Make local inference limits and workstation setup reproducible

config/config.env.example

@@ -7,6 +7,9 @@ HERMES_BRANCH="main"
 GATEWAY_SERVICE="hermes-gateway.service"
 LLAMA_SERVICE="llama-qwen.service"
 LLAMA_URL="http://127.0.0.1:8080"
+# Independent slot watchdog. Active requests only; updates hold the same lock.
+LLAMA_MAX_REQUEST_SECONDS=600
+LLAMA_MAX_OUTPUT_TOKENS=2048
 # 1: inaktiven Dienst wieder starten. HTTP-Timeouts allein starten nie neu.
 # Standard 0 verhindert unerwünschte Modellstarts während Wartung/Tuning.
 LLAMA_HEALTH_AUTORESTART=0

config/llama.env.example

@@ -8,6 +8,7 @@ LLAMA_ALIAS="qwen38-27b-local"
 LLAMA_MMPROJ=""
 LLAMA_HOST="127.0.0.1"
 LLAMA_PORT="8080"
+LLAMA_MAX_OUTPUT_TOKENS=2048
 
 # Standard für eine gemeinsam mit dem Desktop genutzte GPU: 64K / 4096 MiB.
 # Fit ist ein Planungsziel; die freie Reserve auf der Zielmaschine messen.

config/models.lock.json

@@ -0,0 +1,51 @@
+{
+  "llama_cpp_commit": "d81235049384534c167caea52b85a694f6103d14",
+  "models": {
+    "routine": {
+      "repo": "unsloth/Qwen3.5-4B-GGUF",
+      "revision": "e87f176479d0855a907a41277aca2f8ee7a09523",
+      "directory": "qwen35-4b/e87f176479d0855a907a41277aca2f8ee7a09523",
+      "files": [
+        {
+          "name": "Qwen3.5-4B-Q4_K_M.gguf",
+          "sha256": "00fe7986ff5f6b463e62455821146049db6f9313603938a70800d1fb69ef11a4",
+          "size": 2740937888
+        },
+        {
+          "name": "mmproj-F16.gguf",
+          "sha256": "cd88edcf8d031894960bb0c9c5b9b7e1fea6ebee02b9f7ce925a00d12891f864",
+          "size": 672423616
+        }
+      ]
+    },
+    "large": {
+      "repo": "ggml-org/Qwen3.8-27B-GGUF",
+      "revision": "0669b98607d47046c7c2b3f801011d54a08cfccf",
+      "directory": "qwen38-27b/0669b98607d47046c7c2b3f801011d54a08cfccf",
+      "files": [
+        {
+          "name": "Qwen3.8-27B-Q4_K_M.gguf",
+          "sha256": "31629f53165ab6a7dad8c9847dcfd1fdf55829dac1e6e748f4a68581b0033d34",
+          "size": 18973870432
+        },
+        {
+          "name": "mmproj-Qwen3.8-27B-Q8_0.gguf",
+          "sha256": "2e968a6af97ce35d8971890b257b9b7edabf20ad91450501fa53162a19ee33eb",
+          "size": 629247008
+        }
+      ]
+    },
+    "compression": {
+      "repo": "ggml-org/Qwen3-1.7B-GGUF",
+      "revision": "daeb8e2d528a760970442092f6bf1e55c3b659eb",
+      "directory": "qwen3-1.7b-compression",
+      "files": [
+        {
+          "name": "Qwen3-1.7B-Q4_K_M.gguf",
+          "sha256": "d2387ca2dbfee2ffabce7120d3770dadca0b293052bc2f0e138fdc940d9bc7b5",
+          "size": 1282439264
+        }
+      ]
+    }
+  }
+}