feat: Modell der Coder/Judge-Schleife per PI_CODER_MODEL wählbar

PI_CODER_MODEL=<provider>/<id> setzt das Modell für beide Rollen; ohne
Variable bleibt es bei llama-cpp-single/coding_model. Die Bereitschafts-
prüfung nutzt baseUrl des Modells statt fest Port 8001. Neuer Provider
strata (lokaler Strata-Server, 127.0.0.1:9090) in models.json.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

models.json

@@ -39,6 +39,28 @@
       ]
     },
 
+    "strata": {
+      "baseUrl": "http://127.0.0.1:9090/v1",
+      "api": "openai-completions",
+      "apiKey": "none",
+      "compat": {
+        "supportsDeveloperRole": false,
+        "supportsReasoningEffort": true,
+        "maxTokensField": "max_tokens"
+      },
+      "models": [
+        {
+          "id": "qwen3.8-flash-next-iq3_s",
+          "name": "Strata Qwen3.8-Flash-Next IQ3_S (lokal :9090)",
+          "reasoning": true,
+          "input": ["text"],
+          "contextWindow": 262144,
+          "maxTokens": 16384,
+          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
+        }
+      ]
+    },
+
     "openrouter": {
       "models": [
         { "id": "qwen/qwen3-235b-a22b:free",            "name": "Qwen3 235B (Free)" },