conjurer: pin the model Ollama actually has, and raise the AI timeout

Probing the real server (192.168.1.72:11434) after it was opened to the LAN:
/v1/models returns exactly one model, gemma4:e2b. Without pinning it the
bot would request the built-in default llama3.1:8b and every reply would
fail with "model not found", so set it explicitly on both bots.

Also raise CONJURER_AI_TIMEOUT_SECONDS to 240. Self-hosted generation is far
slower than a hosted API, particularly the first request after the model is
evicted from VRAM. It applies to every backend, so it is deliberately not
set higher than needed.

Caveat recorded honestly: at the time of writing, generation on that server
does not complete. /v1/models answers instantly, but both /v1/chat/
completions (180s) and native /api/generate with num_predict=5 (60s) return
nothing, and /api/ps shows no model ever becomes resident - so the model
never finishes loading. Ollama is 0.32.14 and gemma4:e2b is 5.1B Q4_K_M
(~3.5GB) despite the "e2b" name. That is a server-side problem, not a
configuration one; these values are correct and take effect once it loads.

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

astrololo/README.md

@@ -90,11 +90,26 @@ read -rs -p "Hasło do aplikacji (APP_PASSWORD): " APP_PASSWORD; echo
 
 kubectl -n astrololo create secret generic astrololo-auth \
   --from-literal=APP_PASSWORD="$APP_PASSWORD" \
-  --from-literal=INTERNAL_TOKEN="$(openssl rand -hex 32)"
+  --from-literal=INTERNAL_TOKEN="$(openssl rand -hex 32)" \
+  --from-literal=SESSION_SECRET="$(openssl rand -hex 32)"
 
 unset APP_PASSWORD
 ```
 
+`SESSION_SECRET` podpisuje ciasteczka sesji (LOG-34). **Pod bez niego celowo nie
+wstanie**: usługa z kontami, ale bez klucza, nie odróżniłaby ważnej sesji od
+podrobionej. Nikt go nigdy nie musi oglądać.
+
+> **Rotacja tego klucza wylogowuje WSZYSTKICH.** To nie usterka, tylko awaryjny
+> wyłącznik: gdy podejrzewasz, że ktoś przechwycił cudzą sesję, podmiana klucza
+> unieważnia je wszystkie naraz.
+>
+> ```bash
+> kubectl -n astrololo patch secret astrololo-auth --type=json \
+>   -p="[{\"op\":\"replace\",\"path\":\"/data/SESSION_SECRET\",\"value\":\"$(openssl rand -hex 32 | base64 | tr -d '\n')\"}]"
+> kubectl -n astrololo rollout restart deploy/presentation
+> ```
+
 `INTERNAL_TOKEN` jest losowany i **nikt go nigdy nie musi oglądać** — służy tylko
 usługom do rozmowy między sobą. `APP_PASSWORD` wpisujesz w przeglądarce
 (użytkownik: `astrololo`, zmienny przez `APP_USER` w `presentation.yaml`).

astrololo/kustomization.yaml

@@ -11,10 +11,10 @@ resources:
   - ingress.yaml # wejście po https + przekierowanie z http
 images:
   - name: gitea.czernobog.pl/gitea/astrololo-data
-    newTag: 71bb3b9c
+    newTag: f0d07ee8
   - name: gitea.czernobog.pl/gitea/astrololo-logic
-    newTag: 71bb3b9c
+    newTag: f0d07ee8
   - name: gitea.czernobog.pl/gitea/astrololo-render
     newTag: latest
   - name: gitea.czernobog.pl/gitea/astrololo-presentation
-    newTag: 71bb3b9c
+    newTag: f0d07ee8

astrololo/presentation.yaml

@@ -32,6 +32,13 @@ spec:
                 secretKeyRef: { name: astrololo-auth, key: INTERNAL_TOKEN }
             - name: APP_USER
               value: "astrololo"
+            # Klucz podpisu ciasteczek sesji (LOG-34). WYMAGANY — pod bez niego
+            # celowo nie wstaje: usługa z kontami, ale bez klucza, nie umiałaby
+            # odróżnić ważnej sesji od podrobionej. Rotacja tego klucza WYLOGOWUJE
+            # WSZYSTKICH, i tak ma być — to jest awaryjny wyłącznik.
+            - name: SESSION_SECRET
+              valueFrom:
+                secretKeyRef: { name: astrololo-auth, key: SESSION_SECRET }
             - name: RATE_LIMIT_PER_MIN
               value: "120"                       # 0 = bez limitu
             # Aplikacja stoi za Ingressem, więc bezpośrednim rozmówcą jest zawsze

conjurer/bot.yaml

@@ -31,6 +31,19 @@ spec:
             # Where the librarian sends THIS bot's results/pongs back to (its own
             # NodePort). Lets one librarian serve both bots - see deploy-bot.yaml.
             - { name: CONJURER_SELF_CALLBACK,     value: "http://192.168.1.73:32442" }
+            # Self-hosted models (Ollama). No API key - the endpoint IS the
+            # configuration, and the backend stays unselectable while unset.
+            # Pick a model at runtime with: $gadaj_teraz ollama <model>
+            # ($modele_ai lists what the server actually has pulled).
+            - { name: CONJURER_OLLAMA_URL,        value: "http://192.168.1.72:11434" }
+            # The server currently has exactly one model pulled (verified via
+            # /v1/models): gemma4:e2b. Without this the built-in default
+            # (llama3.1:8b) would be requested and every reply would fail.
+            - { name: CONJURER_OLLAMA_MODEL,      value: "gemma4:e2b" }
+            # Self-hosted generation is far slower than a hosted API, especially
+            # the first request after the model is evicted from VRAM. Applies to
+            # every backend, so keep it only as high as you actually need.
+            - { name: CONJURER_AI_TIMEOUT_SECONDS, value: "240" }
           volumeMounts:
             - { name: data,  mountPath: /data }
             - { name: netrc, mountPath: /secrets, readOnly: true }

conjurer/deploy-bot.yaml

@@ -51,6 +51,19 @@ spec:
             # query and answers results/pongs HERE - so it serves this bot AND the
             # test bot from one instance, no CONJURER_MAIN_BOT repointing needed.
             - { name: CONJURER_SELF_CALLBACK,     value: "http://192.168.1.73:32443" }
+            # Self-hosted models (Ollama). No API key - the endpoint IS the
+            # configuration, and the backend stays unselectable while unset.
+            # Pick a model at runtime with: $gadaj_teraz ollama <model>
+            # ($modele_ai lists what the server actually has pulled).
+            - { name: CONJURER_OLLAMA_URL,        value: "http://192.168.1.72:11434" }
+            # The server currently has exactly one model pulled (verified via
+            # /v1/models): gemma4:e2b. Without this the built-in default
+            # (llama3.1:8b) would be requested and every reply would fail.
+            - { name: CONJURER_OLLAMA_MODEL,      value: "gemma4:e2b" }
+            # Self-hosted generation is far slower than a hosted API, especially
+            # the first request after the model is evicted from VRAM. Applies to
+            # every backend, so keep it only as high as you actually need.
+            - { name: CONJURER_AI_TIMEOUT_SECONDS, value: "240" }
           volumeMounts:
             - { name: data,  mountPath: /data }
             - { name: netrc, mountPath: /secrets, readOnly: true }