        'thumbprint_sha1': 'ab',
+        'cert': {**LOOKED_UP['cert'], 'sha256': None},
+    }
+
+    assert resolve_certificate(_connector([looked_up])) == LOOKED_UP
+
+
+@pytest.mark.parametrize(
+    'certificates',
+    [
+        pytest.param(None, id='no-lookup'),
+        pytest.param([], id='not-found'),
+        pytest.param([{**LOOKED_UP, 'application_uri': ''}], id='no-application-uri'),
+        pytest.param([{**LOOKED_UP, 'cert': None}], id='no-cert'),
+        pytest.param([{**LOOKED_UP, 'private_key': {'object_name': 'k'}}], id='key-no-bucket'),
+        pytest.param(['not a document'], id='not-a-document'),
+    ],
+)
+def test_resolve_certificate_without_a_usable_certificate(certificates):
+    assert resolve_certificate(_connector(certificates)) is None
+
+
+def test_client_certificate_id():
+    assert client_certificate_id(_connector([])) == 1
+    assert client_certificate_id(_connector([], certificate_id=None)) is None
+    assert client_certificate_id({'connector_id': 'x'}) is None
+    assert client_certificate_id({'security': None}) is None
+
+
+def test_has_security():
+    assert has_security(_connector([]))
+    assert has_security({'security': {'mode': 'None', 'policy': 'None'}})
+    assert not has_security({'security': {'mode': 'Sign'}})
+    assert not has_security({'security': None})
+    assert not has_security({})

tests/unit/connection/test_certs.py

@@ -1,136 +1,109 @@
-from unittest.mock import AsyncMock
+import asyncio
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
-from ingestor.connection.certs import CertProvider
+from ingestor.connection.certs import CertificateNotConfiguredError, CertProvider, LazyMinio
 
 
-@pytest.mark.asyncio
-async def test_fetch_returns_local_paths(tmp_path):
-    mongo = AsyncMock()
-    mongo.find_one.return_value = {
-        'client_cert': {'minio_object_name': 'platform/certificates/client_cert_c.pem'},
-        'private_key': {'minio_object_name': 'platform/certificates/private_key_k.pem'},
+def certificate(certificate_id=1, name='sientia-platform', ext='pem', bucket='opc-certificates'):
+    """A client certificate as the slot v2 carries it."""
+    return {
+        'certificate_id': certificate_id,
+        'application_uri': 'urn:sientia:opc-ingestor',
+        'cert': {'bucket': bucket, 'object_name': f'client/{name}/cert.{ext}'},
+        'private_key': {'bucket': bucket, 'object_name': f'client/{name}/key.{ext}'},
     }
-    minio = AsyncMock()
-    minio.download_file.side_effect = [b'cert-bytes', b'key-bytes']
-
-    provider = CertProvider(mongo, minio, cache_dir=str(tmp_path), bucket='sientia-dataops')
-    cert, key = await provider.fetch()
-
-    assert cert.endswith('c.pem') and key.endswith('k.pem')
-    assert minio.download_file.await_count == 2
-    mongo.find_one.assert_awaited_once_with('platform_certificates', {}, {})
-    minio.download_file.assert_any_await(
-        'platform/certificates/client_cert_c.pem', 'sientia-dataops', {}
-    )
-    assert (tmp_path / 'client_cert_c.pem').read_bytes() == b'cert-bytes'
-    assert (tmp_path / 'private_key_k.pem').read_bytes() == b'key-bytes'
 
 
-@pytest.mark.asyncio
-async def test_lazy_minio_builds_client_once_on_first_download():
-    from unittest.mock import MagicMock
-
-    from ingestor.connection.certs import LazyMinio
-
-    client = AsyncMock()
-    client.download_file.return_value = b'bytes'
-    factory = MagicMock(return_value=client)
-    minio = LazyMinio(factory)
-
-    factory.assert_not_called()  # no network at construction
-    assert await minio.download_file('a.pem', 'bucket', {}) == b'bytes'
-    await minio.download_file('b.pem', 'bucket', {})
-
-    factory.assert_called_once()
-    assert client.download_file.await_count == 2
-
-
-def test_build_cert_provider_is_lazy_and_uses_config(monkeypatch):
-    from unittest.mock import MagicMock
-
-    from ingestor.config import GatewayConfig
-    from ingestor.connection import certs
-
-    minio_cls = MagicMock()
-    monkeypatch.setattr(certs, 'MinioRepository', minio_cls)
-    mongo = MagicMock()
-
-    provider = certs.build_cert_provider(
-        mongo=mongo,
-        config=GatewayConfig(cert_bucket='streamlit-connectors', cert_cache_dir='certs-cache'),
-        logger=MagicMock(),
-        notification_handler=MagicMock(),
-        metrics_controller=MagicMock(),
-    )
-
-    assert provider.mongo is mongo
-    assert provider.bucket == 'streamlit-connectors'
-    assert provider.cache_dir == 'certs-cache'
-    assert isinstance(provider.minio, certs.LazyMinio)
-    minio_cls.assert_not_called()  # MinIO is only reached when a cert is needed
-
-
-def _provider(tmp_path, doc=None, data=b'pem'):
-    from unittest.mock import MagicMock
-
-    mongo = MagicMock()
-    mongo.find_one = AsyncMock(
-        return_value=doc
-        if doc is not None
-        else {
-            'client_cert': {'minio_object_name': 'platform_certificates/c.pem'},
-            'private_key': {'minio_object_name': 'platform_certificates/k.pem'},
-        }
-    )
+def _provider(tmp_path, data=b'pem'):
     minio = MagicMock()
     minio.download_file = AsyncMock(return_value=data)
-    return CertProvider(mongo=mongo, minio=minio, cache_dir=str(tmp_path), bucket='b'), minio
+    return CertProvider(minio=minio, cache_dir=str(tmp_path)), minio
+
+
+@pytest.mark.asyncio
+async def test_fetch_downloads_the_objects_the_certificate_names(tmp_path):
+    minio = AsyncMock()
+    minio.download_file.side_effect = [b'cert-bytes', b'key-bytes']
+    provider = CertProvider(minio, cache_dir=str(tmp_path))
+
+    cert, key = await provider.fetch(certificate(7))
+
+    assert (cert, key) == (str(tmp_path / '7' / 'cert.pem'), str(tmp_path / '7' / 'key.pem'))
+    assert [c.args for c in minio.download_file.await_args_list] == [
+        ('client/sientia-platform/cert.pem', 'opc-certificates', {}),
+        ('client/sientia-platform/key.pem', 'opc-certificates', {}),
+    ]
+    assert (tmp_path / '7' / 'cert.pem').read_bytes() == b'cert-bytes'
+    assert (tmp_path / '7' / 'key.pem').read_bytes() == b'key-bytes'
+
+
+@pytest.mark.asyncio
+async def test_local_files_keep_the_object_extension(tmp_path):
+    """asyncua picks the format (.pem / .der) by the extension"""
+    provider, _minio = _provider(tmp_path)
+
+    cert, key = await provider.fetch(certificate(ext='der'))
+
+    assert cert.endswith('cert.der')
+    assert key.endswith('key.der')
 
 
 @pytest.mark.asyncio
 @pytest.mark.parametrize(
-    'doc',
+    'broken',
     [
-        None,
-        {},
-        {'client_cert': {'minio_object_name': 'c.pem'}},
-        {'client_cert': None, 'private_key': {}},
+        pytest.param({'cert': None}, id='no-cert'),
+        pytest.param({'private_key': {'bucket': 'b'}}, id='key-without-object'),
+        pytest.param({'certificate_id': None}, id='no-id'),
+        pytest.param({'certificate_id': '../etc'}, id='id-not-an-integer'),
     ],
 )
-async def test_fetch_without_platform_certificate_raises_clear_error(tmp_path, doc):
-    from ingestor.connection.certs import CertificateNotConfiguredError
-
+async def test_fetch_of_an_incomplete_certificate_raises_clear_error(tmp_path, broken):
     provider, minio = _provider(tmp_path)
-    provider.mongo.find_one.return_value = doc
+    incomplete = {**certificate(), **broken}
 
-    with pytest.raises(CertificateNotConfiguredError, match='platform_certificates'):
-        await provider.fetch()
+    with pytest.raises(CertificateNotConfiguredError, match='opc_certificates|certificate_id'):
+        await provider.fetch(incomplete)
     minio.download_file.assert_not_awaited()
 
 
 @pytest.mark.asyncio
-async def test_fetch_is_cached_until_invalidated(tmp_path):
+async def test_fetch_is_cached_per_certificate_until_invalidated(tmp_path):
     provider, minio = _provider(tmp_path)
 
-    first = await provider.fetch()
-    second = await provider.fetch()
-    assert first == second
+    first = await provider.fetch(certificate(1))
+    assert await provider.fetch(certificate(1)) == first
     assert minio.download_file.await_count == 2  # cert + key, once
 
-    provider.invalidate()
-    await provider.fetch()
+    other = await provider.fetch(certificate(2, name='other'))
+    assert other != first
     assert minio.download_file.await_count == 4
 
+    provider.invalidate(1)
+    await provider.fetch(certificate(1))
+    await provider.fetch(certificate(2, name='other'))  # still cached
+    assert minio.download_file.await_count == 6
+
+
+@pytest.mark.asyncio
+async def test_a_replaced_certificate_is_downloaded_again(tmp_path):
+    """Same certificate_id, other objects in the slot: the cache does not serve the old files"""
+    provider, minio = _provider(tmp_path)
+
+    await provider.fetch(certificate(1, name='old'))
+    await provider.fetch(certificate(1, name='new'))
+
+    assert minio.download_file.await_count == 4
+    assert minio.download_file.await_args_list[-1].args[0] == 'client/new/key.pem'
+
 
 @pytest.mark.asyncio
 async def test_concurrent_fetches_download_once(tmp_path):
-    import asyncio
-
     provider, minio = _provider(tmp_path)
 
-    results = await asyncio.gather(*(provider.fetch() for _ in range(5)))
+    results = await asyncio.gather(*(provider.fetch(certificate()) for _ in range(5)))
 
     assert len(set(results)) == 1
     assert minio.download_file.await_count == 2
@@ -138,11 +111,51 @@ async def test_concurrent_fetches_download_once(tmp_path):
 
 @pytest.mark.asyncio
 async def test_download_replaces_file_atomically(tmp_path):
-    provider, minio = _provider(tmp_path, data=b'new')
-    (tmp_path / 'c.pem').write_bytes(b'old')
+    provider, _minio = _provider(tmp_path, data=b'new')
+    (tmp_path / '1').mkdir()
+    (tmp_path / '1' / 'cert.pem').write_bytes(b'old')
 
-    cert_path, _ = await provider.fetch()
+    cert_path, _ = await provider.fetch(certificate(1))
 
-    assert (tmp_path / 'c.pem').read_bytes() == b'new'
-    assert cert_path == str(tmp_path / 'c.pem')
-    assert not list(tmp_path.glob('*.tmp'))
+    assert (tmp_path / '1' / 'cert.pem').read_bytes() == b'new'
+    assert cert_path == str(tmp_path / '1' / 'cert.pem')
+    assert not list(tmp_path.glob('**/*.tmp'))
+
+
+@pytest.mark.asyncio
+async def test_lazy_minio_builds_one_client_per_bucket_on_first_download():
+    clients = {'a': AsyncMock(), 'b': AsyncMock()}
+    for client in clients.values():
+        client.download_file.return_value = b'bytes'
+    factory = MagicMock(side_effect=lambda bucket: clients[bucket])
+    minio = LazyMinio(factory)
+
+    factory.assert_not_called()  # no network at construction
+    assert await minio.download_file('x.pem', 'a', {}) == b'bytes'
+    await minio.download_file('y.pem', 'a', {})
+    await minio.download_file('z.pem', 'b', {})
+
+    assert [c.args for c in factory.call_args_list] == [('a',), ('b',)]
+    assert clients['a'].download_file.await_count == 2
+    clients['b'].download_file.assert_awaited_once_with('z.pem', 'b', {})
+
+
+def test_build_cert_provider_is_lazy_and_uses_config(monkeypatch):
+    from ingestor.config import GatewayConfig
+    from ingestor.connection import certs
+
+    minio_cls = MagicMock()
+    monkeypatch.setattr(certs, 'MinioRepository', minio_cls)
+
+    provider = certs.build_cert_provider(
+        config=GatewayConfig(cert_cache_dir='certs-cache'),
+        logger=MagicMock(),
+        notification_handler=MagicMock(),
+        metrics_controller=MagicMock(),
+    )
+
+    assert provider.cache_dir == 'certs-cache'
+    assert isinstance(provider.minio, certs.LazyMinio)
+    minio_cls.assert_not_called()  # MinIO is only reached when a cert is needed
+    provider.minio._factory('opc-certificates')
+    assert minio_cls.call_args.kwargs['bucket'] == 'opc-certificates'

tests/unit/connection/test_clock.py

@@ -5,4 +5,6 @@ def test_elapsed_is_non_negative_and_monotonic():
     clk = MonotonicClock()
     a = clk.elapsed()
     b = clk.elapsed()
-    assert a >= 0 and b >= a  # never negative even if wall clock jumps back
+    # never negative even if wall clock jumps back
+    assert a >= 0
+    assert b >= a

tests/unit/connection/test_pool.py

@@ -6,6 +6,15 @@ import pytest
 import ingestor.metrics as metrics
 from ingestor.connection.pool import OpcConnectionPool
 
+SECURITY = {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'}
+CERTIFICATE = {
+    'certificate_id': 7,
+    'application_uri': 'urn:sientia:opc-ingestor',
+    'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+    'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+}
+SECURED = {'url': 'opc.tcp://h:4840', 'security': SECURITY, 'certificate': CERTIFICATE}
+
 
 def make_pool(cert_provider=None):
     pool = OpcConnectionPool(
@@ -23,8 +32,8 @@ async def test_get_reuses_connection_per_server():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        c1 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
-        c2 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        c1 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
+        c2 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     assert c1 is c2
     assert fake_client.connect.await_count == 1
@@ -37,7 +46,7 @@ async def test_get_failure_records_metric_and_raises():
     fake_client.connect.side_effect = RuntimeError('boom')
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
         with pytest.raises(RuntimeError):
-            await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+            await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     pool.emit_metric.assert_any_await(
         metric_object=metrics.OPC_CONNECTIONS_FAILED,
@@ -48,13 +57,13 @@ async def test_get_failure_records_metric_and_raises():
     # a later successful get must reconnect (failed attempt was not cached)
     fake_client2 = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client2):
-        client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
     assert client is fake_client2
     assert fake_client2.connect.await_count == 1
 
 
 @pytest.mark.asyncio
-async def test_get_applies_security_when_requested():
+async def test_get_applies_the_certificate_and_security_of_the_server():
     cert_provider = AsyncMock()
     cert_provider.fetch.return_value = ('cert.pem', 'key.pem')
     pool = make_pool(cert_provider=cert_provider)
@@ -63,13 +72,32 @@ async def test_get_applies_security_when_requested():
         patch('ingestor.connection.pool.Client', return_value=fake_client),
         patch('ingestor.connection.pool.apply_security', new=AsyncMock()) as mock_apply,
     ):
-        await pool.get(
-            'srv',
-            {'url': 'opc.tcp://h:4840', 'server_uri': 'urn:test', 'use_security': True},
-        )
+        await pool.get('srv', SECURED)
 
-    cert_provider.fetch.assert_awaited_once()
-    mock_apply.assert_awaited_once_with(fake_client, 'urn:test', 'cert.pem', 'key.pem', None)
+    cert_provider.fetch.assert_awaited_once_with(CERTIFICATE)
+    mock_apply.assert_awaited_once_with(fake_client, SECURITY, CERTIFICATE, 'cert.pem', 'key.pem')
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    'cfg',
+    [
+        pytest.param({**SECURED, 'certificate': None}, id='no-certificate'),
+        pytest.param({**SECURED, 'security': {'mode': 'None', 'policy': 'None'}}, id='mode-none'),
+    ],
+)
+async def test_get_without_certificate_connects_without_security(cfg):
+    """No client certificate (or mode None): no security, no MinIO download (D5)"""
+    cert_provider = AsyncMock()
+    pool = make_pool(cert_provider=cert_provider)
+    with (
+        patch('ingestor.connection.pool.Client', return_value=AsyncMock()),
+        patch('ingestor.connection.pool.apply_security', new=AsyncMock()) as mock_apply,
+    ):
+        await pool.get('srv', cfg)
+
+    cert_provider.fetch.assert_not_awaited()
+    mock_apply.assert_not_awaited()
 
 
 @pytest.mark.asyncio
@@ -77,7 +105,7 @@ async def test_release_idle_evicts_and_disconnects():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     client, _ = pool._connections['srv']
     pool._connections['srv'] = (client, -1000.0)  # force idle
@@ -97,7 +125,7 @@ async def test_release_idle_keeps_recently_used():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     await pool.release_idle(max_idle_s=3600)
 
@@ -110,8 +138,8 @@ async def test_close_all_disconnects_everything():
     pool = make_pool()
     fake_a, fake_b = AsyncMock(), AsyncMock()
     with patch('ingestor.connection.pool.Client', side_effect=[fake_a, fake_b]):
-        await pool.get('a', {'url': 'opc.tcp://h:4840', 'use_security': False})
-        await pool.get('b', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('a', {'url': 'opc.tcp://h:4840', 'certificate': None})
+        await pool.get('b', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     await pool.close_all()
 
@@ -126,7 +154,7 @@ async def test_release_idle_disconnect_retries_then_gives_up():
     fake_client = AsyncMock()
     fake_client.disconnect.side_effect = RuntimeError('nope')
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     client, _ = pool._connections['srv']
     pool._connections['srv'] = (client, -1000.0)
@@ -142,7 +170,7 @@ async def test_success_path_emits_connection_metrics():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     pool.emit_metric.assert_any_await(
         metric_object=metrics.OPC_CONNECTIONS_TOTAL,
@@ -170,7 +198,7 @@ async def test_concurrent_get_same_server_connects_once():
 
     clients[0].connect.side_effect = slow_connect
 
-    cfg = {'url': 'opc.tcp://h:4840', 'use_security': False}
+    cfg = {'url': 'opc.tcp://h:4840', 'certificate': None}
     with patch('ingestor.connection.pool.Client', side_effect=clients) as ctor:
         t1 = asyncio.create_task(pool.get('srv', cfg))
         await started.wait()  # t1 is mid-connect, holding the per-server lock
@@ -191,7 +219,7 @@ async def test_release_idle_keeps_pinned_connection():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     pool.pin('srv')
     await pool.release_idle(max_idle_s=0)
@@ -205,7 +233,7 @@ async def test_release_idle_evicts_after_last_unpin():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     pool.pin('srv')
     pool.pin('srv')  # two slots subscribed on the same server
@@ -233,9 +261,9 @@ async def test_evict_disconnects_now_and_next_get_reconnects():
     pool = make_pool()
     first, second = AsyncMock(), AsyncMock()
     with patch('ingestor.connection.pool.Client', side_effect=[first, second]):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
         await pool.evict('srv')
-        client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     first.disconnect.assert_awaited_once()
     assert client is second
@@ -255,8 +283,8 @@ async def test_get_normalizes_server_id_to_str():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        c1 = await pool.get(1, {'url': 'opc.tcp://h:4840', 'use_security': False})
-        c2 = await pool.get('1', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        c1 = await pool.get(1, {'url': 'opc.tcp://h:4840', 'certificate': None})
+        c2 = await pool.get('1', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     assert c1 is c2
     assert fake_client.connect.await_count == 1
@@ -267,8 +295,8 @@ async def test_get_with_different_cfg_reuses_client_and_warns():
     pool = make_pool()
     fake_client = AsyncMock()
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
-        client = await pool.get('srv', {'url': 'opc.tcp://10.0.0.5:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
+        client = await pool.get('srv', {'url': 'opc.tcp://10.0.0.5:4840', 'certificate': None})
 
     assert client is fake_client
     assert fake_client.connect.await_count == 1
@@ -276,6 +304,21 @@ async def test_get_with_different_cfg_reuses_client_and_warns():
     assert 'url' in pool.logger.warning.call_args.args[0]
 
 
+@pytest.mark.asyncio
+async def test_get_with_another_certificate_warns():
+    cert_provider = AsyncMock()
+    cert_provider.fetch.return_value = ('cert.pem', 'key.pem')
+    pool = make_pool(cert_provider=cert_provider)
+    with (
+        patch('ingestor.connection.pool.Client', return_value=AsyncMock()),
+        patch('ingestor.connection.pool.apply_security', new=AsyncMock()),
+    ):
+        await pool.get('srv', SECURED)
+        await pool.get('srv', {**SECURED, 'certificate': {**CERTIFICATE, 'certificate_id': 8}})
+
+    assert 'certificate' in pool.logger.warning.call_args.args[0]
+
+
 @pytest.mark.asyncio
 async def test_secured_connect_failure_invalidates_cert_cache():
     from unittest.mock import MagicMock
@@ -290,9 +333,9 @@ async def test_secured_connect_failure_invalidates_cert_cache():
         patch('ingestor.connection.pool.apply_security', AsyncMock()),
     ):
         with pytest.raises(RuntimeError):
-            await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': True})
+            await pool.get('srv', SECURED)
 
-    cert_provider.invalidate.assert_called_once()
+    cert_provider.invalidate.assert_called_once_with(7)
 
 
 @pytest.mark.asyncio
@@ -305,7 +348,7 @@ async def test_insecure_connect_failure_keeps_cert_cache():
     fake_client.connect.side_effect = RuntimeError('unreachable')
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
         with pytest.raises(RuntimeError):
-            await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+            await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     cert_provider.invalidate.assert_not_called()
 
@@ -317,7 +360,7 @@ async def test_connect_identifies_the_pod_on_the_server():
     pool = make_pool()
     fake_client = MagicMock(connect=AsyncMock())
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
+        await pool.get('srv', {'url': 'opc.tcp://h:4840', 'certificate': None})
 
     assert fake_client.name == pool.pod_id
     assert fake_client.description == pool.pod_id
@@ -326,19 +369,35 @@ async def test_connect_identifies_the_pod_on_the_server():
 
 
 @pytest.mark.asyncio
-async def test_connect_server_uri_still_wins_for_application_uri():
-    pool = make_pool()
-    fake_client = MagicMock(connect=AsyncMock())
+async def test_connect_with_certificate_uses_its_application_uri():
+    """apply_security sets the certificate's URI: it must match its SAN URI
+    (BadCertificateUriInvalid otherwise)"""
+    cert_provider = AsyncMock()
+    cert_provider.fetch.return_value = ('cert.pem', 'key.pem')
+    pool = make_pool(cert_provider=cert_provider)
+    fake_client = MagicMock(connect=AsyncMock(), set_security=AsyncMock())
     with patch('ingestor.connection.pool.Client', return_value=fake_client):
-        await pool.get(
-            'srv',
-            {
-                'url': 'opc.tcp://h:4840',
-                'use_security': False,
-                'server_uri': 'urn:sientia:opc-ingestor',
-            },
-        )
+        await pool.get('srv', SECURED)
 
-    # must match the certificate SAN URI (BadCertificateUriInvalid otherwise)
     assert fake_client.application_uri == 'urn:sientia:opc-ingestor'
     assert fake_client.name == pool.pod_id
+
+
+@pytest.mark.asyncio
+async def test_config_for_returns_a_copy_of_the_live_connection_settings():
+    pool = make_pool()
+    cfg = {'url': 'opc.tcp://h:4840', 'security': SECURITY, 'certificate': None}
+    with patch('ingestor.connection.pool.Client', return_value=AsyncMock()):
+        await pool.get(1, cfg)
+
+    found = pool.config_for('1')
+    assert found == cfg
+    found['url'] = 'mutated'
+    assert pool.config_for(1)['url'] == 'opc.tcp://h:4840'
+
+    await pool.evict('1')
+    assert pool.config_for('1') is None
+
+
+def test_config_for_unknown_server_is_none():
+    assert make_pool().config_for('missing') is None

tests/unit/connection/test_security.py

@@ -1,18 +1,92 @@
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
+from asyncua import ua
+from asyncua.crypto.security_policies import (
+    SecurityPolicyAes128Sha256RsaOaep,
+    SecurityPolicyBasic256Sha256,
+)
 
-from ingestor.connection.security import SESSION_TIMEOUT_MS, apply_security
+from ingestor.connection.security import (
+    SESSION_TIMEOUT_MS,
+    UnsupportedSecurityError,
+    apply_security,
+    is_secured,
+)
+
+CERTIFICATE = {'certificate_id': 1, 'application_uri': 'urn:sientia:opc-ingestor'}
+
+
+def _client():
+    client = MagicMock()
+    client.set_security = AsyncMock()
+    return client
 
 
 @pytest.mark.asyncio
-async def test_apply_security_sets_sha256_and_channel_lifetime():
-    client = MagicMock()
-    client.set_security = AsyncMock()
-    await apply_security(client, 'urn:x', 'c.pem', 'k.pem', None)
+async def test_apply_security_uses_mode_and_policy_and_channel_lifetime():
+    client = _client()
+
+    await apply_security(
+        client, {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'}, CERTIFICATE, 'c', 'k'
+    )
+
+    assert client.application_uri == 'urn:sientia:opc-ingestor'
     assert client.session_timeout == SESSION_TIMEOUT_MS
     assert client.secure_channel_timeout == int(SESSION_TIMEOUT_MS * 1.25)
     args, kwargs = client.set_security.call_args
-    from asyncua.crypto.security_policies import SecurityPolicyBasic256Sha256
-
     assert args[0] is SecurityPolicyBasic256Sha256
+    assert kwargs == {
+        'certificate': 'c',
+        'private_key': 'k',
+        'server_certificate': None,
+        'mode': ua.MessageSecurityMode.SignAndEncrypt,
+    }
+
+
+@pytest.mark.asyncio
+async def test_apply_security_sign_with_another_policy():
+    client = _client()
+
+    await apply_security(
+        client, {'mode': 'Sign', 'policy': 'Aes128Sha256RsaOaep'}, CERTIFICATE, 'c', 'k'
+    )
+
+    args, kwargs = client.set_security.call_args
+    assert args[0] is SecurityPolicyAes128Sha256RsaOaep
+    assert kwargs['mode'] == ua.MessageSecurityMode.Sign
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    'security',
+    [
+        {'mode': 'Encrypt', 'policy': 'Basic256Sha256'},
+        {'mode': 'Sign', 'policy': 'Basic999'},
+        {'mode': 'Sign', 'policy': 'None'},
+        {},
+    ],
+)
+async def test_apply_security_rejects_unknown_mode_or_policy(security):
+    client = _client()
+
+    with pytest.raises(UnsupportedSecurityError):
+        await apply_security(client, security, CERTIFICATE, 'c', 'k')
+    client.set_security.assert_not_awaited()
+
+
+@pytest.mark.parametrize(
+    ('server_cfg', 'secured'),
+    [
+        ({'security': {'mode': 'SignAndEncrypt'}, 'certificate': CERTIFICATE}, True),
+        ({'security': {'mode': 'Sign'}, 'certificate': CERTIFICATE}, True),
+        # No certificate: no security (D5), whatever the mode
+        ({'security': {'mode': 'SignAndEncrypt'}, 'certificate': None}, False),
+        ({'security': {'mode': 'SignAndEncrypt'}}, False),
+        # mode None: no security even with a certificate
+        ({'security': {'mode': 'None'}, 'certificate': CERTIFICATE}, False),
+        ({}, False),
+    ],
+)
+def test_is_secured(server_cfg, secured):
+    assert is_secured(server_cfg) is secured

tests/unit/connection/test_servers.py

@@ -0,0 +1,149 @@
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from ingestor.connection.servers import CONNECTORS, ServerConfigResolver
+
+LOOKED_UP = {
+    'certificate_id': 1,
+    'application_uri': 'urn:sientia:opc-ingestor',
+    'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+    'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+}
+# A connector as the aggregation returns it ($lookup on opc_certificates)
+CONNECTOR = {
+    'connector_id': 'kepserver',
+    'url': 'opc.tcp://kepserver:49320',
+    'subscription_period_ms': 500,
+    'security': {
+        'mode': 'SignAndEncrypt',
+        'policy': 'Basic256Sha256',
+        'client_certificate_id': 1,
+    },
+    'certificates': [LOOKED_UP],
+}
+# The same server in the slot v2 format
+CONFIG = {
+    'server_id': 'kepserver',
+    'url': 'opc.tcp://kepserver:49320',
+    'subscription_period_ms': 500,
+    'security': {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'},
+    'certificate': LOOKED_UP,
+}
+
+
+def make_resolver(connector=None, pooled=None, ttl_s=60.0):
+    pool = MagicMock()
+    pool.config_for = MagicMock(return_value=pooled)
+    mongo = MagicMock()
+    mongo.aggregate = AsyncMock(return_value=[connector] if connector is not None else [])
+    return ServerConfigResolver(pool, mongo, MagicMock(), ttl_s=ttl_s)
+
+
+@pytest.mark.asyncio
+async def test_live_pooled_connection_wins_over_mongo():
+    """Writes reuse exactly the settings the read path opened the connection with."""
+    pooled = {'url': 'opc.tcp://read:1', 'security': CONFIG['security'], 'certificate': None}
+    resolver = make_resolver(connector=CONNECTOR, pooled=pooled)
+
+    assert await resolver.resolve('kepserver') == pooled
+    resolver.pool.config_for.assert_called_once_with('kepserver')
+    resolver.mongo.aggregate.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_connector_with_its_certificate_in_the_slot_format():
+    resolver = make_resolver(connector=CONNECTOR)
+
+    assert await resolver.resolve('kepserver') == CONFIG
+    collection, pipeline, _ = resolver.mongo.aggregate.await_args.args
+    assert collection == CONNECTORS
+    assert pipeline[0] == {
+        '$match': {'connector_id': 'kepserver', 'type': 'opc_ua', 'status': 'Active'}
+    }
+    # The same rule as the orchestrator: only an active client certificate (D5)
+    [lookup] = [stage['$lookup'] for stage in pipeline if '$lookup' in stage]
+    assert lookup['from'] == 'opc_certificates'
+    assert lookup['pipeline'][0]['$match']['status'] == 'active'
+    assert lookup['pipeline'][0]['$match']['kind'] == 'client'
+    resolver.logger.warning.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_connector_without_certificate_id_connects_without_security():
+    connector = {
+        **CONNECTOR,
+        'security': {'mode': 'None', 'policy': 'None', 'client_certificate_id': None},
+        'certificates': [],
+    }
+    resolver = make_resolver(connector=connector)
+
+    cfg = await resolver.resolve('kepserver')
+
+    assert cfg['certificate'] is None
+    assert cfg['security'] == {'mode': 'None', 'policy': 'None'}
+    resolver.logger.warning.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_certificate_id_without_an_active_client_certificate_warns():
+    resolver = make_resolver(connector={**CONNECTOR, 'certificates': []})
+
+    cfg = await resolver.resolve('kepserver')
+
+    assert cfg == {**CONFIG, 'certificate': None}
+    assert 'client_certificate_id 1' in resolver.logger.warning.call_args.args[0]
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    'connector',
+    [
+        pytest.param({**CONNECTOR, 'url': ''}, id='no-url'),
+        pytest.param({**CONNECTOR, 'security': {'mode': 'Sign'}}, id='no-policy'),
+        pytest.param({k: v for k, v in CONNECTOR.items() if k != 'security'}, id='no-security'),
+    ],
+)
+async def test_incomplete_connectors_are_not_found(connector):
+    resolver = make_resolver(connector=connector)
+
+    assert await resolver.resolve('kepserver') is None
+    resolver.logger.warning.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_unknown_server_is_cached_briefly():
+    resolver = make_resolver(ttl_s=60.0)
+    resolver.missing_ttl_s = 10.0
+    resolver.clock = MagicMock()
+    resolver.clock.elapsed.side_effect = [0.0, 5.0, 11.0]
+
+    assert await resolver.resolve('9') is None
+    assert await resolver.resolve('9') is None  # within missing_ttl_s: no lookup
+    assert await resolver.resolve('9') is None  # expired: looked up again
+    assert resolver.mongo.aggregate.await_count == 2
+    assert resolver.logger.warning.call_count == 2
+
+
+@pytest.mark.asyncio
+async def test_lookups_are_cached_for_the_ttl():
+    resolver = make_resolver(connector=CONNECTOR, ttl_s=60.0)
+    resolver.clock = MagicMock()
+    resolver.clock.elapsed.side_effect = [0.0, 30.0, 61.0]
+
+    first = await resolver.resolve('kepserver')
+    first['url'] = 'mutated by the caller'
+    second = await resolver.resolve('kepserver')  # within the TTL: cached, and a copy
+    await resolver.resolve('kepserver')  # expired: looked up again
+
+    assert second['url'] == 'opc.tcp://kepserver:49320'
+    assert resolver.mongo.aggregate.await_count == 2
+
+
+@pytest.mark.asyncio
+async def test_mongo_errors_propagate_to_the_caller():
+    resolver = make_resolver()
+    resolver.mongo.aggregate = AsyncMock(side_effect=RuntimeError('mongo down'))
+
+    with pytest.raises(RuntimeError, match='mongo down'):
+        await resolver.resolve('kepserver')

tests/unit/engines/test_write.py

@@ -7,8 +7,22 @@ from asyncua import ua
 import ingestor.metrics as metrics
 from ingestor.engines.write import WriteEngine
 
+SERVER_CFG = {
+    'server_id': 'srv1',
+    'url': 'opc.tcp://kepserver:49320',
+    'security': {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'},
+    'certificate': None,
+}
+
+
+def make_resolver(cfg=SERVER_CFG):
+    resolver = MagicMock()
+    resolver.resolve = AsyncMock(return_value=cfg)
+    return resolver
+
 
 def make_engine(**kwargs):
+    kwargs.setdefault('servers', make_resolver())
     eng = WriteEngine(
         pool=AsyncMock(),
         sink=AsyncMock(),
@@ -126,6 +140,36 @@ async def test_write_engine_flags_off_omit_statuscode_and_timestamp():
     assert dv.SourceTimestamp is None
 
 
+@pytest.mark.asyncio
+async def test_write_engine_timestamp_off_keeps_statuscode():
+    eng = make_engine(write_timestamp=False)
+    node = make_node()
+    eng.pool.get.return_value = make_client(node)
+
+    await eng.write(base_cmd())
+
+    dv = node.write_value.await_args.args[0]
+    assert dv.Value.Value == 42.0
+    assert dv.SourceTimestamp is None
+    assert dv.StatusCode is not None
+    assert dv.StatusCode.is_good()
+
+
+@pytest.mark.asyncio
+async def test_write_engine_quality_off_keeps_timestamp():
+    # The command has no write_quality, so the engine (env) default applies.
+    eng = make_engine(write_quality=False)
+    node = make_node()
+    eng.pool.get.return_value = make_client(node)
+
+    await eng.write(base_cmd())
+
+    dv = node.write_value.await_args.args[0]
+    assert dv.Value.Value == 42.0
+    assert dv.StatusCode is None
+    assert dv.SourceTimestamp == datetime.fromisoformat('2026-07-13T12:00:00Z')
+
+
 @pytest.mark.asyncio
 async def test_per_message_flag_override_disables_timestamp():
     # Engine default is True, but the command explicitly turns it off.
@@ -257,3 +301,106 @@ async def test_no_rate_limit_when_min_pause_is_zero():
         await eng.write(base_cmd())
         await eng.write(base_cmd())
         sleep_mock.assert_not_awaited()
+
+
+# --- SIENTIAPDE-1975: server resolution (GW1) and error reporting (GW4) ---
+
+
+@pytest.mark.asyncio
+async def test_write_uses_the_resolved_server_connection():
+    """The C2 command of the Laborious carries only the server_id."""
+    eng = make_engine()
+    eng.pool.get.return_value = make_client()
+
+    await eng.write(base_cmd())
+
+    eng.servers.resolve.assert_awaited_once_with('srv1')
+    eng.pool.get.assert_awaited_once_with('srv1', SERVER_CFG)
+
+
+@pytest.mark.asyncio
+async def test_write_unknown_server_records_error_without_connecting():
+    eng = make_engine(servers=make_resolver(cfg=None))
+
+    result = await eng.write(base_cmd())
+
+    assert result.status == 'error'
+    assert result.opc_status_code == 'server_not_found'
+    eng.pool.get.assert_not_awaited()
+    eng.sink.update_write_status.assert_awaited_once_with(base_cmd(), result)
+
+
+@pytest.mark.asyncio
+async def test_write_server_lookup_failure_records_error():
+    resolver = make_resolver()
+    resolver.resolve.side_effect = RuntimeError('mongo down')
+    eng = make_engine(servers=resolver)
+
+    result = await eng.write(base_cmd())
+
+    assert result.status == 'error'
+    assert result.opc_status_code == 'server_lookup'
+    assert 'mongo down' in result.message
+    eng.pool.get.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_write_ignores_a_connection_carried_by_the_command():
+    """The server is always resolved by server_id (SIENTIAPDE-1974): connection fields
+    in the command are not an override"""
+    eng = make_engine()
+    eng.pool.get.return_value = make_client()
+
+    await eng.write(base_cmd(url='opc.tcp://h:4840'))
+
+    eng.pool.get.assert_awaited_once_with('srv1', SERVER_CFG)
+
+
+@pytest.mark.asyncio
+async def test_write_without_resolver_is_server_not_found():
+    eng = make_engine(servers=None)
+
+    result = await eng.write(base_cmd(url='opc.tcp://h:4840'))
+
+    assert result.opc_status_code == 'server_not_found'
+    eng.pool.get.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_write_error_logs_the_reason_and_sets_the_model_status():
+    eng = make_engine()
+    node = make_node()
+    node.write_value.side_effect = RuntimeError('BadWriteNotSupported')
+    eng.pool.get.return_value = make_client(node)
+
+    await eng.write(base_cmd())
+
+    logged = eng.logger.error.call_args.args[0]
+    assert 'RuntimeError' in logged
+    assert 'BadWriteNotSupported' in logged
+    assert 'addr=ns=2;i=5' in logged
+    assert 'model_id=m1' in logged
+    status_call = next(
+        c
+        for c in eng.emit_metric.await_args_list
+        if c.kwargs['metric_object'] is metrics.OPC_WRITE_STATUS_BY_MODEL
+    )
+    # Same series as a success, so it shows the last outcome.
+    assert status_call.kwargs['value'] == 0
+    assert status_call.kwargs['tags'] == {'pod_id': eng.pod_id, 'model_id': 'm1', 'status': 'ok'}
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize('timestamp', [None, 'not-a-timestamp'])
+async def test_write_bad_timestamp_records_error_without_raising(timestamp):
+    eng = make_engine(write_timestamp=True)
+    cmd = base_cmd(timestamp=timestamp)
+    if timestamp is None:
+        del cmd['timestamp']
+
+    result = await eng.write(cmd)
+
+    assert result.status == 'error'
+    assert result.opc_status_code == 'bad_timestamp'
+    eng.pool.get.assert_not_awaited()
+    eng.sink.update_write_status.assert_awaited_once()

tests/unit/io/test_data_sink_publish.py

@@ -67,26 +67,3 @@ async def test_publish_reading_emits_tag_value_metric_per_name():
         value=42,
         tags={'pod_id': dm.pod_id, 'tag_name': 'Counter', 'model_id': '1'},
     )
-
-
-@pytest.mark.asyncio
-async def test_publish_reading_without_model_id_keeps_legacy_doc():
-    """Names converted from a slot v1 carry no model_id: the document must be the
-    same as the legacy OpcManager one (SIENTIAPDE-1974 NF2)."""
-    sink, dm = make_sink()
-    names = [{'collection': 'raw_x', 'tag_name': 'Counter'}]
-
-    await sink.publish_reading(
-        tag='ns=2;i=2', value=42, timestamp='2026-07-13 00:00:00+0000', names=names
-    )
-
-    collection, doc = dm.publish.await_args_list[0].args
-    assert collection == 'raw_x'
-    assert doc == {
-        'tag': 'ns=2;i=2',
-        'name': 'Counter',
-        'timestamp': '2026-07-13 00:00:00+0000',
-        'value': 42,
-    }
-    _, kwargs = sink.emit_metric.await_args
-    assert kwargs['tags']['model_id'] == ''

tests/unit/io/test_data_sink_status.py

@@ -1,89 +1,150 @@
-from unittest.mock import MagicMock
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
+from sqlalchemy import create_engine, text
+from sqlalchemy.dialects import postgresql
 
+import ingestor.metrics as metrics
 from ingestor.engines.write import WriteResult
-from ingestor.io.data_sink import DataSink
+from ingestor.io.data_sink import DataSink, write_status_statements
+
+CMD = {
+    'server_id': '1',
+    'addr': 'ns=2;s=Pred',
+    'schema': 'sientia_data',
+    'table_name': 'pred_m1',
+    'model_id': '1',
+    'timestamp': '2026-07-13T00:00:00Z',
+}
 
 
-def make_sink():
+def _result(status):
+    return WriteResult(ok=status == 'ok', status=status, opc_status_code='x', message='')
+
+
+def make_sink(rowcount=1, existing_row=True):
     postgres = MagicMock()
     connection = MagicMock()
+    connection.execute.return_value.rowcount = rowcount
+    connection.execute.return_value.first.return_value = (1,) if existing_row else None
     postgres.engine.begin.return_value.__enter__.return_value = connection
-    sink = DataSink(data_manager=MagicMock(), postgres=postgres)
+    data_manager = MagicMock()
+    data_manager.emit_metric = AsyncMock()
+    sink = DataSink(data_manager=data_manager, postgres=postgres)
     return sink, connection
 
 
+def _outcome_metric(sink):
+    calls = [
+        c
+        for c in sink.data_manager.emit_metric.await_args_list
+        if c.kwargs['metric_object'] is metrics.OPC_WRITE_STATUS_UPDATE_TOTAL
+    ]
+    assert len(calls) == 1
+    return calls[0].kwargs['tags']['result']
+
+
 @pytest.mark.asyncio
-async def test_update_write_status_targets_model_row():
+async def test_update_write_status_targets_model_row_with_precedence():
     sink, connection = make_sink()
-    cmd = {
-        'schema': 'sientia_data',
-        'table_name': 'pred_m1',
-        'model_id': '1',
-        'timestamp': '2026-07-13T00:00:00Z',
-    }
-    result = WriteResult(ok=True, status='ok', opc_status_code='Good', message='')
 
-    await sink.update_write_status(cmd, result)
+    outcome = await sink.update_write_status(CMD, _result('ok'))
 
+    assert outcome == 'updated'
     assert connection.execute.call_count == 1
-    stmt, params = connection.execute.call_args[0]
-    sql = str(stmt)
-    assert 'update' in sql.lower() and 'write_status' in sql.lower()
-    assert 'sientia_data.pred_m1' in sql
+    (stmt,) = connection.execute.call_args[0]
+    compiled = stmt.compile(dialect=postgresql.dialect())
+    sql = str(compiled)
+    assert sql.startswith('UPDATE sientia_data.pred_m1 SET write_status=')
+    assert 'CASE sientia_data.pred_m1.write_status WHEN' in sql
     # values must be bound params, never interpolated into the SQL text itself
-    assert params == {'status': 'ok', 'timestamp': '2026-07-13T00:00:00Z', 'model_id': '1'}
-    assert 'ok' not in sql
     assert '2026-07-13T00:00:00Z' not in sql
+    assert "'ok'" not in sql
+    assert compiled.params['write_status'] == 'ok'
+    assert '2026-07-13T00:00:00Z' in compiled.params.values()
+    assert _outcome_metric(sink) == 'updated'
 
 
 @pytest.mark.asyncio
-async def test_update_write_status_rejects_bad_schema():
-    sink, connection = make_sink()
-    cmd = {
-        'schema': 'a; DROP TABLE x',
-        'table_name': 'pred_m1',
-        'model_id': '1',
-        'timestamp': '2026-07-13T00:00:00Z',
-    }
-    result = WriteResult(ok=False, status='error', opc_status_code='Bad', message='x')
+async def test_update_write_status_kept_when_the_row_has_a_worse_outcome():
+    sink, _ = make_sink(rowcount=0, existing_row=True)
 
-    with pytest.raises(ValueError):
-        await sink.update_write_status(cmd, result)
-
-    connection.execute.assert_not_called()
+    assert await sink.update_write_status(CMD, _result('ok')) == 'kept'
+    assert _outcome_metric(sink) == 'kept'
 
 
 @pytest.mark.asyncio
-async def test_update_write_status_rejects_trailing_newline_identifier():
-    sink, connection = make_sink()
-    cmd = {
-        'schema': 'sientia_data\n',
-        'table_name': 'pred_m1',
-        'model_id': '1',
-        'timestamp': '2026-07-13T00:00:00Z',
-    }
-    result = WriteResult(ok=True, status='ok', opc_status_code='Good', message='')
+async def test_update_write_status_row_not_found_is_logged():
+    """E.g. the Laborious INSERT failed and it wrote to OPC anyway (SIENTIAPDE-1975 D10)."""
+    sink, _ = make_sink(rowcount=0, existing_row=False)
 
-    with pytest.raises(ValueError):
-        await sink.update_write_status(cmd, result)
-
-    connection.execute.assert_not_called()
+    assert await sink.update_write_status(CMD, _result('error')) == 'row_not_found'
+    assert 'no prediction row' in sink.data_manager.logger.warning.call_args.args[0]
+    assert _outcome_metric(sink) == 'row_not_found'
 
 
 @pytest.mark.asyncio
-async def test_update_write_status_rejects_bad_table_name():
+async def test_update_write_status_database_error_is_not_raised():
     sink, connection = make_sink()
-    cmd = {
-        'schema': 'sientia_data',
-        'table_name': 'pred_m1; DROP TABLE x',
-        'model_id': '1',
-        'timestamp': '2026-07-13T00:00:00Z',
-    }
-    result = WriteResult(ok=False, status='error', opc_status_code='Bad', message='x')
+    connection.execute.side_effect = RuntimeError('column "write_status" does not exist')
 
-    with pytest.raises(ValueError):
-        await sink.update_write_status(cmd, result)
+    assert await sink.update_write_status(CMD, _result('ok')) == 'error'
+    assert 'write_status' in sink.data_manager.logger.warning.call_args.args[0]
+    assert _outcome_metric(sink) == 'error'
 
+
+@pytest.mark.parametrize(
+    ('field', 'value'),
+    [
+        ('schema', 'a; DROP TABLE x'),
+        ('schema', 'sientia_data\n'),
+        ('table_name', 'pred_m1; DROP TABLE x'),
+        ('schema', None),
+        ('timestamp', None),
+        ('model_id', None),
+    ],
+)
+@pytest.mark.asyncio
+async def test_update_write_status_rejects_invalid_commands(field, value):
+    sink, connection = make_sink()
+
+    outcome = await sink.update_write_status({**CMD, field: value}, _result('error'))
+
+    assert outcome == 'invalid'
     connection.execute.assert_not_called()
+    assert _outcome_metric(sink) == 'invalid'
+
+
+def _apply(initial, answers):
+    """Run the real statements on SQLite for each answer; return the final status."""
+    engine = create_engine('sqlite://')
+    with engine.begin() as connection:
+        connection.execute(
+            text('CREATE TABLE pred (model_id INTEGER, timestamp TEXT, write_status TEXT)')
+        )
+        connection.execute(
+            text('INSERT INTO pred VALUES (1, :ts, :status)'),
+            {'ts': '2026-07-13T00:00:00Z', 'status': initial},
+        )
+        for answer in answers:
+            update_stmt, exists_stmt = write_status_statements(
+                None, 'pred', answer, '2026-07-13T00:00:00Z', 1
+            )
+            connection.execute(update_stmt)
+            assert connection.execute(exists_stmt).first() is not None
+        return connection.execute(text('SELECT write_status FROM pred')).scalar()
+
+
+@pytest.mark.parametrize(
+    ('initial', 'answers', 'expected'),
+    [
+        ('pending', ['ok'], 'ok'),
+        ('pending', ['error', 'ok'], 'error'),
+        ('pending', ['ok', 'error'], 'error'),
+        ('pending', ['session_bad', 'error', 'ok'], 'session_bad'),
+        ('error', ['ok'], 'error'),
+        (None, ['ok'], 'ok'),
+    ],
+)
+def test_update_statement_keeps_the_worst_answer(initial, answers, expected):
+    assert _apply(initial, answers) == expected

tests/unit/io/test_slots.py

@@ -1,11 +1,24 @@
-from ingestor.io.slots import parse_slot
+import pytest
+
+from ingestor.io.slots import CONNECTION_FIELDS, parse_slot
+
+SECURITY = {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'}
+CERTIFICATE = {
+    'certificate_id': 1,
+    'application_uri': 'urn:sientia:opc-ingestor',
+    'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+    'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+}
+NAME = {'collection': 'c', 'tag_name': 't', 'model_name': 'm', 'model_id': '1'}
 
 RAW = {
     'server1': {
         'server_id': '1',
+        'name': 'server1',
         'url': 'opc.tcp://h:4840',
-        'use_security': True,
         'subscription_period_ms': 1000,
+        'security': SECURITY,
+        'certificate': CERTIFICATE,
         'tags': {
             'ns=2;i=2': {
                 'frequency': '15000',
@@ -30,6 +43,17 @@ RAW = {
 }
 
 
+def _server(**fields):
+    server = {
+        'server_id': '1',
+        'url': 'u',
+        'security': {'mode': 'None', 'policy': 'None'},
+        'certificate': None,
+        'tags': {'ns=2;i=1': {'frequency': '1000', 'names': [NAME]}},
+    }
+    return {'s': {**server, **fields}}
+
+
 def test_parse_slot_multi_name():
     slot = parse_slot(RAW)
     tag = slot['server1']['tags']['ns=2;i=2']
@@ -37,127 +61,71 @@ def test_parse_slot_multi_name():
     assert tag['active_read']['cycle_multiple'] == 3
 
 
-def test_parse_slot_defaults_active_read_disabled():
-    raw = {
-        's': {
-            'server_id': '1',
-            'url': 'u',
-            'tags': {
-                'ns=2;i=1': {
-                    'frequency': '1000',
-                    'names': [
-                        {'collection': 'c', 'tag_name': 't', 'model_name': 'm', 'model_id': '1'}
-                    ],
-                }
-            },
-        }
+def test_parse_slot_keeps_security_and_certificate():
+    server = parse_slot(RAW)['server1']
+
+    assert server['security'] == SECURITY
+    assert server['certificate'] == CERTIFICATE
+    assert {field: server[field] for field in CONNECTION_FIELDS} == {
+        'url': 'opc.tcp://h:4840',
+        'subscription_period_ms': 1000,
+        'security': SECURITY,
+        'certificate': CERTIFICATE,
     }
-    tag = parse_slot(raw)['s']['tags']['ns=2;i=1']
-    assert tag['active_read'] == {'enabled': False}
 
 
-def test_parse_slot_rejects_tag_without_names():
-    raw = {'s': {'server_id': '1', 'url': 'u', 'tags': {'ns=2;i=1': {'frequency': '1000'}}}}
-    import pytest
-
-    with pytest.raises((KeyError, ValueError)):
-        parse_slot(raw)
-
-
-RAW_V1 = {
-    'kepserver': {
-        'name': 'kepserver',
-        'server_id': '1',
-        'url': 'opc.tcp://kepserver:49320',
-        'server_uri': 'urn:sientia:opc-ingestor',
-        'cert_path': '/app/certs/opc-ingestor-cert.pem',
-        'private_key_path': '/app/certs/opc-ingestor-key.pem',
-        'server_cert_path': None,
-        'subscription_period_ms': 15000.0,
-        'tags': {
-            'ns=2;s=A.TargetSin': {
-                'aggr_func': 'lts',
-                'frequency': 30000,
-                'server_id': '1',
-                'tag_address': 'ns=2;s=A.TargetSin',
-                'tag_name': 'TargetSin',
-                'topics': ['raw_scouter-sin-approx', 'raw_other-model'],
-            }
-        },
-    }
-}
-
-
-def test_parse_slot_converts_v1_topics_to_names():
-    """Slot v1 (current Orchestrator) is read as v2: one name per topic, no model_id,
-    so the documents stay identical to the legacy ones (SIENTIAPDE-1974 G1)."""
-    server = parse_slot(RAW_V1)['kepserver']
-    tag = server['tags']['ns=2;s=A.TargetSin']
-
-    assert tag['names'] == [
-        {'collection': 'raw_scouter-sin-approx', 'tag_name': 'TargetSin'},
-        {'collection': 'raw_other-model', 'tag_name': 'TargetSin'},
-    ]
-    assert tag['frequency'] == 30000
-    assert tag['active_read'] == {'enabled': False}
-
-
-def test_parse_slot_v1_cert_path_means_security_but_path_is_dropped():
-    server = parse_slot(RAW_V1)['kepserver']
-
-    assert server['use_security'] is True
-    assert server['name'] == 'kepserver'
-    assert server['server_id'] == '1'
-    assert server['subscription_period_ms'] == 15000.0
-    # the certificate always comes from MinIO now: no file path survives the parse
-    assert 'cert_path' not in server
-    assert 'private_key_path' not in server
-
-
-def test_parse_slot_v1_without_cert_path_is_insecure():
-    raw = {
-        's': {
-            'server_id': '2',
-            'url': 'u',
-            'cert_path': None,
-            'tags': {'ns=2;i=1': {'tag_name': 't', 'frequency': '1000', 'topics': ['raw_c']}},
-        }
-    }
+def test_parse_slot_without_certificate_key_means_no_certificate():
+    raw = _server()
+    del raw['s']['certificate']
 
     server = parse_slot(raw)['s']
 
-    assert server['use_security'] is False
+    assert server['certificate'] is None
     assert server['name'] == 's'  # falls back to the slot key
 
 
-def test_parse_slot_v2_explicit_use_security_wins():
-    raw = {
-        's': {
-            'server_id': '1',
-            'url': 'u',
-            'use_security': False,
-            'cert_path': '/legacy/path',
-            'tags': {
-                'ns=2;i=1': {
-                    'frequency': '1000',
-                    'names': [{'collection': 'c', 'tag_name': 't', 'model_id': '1'}],
+def test_parse_slot_defaults_active_read_disabled():
+    tag = parse_slot(_server())['s']['tags']['ns=2;i=1']
+    assert tag['active_read'] == {'enabled': False}
+
+
+@pytest.mark.parametrize(
+    'raw',
+    [
+        pytest.param(_server(tags={'ns=2;i=1': {'frequency': '1000'}}), id='tag-without-names'),
+        pytest.param(
+            _server(tags={'ns=2;i=1': {'frequency': '1', 'names': [{'collection': 'c'}]}}),
+            id='name-without-tag-name',
+        ),
+        pytest.param(
+            _server(
+                tags={
+                    'ns=2;i=1': {
+                        'frequency': '1',
+                        'names': [{'collection': 'c', 'tag_name': 't'}],
+                    }
+                }
+            ),
+            id='name-without-model-id',
+        ),
+        pytest.param(_server(security=None), id='no-security'),
+        # Slot v1 (an Orchestrator before SIENTIAPDE-1974): no longer accepted
+        pytest.param(
+            {
+                'kepserver': {
+                    'server_id': '1',
+                    'url': 'opc.tcp://kepserver:49320',
+                    'server_uri': 'urn:sientia:opc-ingestor',
+                    'cert_path': '/app/certs/opc-ingestor-cert.pem',
+                    'tags': {
+                        'ns=2;s=A': {'tag_name': 'A', 'frequency': 30000, 'topics': ['raw_x']}
+                    },
                 }
             },
-        }
-    }
-
-    assert parse_slot(raw)['s']['use_security'] is False
-
-
-def test_parse_slot_rejects_v1_tag_without_tag_name():
-    raw = {
-        's': {
-            'server_id': '1',
-            'url': 'u',
-            'tags': {'ns=2;i=1': {'frequency': '1', 'topics': ['c']}},
-        }
-    }
-    import pytest
-
-    with pytest.raises(ValueError):
+            id='slot-v1',
+        ),
+    ],
+)
+def test_parse_slot_rejects_invalid_slots(raw):
+    with pytest.raises((KeyError, ValueError)):
         parse_slot(raw)

tests/unit/managers/test_ingestor_manager.py

@@ -9,7 +9,6 @@ from ingestor.config import GatewayConfig
 from ingestor.connection.pool import OpcConnectionPool
 from ingestor.io.slots import parse_slot
 from ingestor.managers.ingestor_manager import IngestorManager
-from ingestor.managers.opc_manager import OpcManager
 from ingestor.managers.server_reader import ServerReader
 
 metadata = {
@@ -22,17 +21,27 @@ metadata = {
 }
 
 
-def raw_slot_v1(tag_name='Counter', address='ns=2;i=2'):
-    """A slot as the current (v1) Orchestrator writes it to Redis."""
+SECURITY = {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'}
+CERTIFICATE = {
+    'certificate_id': 1,
+    'application_uri': 'urn:sientia:opc-ingestor',
+    'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+    'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+}
+
+
+def raw_slot(tag_name='Counter', address='ns=2;i=2'):
+    """A slot v2 as the Orchestrator writes it to Redis (contract C1)."""
+    name = {'collection': 'raw_a', 'tag_name': tag_name, 'model_id': '1', 'model_name': 'm'}
     return {
         'server1': {
             'name': 'server1',
             'server_id': '1',
             'url': 'opc.tcp://localhost:4840',
-            'server_uri': 'urn:sientia:opc-ingestor',
-            'cert_path': '/app/certs/opc-ingestor-cert.pem',
             'subscription_period_ms': 500.0,
-            'tags': {address: {'tag_name': tag_name, 'frequency': '1000', 'topics': ['raw_a']}},
+            'security': SECURITY,
+            'certificate': CERTIFICATE,
+            'tags': {address: {'frequency': '1000', 'names': [name]}},
         }
     }
 
@@ -124,7 +133,6 @@ def test___init__(
     # Read path (SIENTIAPDE-1974): pool + read sink built here, nothing connected yet.
     assert isinstance(ingestor.pool, OpcConnectionPool)
     assert ingestor.pool.cert_provider is ingestor.cert_provider
-    assert ingestor.cert_provider.mongo is data_manager_mock.return_value.mongo_repository
     assert ingestor.sink.data_manager is data_manager_mock.return_value
     assert ingestor.sink.postgres is None
 
@@ -143,10 +151,9 @@ def test___init___cert_provider_uses_gateway_config(resource_manager_mock, data_
         notification_handler=MagicMock(),
         metadata=metadata['metadata'],
         metrics_controller=MagicMock(),
-        gateway_config=GatewayConfig(cert_bucket='my-bucket', cert_cache_dir='certs-cache'),
+        gateway_config=GatewayConfig(cert_cache_dir='certs-cache'),
     )
 
-    assert ingestor.cert_provider.bucket == 'my-bucket'
     assert ingestor.cert_provider.cache_dir == 'certs-cache'
 
 
@@ -157,9 +164,9 @@ async def test_initialize_opc_from_config(server_reader, ingestor_manager):
         'name': 'server1',
         'server_id': '1',
         'url': 'opc.tcp://localhost:4840',
-        'server_uri': 'urn:sientia:opc-ingestor',
-        'use_security': True,
         'subscription_period_ms': 1000,
+        'security': SECURITY,
+        'certificate': CERTIFICATE,
     }
 
     server_reader.return_value = MagicMock(connect=AsyncMock())
@@ -191,9 +198,9 @@ async def test_initialize_opc_from_config_exception(
         'name': 'server1',
         'server_id': '1',
         'url': 'opc.tcp://localhost:4840',
-        'server_uri': 'urn:sientia:opc-ingestor',
-        'use_security': True,
         'subscription_period_ms': 1000,
+        'security': SECURITY,
+        'certificate': CERTIFICATE,
     }
 
     ingestor_manager.logger.error = MagicMock()
@@ -483,13 +490,13 @@ async def test_get_number_of_slots_empty(metrics, ingestor_manager):
 @mark.asyncio
 async def test_get_slot_leases_1_success(ingestor_manager):
     ingestor_manager.resource_manager.lease_tag = AsyncMock(return_value=True)
-    ingestor_manager.resource_manager.get_tag_slot = AsyncMock(return_value=raw_slot_v1())
+    ingestor_manager.resource_manager.get_tag_slot = AsyncMock(return_value=raw_slot())
 
     ingestor_manager.number_of_slots = 1
     result = await ingestor_manager.get_slot_leases()
 
     # Stored already normalized to slot v2 (v1 converted by parse_slot).
-    assert result == {'1': parse_slot(raw_slot_v1())}
+    assert result == {'1': parse_slot(raw_slot())}
     assert ingestor_manager.managed_tags == result
 
 
@@ -497,22 +504,22 @@ async def test_get_slot_leases_1_success(ingestor_manager):
 async def test_get_slot_leases_2_success(ingestor_manager):
     ingestor_manager.resource_manager.lease_tag = AsyncMock(side_effect=[True, True])
     ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
-        side_effect=[raw_slot_v1('Counter'), raw_slot_v1('Ramp', 'ns=2;i=3')]
+        side_effect=[raw_slot('Counter'), raw_slot('Ramp', 'ns=2;i=3')]
     )
 
     ingestor_manager.number_of_slots = 2
     result = await ingestor_manager.get_slot_leases(max_slots=2)
 
     assert result == {
-        '1': parse_slot(raw_slot_v1('Counter')),
-        '2': parse_slot(raw_slot_v1('Ramp', 'ns=2;i=3')),
+        '1': parse_slot(raw_slot('Counter')),
+        '2': parse_slot(raw_slot('Ramp', 'ns=2;i=3')),
     }
 
 
 @mark.asyncio
 async def test_get_slot_leases_skips_malformed_slot(ingestor_manager):
     ingestor_manager.resource_manager.lease_tag = AsyncMock(return_value=True)
-    # tag without names/topics/frequency
+    # tag without names/frequency
     ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
         return_value={'server1': {'server_id': '1', 'url': 'u', 'tags': {'ns=2;i=2': {}}}}
     )
@@ -624,8 +631,8 @@ async def test_unsubscribe_slot_reader_failure_does_not_raise(ingestor_manager,
 
 @mark.asyncio
 async def test_unsubscribe_slot_with_real_readers(ingestor_manager):
-    """Contract: both real readers keep `subscriptions` keyed by slot, and
-    unsubscribe_slot closes the slot's subscription on each of them"""
+    """Contract: the real reader keeps `subscriptions` keyed by slot, and
+    unsubscribe_slot closes the slot's subscription"""
     v2_subscription = AsyncMock()
     client = MagicMock(create_subscription=AsyncMock(return_value=v2_subscription))
     pool = MagicMock(get=AsyncMock(return_value=client), evict=AsyncMock())
@@ -646,35 +653,13 @@ async def test_unsubscribe_slot_with_real_readers(ingestor_manager):
     server_reader.engine.emit_metric = AsyncMock()
     await server_reader.create_subscription('slot1')
 
-    with patch('ingestor.managers.opc_manager.metrics'):
-        legacy_reader = OpcManager(
-            name='legacy',
-            url='opc.tcp://legacy:4840',
-            data_manager=AsyncMock(),
-            subscription_period_ms=1000,
-            logger=MagicMock(),
-            server_uri='opc.tcp://legacy:4840',
-            notification_handler=MagicMock(),
-            metadata={},
-            metrics_controller=AsyncMock(),
-        )
-    legacy_reader.emit_metric = AsyncMock()
-    legacy_subscription = AsyncMock()
-    legacy_reader.client = MagicMock(
-        create_subscription=AsyncMock(return_value=legacy_subscription)
-    )
-    await legacy_reader.create_subscription('slot1')
-
     assert 'slot1' in server_reader.subscriptions
-    assert 'slot1' in legacy_reader.subscriptions
-    ingestor_manager.opc_managers = {'kepserver': server_reader, 'legacy': legacy_reader}
+    ingestor_manager.opc_managers = {'kepserver': server_reader}
 
     await ingestor_manager.unsubscribe_slot('slot1')
 
     v2_subscription.delete.assert_awaited_once()
-    legacy_subscription.delete.assert_awaited_once()
     assert 'slot1' not in server_reader.subscriptions
-    assert 'slot1' not in legacy_reader.subscriptions
     pool.pin.assert_called_once_with('1')
     pool.unpin.assert_called_once_with('1')
 
@@ -683,13 +668,13 @@ async def test_unsubscribe_slot_with_real_readers(ingestor_manager):
 async def test_update_slot_config_unsubscribes_removed_slot(ingestor_manager, reader_double):
     """A slot deleted from Redis is unsubscribed right away, not left to the main loop"""
     ingestor_manager.managed_tags = {
-        'slot1': parse_slot(raw_slot_v1('Same')),
-        'slot2': parse_slot(raw_slot_v1('Same')),
+        'slot1': parse_slot(raw_slot('Same')),
+        'slot2': parse_slot(raw_slot('Same')),
     }
     reader = reader_double('slot1', 'slot2')
     ingestor_manager.opc_managers = {'test_server': reader}
     ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
-        side_effect=lambda slot: raw_slot_v1('Same') if slot == 'slot1' else None
+        side_effect=lambda slot: raw_slot('Same') if slot == 'slot1' else None
     )
     ingestor_manager.resource_manager.renew_tag_lease = AsyncMock()
 
@@ -703,20 +688,20 @@ async def test_update_slot_config_unsubscribes_removed_slot(ingestor_manager, re
 @mark.asyncio
 async def test_update_slot_config(ingestor_manager):
     ingestor_manager.managed_tags = {
-        'slot1': parse_slot(raw_slot_v1('Old')),
-        'slot2': parse_slot(raw_slot_v1('Same')),
-        'slot3': parse_slot(raw_slot_v1('Old')),
+        'slot1': parse_slot(raw_slot('Old')),
+        'slot2': parse_slot(raw_slot('Same')),
+        'slot3': parse_slot(raw_slot('Old')),
     }
 
     ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
-        side_effect=[raw_slot_v1('Updated'), raw_slot_v1('Same'), None]
+        side_effect=[raw_slot('Updated'), raw_slot('Same'), None]
     )
     ingestor_manager.resource_manager.renew_tag_lease = AsyncMock()
 
     await ingestor_manager.update_slot_config()
 
-    assert ingestor_manager.managed_tags['slot1'] == parse_slot(raw_slot_v1('Updated'))
-    assert ingestor_manager.managed_tags['slot2'] == parse_slot(raw_slot_v1('Same'))
+    assert ingestor_manager.managed_tags['slot1'] == parse_slot(raw_slot('Updated'))
+    assert ingestor_manager.managed_tags['slot2'] == parse_slot(raw_slot('Same'))
     assert 'slot3' not in ingestor_manager.managed_tags
 
     ingestor_manager.resource_manager.renew_tag_lease.assert_any_call('slot1')
@@ -783,8 +768,8 @@ async def test_manage_server_create_subscription_failure(ingestor_manager):
 
 @mark.asyncio
 async def test_manage_server_subscribe_and_unsubscribe_failure(ingestor_manager):
-    """subscribe() fails and so does the cleanup unsubscribe (legacy reader, session
-    gone): manage_server reports the failure and nothing escapes to the main loop"""
+    """subscribe() fails and so does the cleanup unsubscribe (session gone):
+    manage_server reports the failure and nothing escapes to the main loop"""
     reader = AsyncMock()
     reader.subscriptions = {}
     reader.subscribe.side_effect = Exception('Subscription error')
@@ -886,7 +871,7 @@ async def test_subscribe_to_tags(ingestor_manager):
 
 @mark.asyncio
 async def test_update_slot_config_keeps_last_good_config_when_malformed(ingestor_manager):
-    good = parse_slot(raw_slot_v1('Counter'))
+    good = parse_slot(raw_slot('Counter'))
     ingestor_manager.managed_tags = {'slot1': good}
     ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
         return_value={'server1': {'server_id': '1', 'url': 'u', 'tags': {'ns=2;i=2': {}}}}
@@ -922,7 +907,7 @@ def test___init___ignores_malformed_write_env(
     """A malformed write/gRPC-only env var must not stop the read path (review #1)."""
     monkeypatch.setenv('GRPC_PORT', '')
     monkeypatch.setenv('WRITE_MIN_PAUSE_S', '0,5')
-    monkeypatch.setenv('CERT_BUCKET', 'streamlit-connectors')
+    monkeypatch.setenv('CERT_CACHE_DIR', 'certs-cache')
 
     ingestor = IngestorManager(
         redis_data={'host': 'localhost', 'port': 6379},
@@ -937,147 +922,4 @@ def test___init___ignores_malformed_write_env(
         metrics_controller=MagicMock(),
     )
 
-    assert ingestor.cert_provider.bucket == 'streamlit-connectors'
-
-
-def test_parse_slot_config_warns_once_about_server_cert_path(ingestor_manager):
-    raw = raw_slot_v1()
-    raw['server1']['server_cert_path'] = '/app/certs/kepserver.der'
-
-    ingestor_manager.parse_slot_config('1', raw)
-    ingestor_manager.parse_slot_config('1', raw)  # every loop refreshes the slot
-
-    warnings = [
-        c for c in ingestor_manager.logger.warning.call_args_list if 'server_cert_path' in str(c)
-    ]
-    assert len(warnings) == 1
-
-
-# --- READ_ENGINE=legacy: plan B with the untouched rc3 OpcManager -------------------
-
-
-def make_manager(read_engine=None):
-    with (
-        patch('ingestor.managers.ingestor_manager.DataManager'),
-        patch('ingestor.managers.ingestor_manager.ResourceManager'),
-    ):
-        manager = IngestorManager(
-            redis_data={'host': 'localhost', 'port': 6379},
-            lease_ttl=60,
-            heartbeat_ttl=60,
-            poll_interval=5,
-            mongo_connection_string='mongodb://localhost:27017',
-            mongo_database='sientia',
-            logger=MagicMock(),
-            notification_handler=MagicMock(),
-            metadata=metadata['metadata'],
-            metrics_controller=MagicMock(),
-            read_engine=read_engine,
-        )
-    manager.send_notification = MagicMock()
-    manager.emit_metric = AsyncMock()
-    return manager
-
-
-def test_read_engine_defaults_to_v2(monkeypatch):
-    monkeypatch.delenv('READ_ENGINE', raising=False)
-
-    assert make_manager().read_engine == 'v2'
-
-
-def test_read_engine_from_env(monkeypatch):
-    monkeypatch.setenv('READ_ENGINE', 'Legacy ')
-
-    assert make_manager().read_engine == 'legacy'
-
-
-def test_invalid_read_engine_falls_back_to_v2(monkeypatch):
-    monkeypatch.setenv('READ_ENGINE', 'v3')
-
-    manager = make_manager()
-
-    assert manager.read_engine == 'v2'
-    assert any('Invalid READ_ENGINE' in str(c) for c in manager.logger.warning.call_args_list)
-
-
-@mark.asyncio
-@patch('ingestor.managers.ingestor_manager.ServerReader')
-@patch('ingestor.managers.ingestor_manager.OpcManager')
-async def test_legacy_initialize_builds_rc3_opc_manager(opc_manager, server_reader):
-    manager = make_manager('legacy')
-    server_config = {
-        'name': 'server1',
-        'server_id': '1',
-        'url': 'opc.tcp://localhost:4840',
-        'subscription_period_ms': 1000,
-        'server_uri': 'urn:sientia:opc-ingestor',
-        'cert_path': '/app/certs/opc-ingestor-cert.pem',
-        'private_key_path': '/app/certs/opc-ingestor-key.pem',
-        'server_cert_path': None,
-    }
-    opc_manager.return_value = MagicMock(connect=AsyncMock())
-
-    result = await manager.initialize_opc_from_config(server_config)
-
-    server_reader.assert_not_called()
-    opc_manager.assert_called_once_with(
-        name='server1',
-        url='opc.tcp://localhost:4840',
-        subscription_period_ms=1000,
-        data_manager=manager.data_manager,
-        logger=manager.logger,
-        server_uri='urn:sientia:opc-ingestor',
-        notification_handler=manager.notification_handler,
-        metadata=metadata['metadata'],
-        cert_path='/app/certs/opc-ingestor-cert.pem',
-        private_key_path='/app/certs/opc-ingestor-key.pem',
-        server_cert_path=None,
-        metrics_controller=manager.metrics_controller,
-    )
-    assert result is opc_manager.return_value
-    result.connect.assert_awaited_once()
-
-
-def test_legacy_keeps_raw_slot_v1():
-    manager = make_manager('legacy')
-    raw = raw_slot_v1()
-
-    # OpcManager reads tag_name/topics and the file cert paths straight from the slot
-    assert manager.parse_slot_config('1', raw) is raw
-
-
-def test_legacy_rejects_slot_v2():
-    manager = make_manager('legacy')
-    raw_v2 = {
-        'server1': {
-            'name': 'server1',
-            'server_id': '1',
-            'url': 'opc.tcp://localhost:4840',
-            'use_security': True,
-            'subscription_period_ms': 500,
-            'tags': {
-                'ns=2;i=2': {
-                    'frequency': '1000',
-                    'names': [{'collection': 'raw_a', 'tag_name': 'Counter', 'model_id': '1'}],
-                }
-            },
-        }
-    }
-
-    assert manager.parse_slot_config('1', raw_v2) is None
-    _, kwargs = manager.send_notification.call_args
-    assert kwargs['notification_id'] == 'OPC_SLOT_CONFIG_ERROR_1'
-    assert 'READ_ENGINE=legacy' in kwargs['message']
-
-
-@mark.asyncio
-async def test_legacy_remove_server_calls_plain_shutdown():
-    manager = make_manager('legacy')
-    opc_manager = MagicMock(shutdown=AsyncMock())
-    manager.opc_managers = {'server1': opc_manager}
-    manager.managed_tags = {'slot1': {'server1': {}}}
-
-    await manager.remove_server('server1', evict=False)
-
-    opc_manager.shutdown.assert_awaited_once_with()
-    assert manager.opc_managers == {}
+    assert ingestor.cert_provider.cache_dir == 'certs-cache'

tests/unit/managers/test_opc_manager.py

@@ -1,627 +0,0 @@
-import json
-from datetime import datetime
-from unittest.mock import ANY, AsyncMock, MagicMock, call, patch
-
-import pytest
-from asyncua.crypto.security_policies import SecurityPolicyBasic256
-from pytest import fixture, mark
-from sientia_do.notifications.models import NotificationLevel
-
-from ingestor.managers.opc_manager import OpcManager
-
-tags = {
-    'ns=3;i=1001': {
-        'aggregation_function': 'LTS',
-        'frequency': 1000,
-        'max_value': 100,
-        'min_value': 0,
-        'tag_name': 'Counter',
-    },
-    'ns=3;i=1003': {
-        'aggregation_function': 'AVG',
-        'frequency': 1000,
-        'max_value': 100,
-        'min_value': 0,
-        'tag_name': 'Random',
-    },
-    'ns=3;i=1004': {
-        'aggregation_function': 'MDN',
-        'frequency': 1000,
-        'max_value': 100,
-        'min_value': 0,
-        'tag_name': 'Sawtooth',
-    },
-}
-
-metadata = {
-    'metadata': {
-        'model_id': 'test_model',
-        'model_name': 'test_model',
-        'workflow_name': 'test_workflow',
-        'schema_name': 'test_schedule',
-    },
-}
-
-
-@fixture
-@patch('ingestor.managers.opc_manager.metrics')
-def raw_opc_manager(mock_metrics):
-    opc_manager = OpcManager(
-        name='TestConnector',
-        url='opc.tcp://localhost:4840',
-        data_manager=AsyncMock(),
-        subscription_period_ms=1000,
-        logger=MagicMock(),
-        server_uri='opc.tcp://localhost:4840',
-        notification_handler=MagicMock(),
-        metadata=metadata['metadata'],
-        metrics_controller=AsyncMock(),
-    )
-
-    opc_manager.emit_metric = AsyncMock()
-    opc_manager.send_notification_async = AsyncMock()
-    opc_manager.send_notification = MagicMock()
-
-    return opc_manager
-
-
-@fixture
-def opc_manager(raw_opc_manager):
-    raw_opc_manager.client = AsyncMock()
-    raw_opc_manager.cert_path = 'cert.pem'
-    raw_opc_manager.private_key_path = 'private_key.pem'
-    raw_opc_manager.server_cert_path = 'server_cert.pem'
-
-    return raw_opc_manager
-
-
-@fixture
-def opc_manager_subscribed(opc_manager):
-    opc_manager.subscriptions['sub1'] = AsyncMock()
-
-    return opc_manager
-
-
-def test___str__(opc_manager):
-    assert (
-        str(opc_manager)
-        == 'OpcManager(name=TestConnector, url=opc.tcp://localhost:4840, server_uri=opc.tcp://localhost:4840)\nnodes={}, subscriptions={}'
-    )
-
-
-@mark.asyncio
-async def test_shutdown_success(opc_manager):
-    opc_manager.disconnect = AsyncMock()
-
-    await opc_manager.shutdown()
-
-    opc_manager.disconnect.assert_called_once()
-
-
-@mark.asyncio
-async def test_shutdown_error(opc_manager):
-    opc_manager.disconnect = AsyncMock(side_effect=Exception('Test error'))
-
-    await opc_manager.shutdown()
-
-    opc_manager.logger.error.assert_called_once_with('Error during cleanup: Test error')
-
-
-@mark.asyncio
-async def test_set_security_success(opc_manager):
-    await opc_manager.set_security()
-
-    assert opc_manager.client.application_uri == opc_manager.server_uri
-
-    opc_manager.client.set_security.assert_called_once_with(
-        SecurityPolicyBasic256,
-        certificate=opc_manager.cert_path,
-        private_key=opc_manager.private_key_path,
-        server_certificate=opc_manager.server_cert_path,
-    )
-
-    assert opc_manager.client.secure_channel_timeout == 10000000
-    assert opc_manager.client.session_timeout == 10000000
-
-
-@mark.asyncio
-async def test_set_security_no_cert(opc_manager):
-    opc_manager.cert_path = None
-    opc_manager.private_key_path = None
-
-    try:
-        await opc_manager.set_security()
-    except ValueError as e:
-        assert str(e) == 'Certificate and private key paths must be provided for secure connection.'
-    else:
-        raise AssertionError('ValueError not raised')
-
-    assert opc_manager.client.set_security.call_count == 0
-
-
-@mark.asyncio
-@patch('ingestor.managers.opc_manager.metrics')
-@patch('ingestor.managers.opc_manager.Client')
-async def test_connect_no_security(client, mock_metrics, raw_opc_manager):
-    raw_opc_manager.set_security = AsyncMock()
-    client.return_value = AsyncMock()
-
-    await raw_opc_manager.connect()
-
-    client.assert_called_once_with(raw_opc_manager.url, timeout=10, watchdog_intervall=3600000)
-    raw_opc_manager.client.connect.assert_called_once()
-    raw_opc_manager.set_security.assert_not_called()
-    raw_opc_manager.emit_metric.assert_has_calls(
-        [
-            call(
-                metric_object=mock_metrics.OPC_CONNECTIONS_TOTAL,
-                tags={
-                    'pod_id': raw_opc_manager.pod_id,
-                    'server_name': raw_opc_manager.name,
-                },
-            ),
-            call(
-                metric_object=mock_metrics.OPC_CONNECTION_STATUS,
-                method='set',
-                value=1,
-                tags={
-                    'pod_id': raw_opc_manager.pod_id,
-                    'server_name': raw_opc_manager.name,
-                    'server_url': raw_opc_manager.url,
-                },
-            ),
-        ],
-        any_order=True,
-    )
-
-
-@mark.asyncio
-@patch('ingestor.managers.opc_manager.Client')
-async def test_connect_with_security(client, raw_opc_manager):
-    raw_opc_manager.cert_path = 'cert.pem'
-    raw_opc_manager.private_key_path = 'private_key.pem'
-    raw_opc_manager.server_cert_path = 'server_cert.pem'
-    raw_opc_manager.set_security = AsyncMock()
-    client.return_value = AsyncMock()
-
-    await raw_opc_manager.connect()
-
-    client.assert_called_once_with(raw_opc_manager.url, timeout=10, watchdog_intervall=3600000)
-    raw_opc_manager.client.connect.assert_called_once()
-    raw_opc_manager.set_security.assert_called_once()
-
-
-@mark.asyncio
-@patch('ingestor.managers.opc_manager.Client')
-@patch('ingestor.managers.opc_manager.metrics')
-async def test_connect_exception_handling_and_metrics(
-    mock_metrics_module, mock_opc_client_class, raw_opc_manager
-):
-    mock_client_instance = mock_opc_client_class.return_value
-    simulated_error_message = 'Erro de conexão simulado'
-    mock_client_instance.connect.side_effect = Exception(simulated_error_message)
-
-    raw_opc_manager.disconnect = AsyncMock()
-
-    opc_manager_instance = raw_opc_manager
-    opc_manager_instance.cert_path = None
-
-    with pytest.raises(Exception, match=simulated_error_message):
-        await opc_manager_instance.connect()
-
-    opc_manager_instance.disconnect.assert_called_once()
-
-
-@mark.asyncio
-async def test_create_subscription_no_client(raw_opc_manager):
-    try:
-        await raw_opc_manager.create_subscription('sub1')
-    except ValueError as e:
-        assert str(e) == 'Client not connected. Call connect first.'
-    else:
-        raise AssertionError('ValueError not raised')
-
-
-@mark.asyncio
-async def test_create_subscription_success_has_period(opc_manager):
-    await opc_manager.create_subscription('sub1')
-
-    opc_manager.client.create_subscription.assert_called_once_with(
-        opc_manager.subscription_period_ms, opc_manager
-    )
-    assert opc_manager.subscriptions['sub1'] is not None
-
-
-@mark.asyncio
-async def test_create_subscription_success_no_period(opc_manager):
-    await opc_manager.create_subscription('sub1')
-
-    opc_manager.client.create_subscription.assert_called_once_with(
-        opc_manager.subscription_period_ms, opc_manager
-    )
-    assert opc_manager.subscriptions['sub1'] is not None
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_create_subscription_with_metrics(metrics, opc_manager):
-    await opc_manager.create_subscription('sub1')
-
-    opc_manager.emit_metric.assert_called_once_with(
-        metric_object=metrics.OPC_SUBSCRIPTIONS_CREATED,
-        method='inc',
-        value=1,
-        tags={
-            'pod_id': opc_manager.pod_id,
-            'server_name': opc_manager.name,
-            'slot_name': 'sub1',
-        },
-    )
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_create_subscription_exception_during_client_call(
-    mock_metrics_module, raw_opc_manager
-):
-    opc_manager_instance = raw_opc_manager
-    opc_manager_instance.client = AsyncMock()
-
-    subscription_name = 'test_sub_client_error'
-    simulated_error_message = 'Falha ao criar subscrição no cliente OPC'
-
-    opc_manager_instance.client.create_subscription.side_effect = Exception(simulated_error_message)
-
-    with pytest.raises(Exception, match=simulated_error_message):
-        await opc_manager_instance.create_subscription(subscription_name)
-
-    opc_manager_instance.client.create_subscription.assert_called_once_with(
-        opc_manager_instance.subscription_period_ms, opc_manager_instance
-    )
-
-    opc_manager_instance.logger.error.assert_called_once_with(
-        f'Failed to create subscription {subscription_name} on {opc_manager_instance.name}: {simulated_error_message}'
-    )
-
-    mock_metrics_module.OPC_SUBSCRIPTIONS_CREATED.labels.assert_not_called()
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_subscribe_no_subscription(metrics, opc_manager):
-    try:
-        await opc_manager.subscribe('sub1', tags, 1000)
-    except ValueError as e:
-        assert str(e) == 'Subscription not created. Call create_subscription first.'
-    else:
-        raise AssertionError('ValueError not raised')
-    metrics.OPC_TAGS_SUBSCRIBED.labels.assert_not_called()
-
-
-@mark.asyncio
-async def test_subscribe_success(opc_manager_subscribed):
-    opc_manager_subscribed.client.get_node = MagicMock()
-    opc_manager_subscribed.nodes = {'ns=3;i=1001': 'data'}
-
-    await opc_manager_subscribed.subscribe('sub1', tags, 1000)
-
-    assert opc_manager_subscribed.nodes == tags
-    opc_manager_subscribed.subscriptions['sub1'].subscribe_data_change.assert_called_once_with(
-        [opc_manager_subscribed.client.get_node(n) for n in tags]
-    )
-
-
-@mark.asyncio
-async def test_unsubscribe_no_subscription(opc_manager):
-    await opc_manager.unsubscribe('sub1')
-
-    opc_manager.logger.warning.assert_called_once_with(
-        "Subscription 'sub1' not found. Cannot unsubscribe."
-    )
-    assert opc_manager.subscriptions.get('sub1') is None
-
-
-@mark.asyncio
-async def test_unsubscribe_success(opc_manager_subscribed):
-    await opc_manager_subscribed.unsubscribe('sub1')
-
-    assert opc_manager_subscribed.subscriptions.get('sub1') is None
-
-
-@mark.asyncio
-async def test_disconnection_fallback_success(opc_manager):
-    opc_manager.client = AsyncMock()
-    opc_manager.client.disconnect.return_value = True
-    result = await opc_manager.disconnection_fallback()
-    assert result == []
-
-
-@mark.asyncio
-async def test_disconnection_fallback_fail(opc_manager):
-    opc_manager.client = AsyncMock()
-    opc_manager.client.disconnect.side_effect = Exception('Test error')
-    result = await opc_manager.disconnection_fallback()
-    assert result == [
-        {'attempt': 1, 'error': 'Test error', 'traceback': ANY},
-        {'attempt': 2, 'error': 'Test error', 'traceback': ANY},
-        {'attempt': 3, 'error': 'Test error', 'traceback': ANY},
-        {'attempt': 4, 'error': 'Test error', 'traceback': ANY},
-        {'attempt': 5, 'error': 'Test error', 'traceback': ANY},
-    ]
-    assert opc_manager.client.disconnect.call_count == 5
-
-
-@mark.asyncio
-async def test_disconnect_success(opc_manager_subscribed):
-    opc_manager_subscribed.client = MagicMock()
-
-    await opc_manager_subscribed.disconnect()
-
-    opc_manager_subscribed.subscriptions['sub1'].delete.assert_called_once()
-    assert opc_manager_subscribed.client is None
-
-
-@mark.asyncio
-async def test_disconnect_no_client(opc_manager_subscribed):
-    opc_manager_subscribed.client = None
-    assert await opc_manager_subscribed.disconnect() is None
-
-    opc_manager_subscribed.logger.warning.assert_has_calls(
-        [
-            call('Client already disconnected.'),
-        ]
-    )
-
-
-@mark.asyncio
-async def test_disconnect_error_unsubscribe(opc_manager_subscribed):
-    opc_manager_subscribed.client = MagicMock(disconnect=AsyncMock())
-    opc_manager_subscribed.subscriptions['sub1'] = MagicMock(
-        delete=AsyncMock(side_effect=Exception('Test error'))
-    )
-
-    await opc_manager_subscribed.disconnect()
-
-    opc_manager_subscribed.subscriptions['sub1'].delete.assert_called_once()
-    opc_manager_subscribed.client = None
-    opc_manager_subscribed.logger.error.assert_called_once_with(
-        'Failed to clean up subscription: Test error'
-    )
-
-
-@mark.asyncio
-async def test_disconnect_error(opc_manager_subscribed):
-    opc_manager_subscribed.client = MagicMock()
-    opc_manager_subscribed.client.disconnect = MagicMock(side_effect=Exception('Test error'))
-
-    await opc_manager_subscribed.disconnect()
-
-    opc_manager_subscribed.subscriptions['sub1'].delete.assert_called_once()
-    opc_manager_subscribed.client = None
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_disconnect_metrics_on_successful_path(mock_metrics_module, raw_opc_manager):
-    mock_metrics_module.OPC_CONNECTION_STATUS.reset_mock()
-    mock_metrics_module.OPC_TAGS_SUBSCRIBED.reset_mock()
-
-    raw_opc_manager.client = MagicMock()
-    mock_sub1 = MagicMock()
-    mock_sub2 = MagicMock()
-    raw_opc_manager.subscriptions = {'sub1': mock_sub1, 'sub2': mock_sub2}
-
-    await raw_opc_manager.disconnect()
-
-    raw_opc_manager.emit_metric.assert_has_calls(
-        [
-            call(
-                metric_object=mock_metrics_module.OPC_CONNECTION_STATUS,
-                method='set',
-                value=0,
-                tags={
-                    'pod_id': raw_opc_manager.pod_id,
-                    'server_name': raw_opc_manager.name,
-                    'server_url': raw_opc_manager.url,
-                },
-            ),
-            call(
-                metric_object=mock_metrics_module.OPC_TAGS_SUBSCRIBED,
-                method='set',
-                value=0,
-                tags={
-                    'pod_id': raw_opc_manager.pod_id,
-                    'server_name': raw_opc_manager.name,
-                },
-            ),
-        ],
-        any_order=True,
-    )
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_datachange_notification(metrics, opc_manager_subscribed):
-    data = MagicMock(
-        monitored_item=MagicMock(
-            Value=MagicMock(
-                Value=MagicMock(Value=42),
-                SourceTimestamp=datetime.strptime('2021-01-01T00:00:00', '%Y-%m-%dT%H:%M:%S'),
-            )
-        )
-    )
-    opc_manager_subscribed.nodes = {
-        'ns=3;i=1001': {
-            'tag_name': 'Counter',
-            'cycle_rule': {'cycle_increment': 1.0, 'cycle_count': 2},
-            'topics': ['topic1', 'topic2'],
-        }
-    }
-
-    await opc_manager_subscribed.datachange_notification('ns=3;i=1001', None, data)
-
-    opc_manager_subscribed.data_manager.publish.assert_any_call(
-        'topic1',
-        {
-            'tag': 'ns=3;i=1001',
-            'name': 'Counter',
-            'timestamp': '2021-01-01 00:00:00-0300',
-            'value': 42,
-        },
-    )
-    opc_manager_subscribed.data_manager.publish.assert_any_call(
-        'topic2',
-        {
-            'tag': 'ns=3;i=1001',
-            'name': 'Counter',
-            'timestamp': '2021-01-01 00:00:00-0300',
-            'value': 42,
-        },
-    )
-    assert opc_manager_subscribed.nodes['ns=3;i=1001']['cycle_rule']['cycle_count'] == 0
-
-    opc_manager_subscribed.emit_metric.assert_called_once_with(
-        metric_object=metrics.OPC_CYCLES_WITHOUT_DATA,
-        method='set',
-        value=0,
-        tags={
-            'pod_id': opc_manager_subscribed.pod_id,
-            'server_name': opc_manager_subscribed.name,
-        },
-    )
-
-
-@mark.asyncio
-async def test_check_cycles_no_notification(opc_manager):
-    # Setup: node with cycle_count just below threshold
-    opc_manager.nodes = {
-        'ns=3;i=1001': {
-            'tag_name': 'Counter',
-            'cycle_rule': {'cycle_increment': 1.0, 'cycle_count': 3.0},
-        }
-    }
-
-    await opc_manager.check_cycles()
-
-    # After one increment, cycle_count = 4.0, still below threshold
-    assert opc_manager.nodes['ns=3;i=1001']['cycle_rule']['cycle_count'] == pytest.approx(4.0)
-    opc_manager.send_notification_async.assert_not_called()
-
-
-@mark.asyncio
-async def test_check_cycles_triggers_notification(opc_manager):
-    # Setup: node with cycle_count just below threshold, increment will cross threshold
-    opc_manager.nodes = {
-        'ns=3;i=1001': {
-            'tag_name': 'Counter',
-            'cycle_rule': {'cycle_increment': 2.5, 'cycle_count': 3.0},
-        }
-    }
-    opc_manager.notification_handler.build_and_send_notification = MagicMock()
-
-    await opc_manager.check_cycles()
-
-    # After increment, cycle_count = 5.5, should trigger notification
-    assert opc_manager.nodes['ns=3;i=1001']['cycle_rule']['cycle_count'] == pytest.approx(5.5)
-    opc_manager.send_notification_async.assert_called_once_with(
-        notification_id='TAG_ns=3;i=1001:Counter_LISTENNING_STOPPED',
-        message='5.5 cycles without receive from ns=3;i=1001:Counter',
-        block='opc_manager',
-        level=NotificationLevel.WARNING,
-        metadata=metadata['metadata'],
-    )
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_check_opc_listenning_no_notification(metrics, opc_manager):
-    opc_manager.non_receive_count = 3
-
-    result = await opc_manager.check_opc_listenning()
-
-    assert opc_manager.non_receive_count == 4
-    opc_manager.send_notification_async.assert_not_called()
-    assert result is False
-
-    opc_manager.emit_metric.assert_called_once_with(
-        metric_object=metrics.OPC_CYCLES_WITHOUT_DATA,
-        method='set',
-        value=opc_manager.non_receive_count,
-        tags={
-            'pod_id': opc_manager.pod_id,
-            'server_name': opc_manager.name,
-        },
-    )
-
-
-@mark.asyncio
-async def test_check_opc_listenning_warning_notification(opc_manager):
-    opc_manager.non_receive_count = 4
-
-    result = await opc_manager.check_opc_listenning()
-
-    assert opc_manager.non_receive_count == 5
-    opc_manager.send_notification_async.assert_called_once_with(
-        notification_id=f'OPC_LISTENNING_STOPPED__{opc_manager.name}',
-        message=f'5 cycles without receive from OPC {opc_manager.name}. Tags: {json.dumps(opc_manager.nodes)}',
-        block='opc_manager',
-        level=NotificationLevel.ERROR,
-        metadata=metadata['metadata'],
-    )
-    assert result is False
-
-
-@patch('ingestor.managers.opc_manager.metrics')
-@mark.asyncio
-async def test_check_opc_listenning_error_notification_and_retry(metrics, opc_manager):
-    opc_manager.non_receive_count = 14
-
-    result = await opc_manager.check_opc_listenning()
-
-    assert opc_manager.non_receive_count == 15
-    # Should be called twice: once for 5, once for 15
-    assert opc_manager.send_notification_async.call_count == 2
-    calls = opc_manager.send_notification_async.call_args_list
-    # First call: 5 cycles warning
-    assert calls[0].kwargs == {
-        'notification_id': f'OPC_LISTENNING_STOPPED__{opc_manager.name}',
-        'message': f'15 cycles without receive from OPC {opc_manager.name}. Tags: {json.dumps(opc_manager.nodes)}',
-        'block': 'opc_manager',
-        'level': NotificationLevel.ERROR,
-        'metadata': metadata['metadata'],
-    }
-    # Second call: 15 cycles retry
-    assert calls[1].kwargs == {
-        'notification_id': f'OPC_CONNECTION_RETRY__{opc_manager.name}',
-        'message': f'Retrying to connect to server {opc_manager.name}',
-        'block': 'opc_manager',
-        'level': NotificationLevel.ERROR,
-        'metadata': metadata['metadata'],
-    }
-    assert result is True
-
-    opc_manager.emit_metric.assert_has_calls(
-        [
-            call(
-                metric_object=metrics.OPC_CYCLES_WITHOUT_DATA,
-                method='set',
-                value=opc_manager.non_receive_count,
-                tags={
-                    'pod_id': opc_manager.pod_id,
-                    'server_name': opc_manager.name,
-                },
-            ),
-        ]
-    )
-
-    opc_manager.emit_metric.assert_has_calls(
-        [
-            call(
-                metric_object=metrics.OPC_RECONNECTIONS_TOTAL,
-                tags={
-                    'pod_id': opc_manager.pod_id,
-                    'server_name': opc_manager.name,
-                },
-            ),
-        ]
-    )

tests/unit/managers/test_server_reader.py

@@ -9,9 +9,14 @@ SERVER_CONFIG = {
     'name': 'kepserver',
     'server_id': 1,  # the slot may carry it as int; the pool keys by str
     'url': 'opc.tcp://kepserver:49320',
-    'server_uri': 'urn:sientia:opc-ingestor',
-    'use_security': True,
     'subscription_period_ms': 15000.0,
+    'security': {'mode': 'SignAndEncrypt', 'policy': 'Basic256Sha256'},
+    'certificate': {
+        'certificate_id': 1,
+        'application_uri': 'urn:sientia:opc-ingestor',
+        'cert': {'bucket': 'opc-certificates', 'object_name': 'client/p/cert.pem'},
+        'private_key': {'bucket': 'opc-certificates', 'object_name': 'client/p/key.pem'},
+    },
 }
 
 
@@ -45,10 +50,8 @@ def test_server_cfg_keeps_only_connection_fields():
 
     assert reader.server_id == '1'
     assert reader.server_cfg == {
-        'url': 'opc.tcp://kepserver:49320',
-        'server_uri': 'urn:sientia:opc-ingestor',
-        'use_security': True,
-        'subscription_period_ms': 15000.0,
+        key: SERVER_CONFIG[key]
+        for key in ('url', 'subscription_period_ms', 'security', 'certificate')
     }
 
 
@@ -58,7 +61,7 @@ async def test_connect_opens_pooled_connection():
 
     await reader.connect()
 
-    # use_security=True: the pool fetches the certificate from MinIO (CertProvider)
+    # With a certificate, the pool fetches it from MinIO (CertProvider)
     pool.get.assert_awaited_once_with('1', reader.server_cfg)
 
 

tests/unit/test_config.py

@@ -8,7 +8,6 @@ _ENV_VARS = (
     'NATS_QUEUE',
     'GRPC_ENABLED',
     'GRPC_PORT',
-    'CERT_BUCKET',
     'CERT_CACHE_DIR',
     'WRITE_TIMESTAMP',
     'WRITE_QUALITY',
@@ -31,7 +30,6 @@ def test_from_env_defaults():
     assert cfg.nats_queue == 'gateway-writers'
     assert cfg.grpc_enabled is False
     assert cfg.grpc_port == 50051
-    assert cfg.cert_bucket == 'streamlit-connectors'
     assert cfg.cert_cache_dir == '/tmp/opc-certs'  # noqa: S108
     assert cfg.write_timestamp is True
     assert cfg.write_quality is True
@@ -43,6 +41,7 @@ def test_from_env_overrides(monkeypatch):
     monkeypatch.setenv('GRPC_ENABLED', 'true')
     monkeypatch.setenv('GRPC_PORT', '6000')
     monkeypatch.setenv('WRITE_MIN_PAUSE_S', '0.5')
+    monkeypatch.setenv('WRITE_TIMESTAMP', 'false')
     monkeypatch.setenv('WRITE_QUALITY', 'false')
 
     cfg = GatewayConfig.from_env()
@@ -50,6 +49,7 @@ def test_from_env_overrides(monkeypatch):
     assert cfg.grpc_enabled is True
     assert cfg.grpc_port == 6000
     assert cfg.write_min_pause_s == 0.5
+    assert cfg.write_timestamp is False
     assert cfg.write_quality is False
 
 
@@ -76,12 +76,10 @@ def test_certs_from_env_ignores_malformed_numeric_vars(monkeypatch):
 
     monkeypatch.setenv('GRPC_PORT', '')
     monkeypatch.setenv('IDLE_CONN_MAX_S', 'abc')
-    monkeypatch.setenv('CERT_BUCKET', 'my-bucket')
     monkeypatch.setenv('CERT_CACHE_DIR', 'certs-cache')
 
     cfg = GatewayConfig.certs_from_env()
 
-    assert cfg.cert_bucket == 'my-bucket'
     assert cfg.cert_cache_dir == 'certs-cache'
     with pytest.raises(ValueError):
         GatewayConfig.from_env()  # the full config still fails, only the runtime uses it

tests/unit/test_gateway_runtime.py

@@ -39,6 +39,7 @@ def mocks(monkeypatch):
     patched['pool'].release_idle = AsyncMock()
     patched['NatsWriteConsumer'].return_value.start = AsyncMock()
     patched['NatsWriteConsumer'].return_value.stop = AsyncMock()
+    patched['NatsWriteConsumer'].return_value.closed = False
     patched['GrpcServer'].return_value.start = AsyncMock()
     patched['GrpcServer'].return_value.stop = AsyncMock()
     return patched
@@ -173,3 +174,47 @@ async def test_idle_sweep_releases_idle_connections(mocks):
     await runtime.idle_sweep()
 
     mocks['pool'].release_idle.assert_awaited_once_with(42.0)
+
+
+def test_write_engine_resolves_servers_from_the_pool_and_mongo(mocks):
+    """SIENTIAPDE-1975 GW1: write commands carry only the server_id."""
+    data_manager = MagicMock()
+    runtime = gr.GatewayRuntime(
+        config=GatewayConfig(),
+        data_manager=data_manager,
+        pool=mocks['pool'],
+        logger=MagicMock(),
+        notification_handler=MagicMock(),
+        metrics_controller=MagicMock(),
+    )
+
+    _, kwargs = mocks['WriteEngine'].call_args
+    assert kwargs['servers'] is runtime.servers
+    assert runtime.servers.pool is mocks['pool']
+    assert runtime.servers.mongo is data_manager.mongo_repository
+
+
+@pytest.mark.asyncio
+async def test_idle_sweep_restarts_a_closed_nats_connection(mocks):
+    runtime = make_runtime(pool=mocks['pool'])
+    nats_mock = mocks['NatsWriteConsumer'].return_value
+    await runtime.start()
+    assert nats_mock.start.await_count == 1
+
+    nats_mock.closed = True  # closed for good (e.g. by the server)
+    await runtime.idle_sweep()
+
+    assert nats_mock.start.await_count == 2
+    assert runtime._nats_started is True
+    runtime.logger.warning.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_idle_sweep_leaves_a_live_nats_connection_alone(mocks):
+    runtime = make_runtime(pool=mocks['pool'])
+    nats_mock = mocks['NatsWriteConsumer'].return_value
+    await runtime.start()
+
+    await runtime.idle_sweep()
+
+    assert nats_mock.start.await_count == 1