conjurer: give librarian 60s termination grace for checkpointing

The librarian now checkpoints an in-progress search on SIGTERM and exits
within CONJURER_LIBRARIAN_GRACEFUL_TIMEOUT (default 45s). Raise k8s
terminationGracePeriodSeconds to 60 so that graceful checkpoint isn't cut
short by SIGKILL - otherwise the long DB scan restarts instead of resuming.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

astrololo/kustomization.yaml

@@ -10,10 +10,10 @@ resources:
   - ingress.yaml # wejście po https + przekierowanie z http
 images:
   - name: gitea.czernobog.pl/gitea/astrololo-data
-    newTag: 623603b1
+    newTag: 8ebce816
   - name: gitea.czernobog.pl/gitea/astrololo-logic
-    newTag: 623603b1
+    newTag: 8ebce816
   - name: gitea.czernobog.pl/gitea/astrololo-render
     newTag: latest
   - name: gitea.czernobog.pl/gitea/astrololo-presentation
-    newTag: 623603b1
+    newTag: 8ebce816

conjurer/bot.yaml

@@ -0,0 +1,59 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: bot
+  namespace: conjurer
+spec:
+  replicas: 1                     # NIGDY więcej — jedna sesja gateway na token
+  strategy: { type: Recreate }    # NIE RollingUpdate — dwa pody = wojna o sesję Discord
+  selector: { matchLabels: { app: bot } }
+  template:
+    metadata: { labels: { app: bot } }
+    spec:
+      imagePullSecrets: [{ name: gitea-registry }]
+      containers:
+        - name: bot
+          image: gitea.czernobog.pl/gitea/conjurer-bot:c8aae106
+          ports: [{ containerPort: 5000 }]
+          env:
+            - { name: CONJURER_DATA_DIR,      value: "/data" }
+            - { name: CONJURER_DISCORD_HOST,  value: "0.0.0.0" }
+            - { name: CONJURER_DISCORD_PORT,  value: "5000" }
+            - { name: CONJURER_API_KEY,  value: "d97008b3-7a5a-11f1-acd1-000b0e0f00ed" }
+            - { name: CONJURER_NETRC_FILE, value: "/secrets/.netrc" }
+            # ↓ NAZWY PODSTAW WG WYNIKU grepa z 0.2 ↓
+            - { name: CONJURER_LIBRARIAN_SERVICE, value: "http://librarian:5001" }
+            - { name: CONJURER_MUSICIAN_SERVICE,  value: "http://192.168.1.89:5000" }
+            - { name: CONJURER_RADIO_SERVICE,     value: "http://192.168.1.79:5005" }
+            - { name: CONJURER_FILE_SERVICE,     value: "http://192.168.1.89:5000" }
+
+            - { name: CONJURER_RADIO_HARBOR,      value: "http://192.168.1.79:54321" }
+          volumeMounts:
+            - { name: data,  mountPath: /data }
+            - { name: netrc, mountPath: /secrets, readOnly: true }
+          resources:
+            requests: { cpu: "200m", memory: "256Mi" }
+            limits:   { cpu: "2",    memory: "1Gi" }
+      volumes:
+        - name: data
+          persistentVolumeClaim: { claimName: bot-data }
+        - name: netrc
+          secret: { secretName: conjurer-netrc }
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata: { name: bot-data, namespace: conjurer }
+spec:
+  accessModes: [ReadWriteOnce]
+  resources: { requests: { storage: 2Gi } }
+---
+apiVersion: v1
+kind: Service
+metadata: { name: bot, namespace: conjurer }
+spec:
+  type: NodePort                  # radio/musician z Dockera muszą go dosięgnąć
+  selector: { app: bot }
+  # nodePort PRZYPIĘTY na sztywno. Bez tego k8s losuje port z 30000-32767 przy
+  # (od)tworzeniu Service, a musician/betoniarka z Dockera adresują bota po
+  # http://192.168.1.73:32442 na sztywno - rozjazd = wyniki/eventy giną w locie.
+  ports: [{ port: 5000, targetPort: 5000, nodePort: 32442 }]

conjurer/conjurer-imageupdater.yaml

@@ -0,0 +1,19 @@
+apiVersion: argocd-image-updater.argoproj.io/v1alpha1
+kind: ImageUpdater
+metadata:
+  name: conjurer
+  namespace: argocd
+spec:
+  commonUpdateSettings:
+    updateStrategy: "newest-build"
+  writeBackConfig:
+    method: "git:secret:argocd/git-creds"
+    gitConfig:
+      repository: "https://gitea.czernobog.pl/gitea/deploy.git"
+      branch: "master"                       # ← gałąź repo deploy
+      writeBackTarget: "kustomization:/conjurer"
+  applicationRefs:
+    - namePattern: "conjurer"
+      images:
+        - { alias: "librarian", imageName: "gitea.czernobog.pl/gitea/conjurer-librarian" }
+        - { alias: "bot",       imageName: "gitea.czernobog.pl/gitea/conjurer-bot" }

conjurer/kustomization.yaml

@@ -2,4 +2,10 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
   - namespace.yaml
-  - librarian.yaml
+  - librarian.yaml
+  - bot.yaml
+images:
+  - name: gitea.czernobog.pl/gitea/conjurer-librarian
+    newTag: 40605b95
+  - name: gitea.czernobog.pl/gitea/conjurer-bot
+    newTag: 8e18071b

conjurer/librarian.yaml

@@ -10,26 +10,45 @@ spec:
     metadata: { labels: { app: librarian } }
     spec:
       imagePullSecrets: [{ name: gitea-registry }]
+      # On SIGTERM the librarian checkpoints the running search and exits within
+      # CONJURER_LIBRARIAN_GRACEFUL_TIMEOUT (default 45s). Give k8s enough grace
+      # to let that finish before it SIGKILLs - otherwise a long scan's checkpoint
+      # is cut short and the search restarts from scratch instead of resuming.
+      terminationGracePeriodSeconds: 60
       containers:
         - name: librarian
-          image: gitea.czernobog.pl/gitea/conjurer-librarian:v0.1.0
+          image: gitea.czernobog.pl/gitea/conjurer-librarian:e243777e
           ports: [{ containerPort: 5001 }]
           env:
             - { name: CONJURER_LIBRARIAN_HOST,      value: "0.0.0.0" }
             - { name: CONJURER_LIBRARIAN_PORT,      value: "5001" }
             - { name: CONJURER_LIBRARIAN_DB_PATH,   value: "/doi/" }
+            - { name: CONJURER_API_KEY,  value: "d97008b3-7a5a-11f1-acd1-000b0e0f00ed" }
+            - { name: CONJURER_LIBRARIAN_MAXTHREADS,  value: "40" }
+            - { name: CONJURER_CROSSREF_MAILTO,  value: "mtuszowski@gmail.com" }
+            - { name: CONJURER_LIBRARIAN_CHUNK,  value: "_chunk.txt" }
+            # Librarian jest W TYM SAMYM klastrze/namespace co bot - gada z nim
+            # po DNS Service'u, nie przez nodePort węzła (ten zostaje tylko dla
+            # zewnętrznych musician/betoniarka z Dockera). Odporne na przetasowania.
+            - { name: CONJURER_MAIN_BOT,  value: "http://bot:5000" }
+
             - { name: CONJURER_LIBRARIAN_STATE_DIR, value: "/lib_temp_files" }
+
           volumeMounts:
             - { name: doi,   mountPath: /doi, readOnly: true }
             - { name: state, mountPath: /lib_temp_files }
           resources:
-            requests: { cpu: "100m", memory: "256Mi" }
-            limits:   { cpu: "1",    memory: "1Gi" }
+            requests: { cpu: "100m", memory: "512Mi" }
+            # Headroom bump: the work-queue OOM is fixed in code, but a deep
+            # search still pulls up to 15000 Crossref records into RAM and the
+            # accumulating result JSONs are loaded whole. 2Gi gives margin so a
+            # big search isn't OOM-killed. Tune down if the node is tight.
+            limits:   { cpu: "1",    memory: "2Gi" }
       volumes:
         - name: doi
           nfs:
             server: 192.168.1.34
-            path: /mnt/Tank1/conjurer_doi
+            path: /mnt/Tank1/conjurer_swap/librarian_data/base_it1
         - name: state
           persistentVolumeClaim: { claimName: librarian-state }
 ---