fix(openwebui): guarantee answer after tool budget

compose.yaml

@@ -705,7 +705,10 @@ services:
       start_period: 10s
 
   open-webui:
-    image: ${OPENWEBUI_IMAGE:-ghcr.io/open-webui/open-webui:v0.9.5}
+    build:
+      context: .
+      dockerfile: platform/openwebui/Dockerfile
+    image: ${OPENWEBUI_IMAGE:-mike-ai/open-webui:v0.9.5-tool-final-v1}
     container_name: mike-ai-open-webui
     restart: unless-stopped
     volumes:
@@ -746,9 +749,10 @@ services:
       AUDIO_TTS_VOICE: alloy
       ENABLE_SIGNUP: ${OPENWEBUI_ENABLE_SIGNUP:-false}
       ENABLE_FOLLOW_UP_GENERATION: ${OPENWEBUI_ENABLE_FOLLOW_UP_GENERATION:-false}
-      # A model must synthesize an answer instead of spending hundreds of
-      # iterations retrying an empty/dynamic page or traversing a repository.
-      CHAT_RESPONSE_MAX_TOOL_CALL_ITERATIONS: "12"
+      # The derived image reserves the last round for a tool-free synthesis.
+      # Eight rounds leave room for real operator work without allowing a
+      # simple repository lookup to fan out into dozens of calls.
+      CHAT_RESPONSE_MAX_TOOL_CALL_ITERATIONS: "8"
       USER_AGENT: "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
       # Seed native MCP connections on a fresh Open WebUI database. Secrets
       # stay inside the tool containers, so these internal URLs need no keys.