fix(openclaw): configure gemini-3.8-flash vision model, document Issue 17, and update wiki submodule

docs/adr/0002-openclaw-model-selection-tiering-and-economics.md

@@ -76,8 +76,8 @@ How do we architect the full-spectrum model selection across **all modalities**
 │                 │ │                 │   │                 │   │ 2. gemini-3-pro-│ │ flash-tts       │
 │ Vision Fallback:│ │                 │   │                 │   │    image        │ │ (FB: MiniMax 2.8│
 │ google/         │ │                 │   │                 │   │                 │ │  Speech HD)     │
-│ gemini-3.1-     │ │                 │   │                 │   │                 │ │                 │
-│ flash-image     │ │                 │   │                 │   │                 │ │                 │
+│ gemini-3.8-     │ │                 │   │                 │   │                 │ │                 │
+│ flash           │ │                 │   │                 │   │                 │ │                 │
 └─────────────────┘ └─────────────────┘   └─────────────────┘   └─────────────────┘ └─────────────────┘
 ```
 
@@ -110,7 +110,7 @@ How do we architect the full-spectrum model selection across **all modalities**
 
 ### 4. Vision Input vs. Text-to-Image Generation (Tier 4)
 * **Crucial Distinction**:
-  - **Vision Input (`imageModel`)**: Reading photos sent to Telegram (e.g. food ingredients, plants, receipts). Handled natively by `z-ai/glm-5.3-flash`, with `google/gemini-3.1-flash-image` as fallback.
+  - **Vision Input (`imageModel`)**: Reading photos sent to Telegram (e.g. food ingredients, plants, receipts). Handled by `google/gemini-3.8-flash` or `z-ai/glm-5.3-flash`, with `google/gemini-2.5-flash` as fallback.
   - **Text-to-Image Synthesis (`mediaModels.image`)**: Creating new pictures upon user request (e.g. *"Zeichne mir ein Profilbild von Octobot"*). Chat LLMs return 404 here.
 * **Image Synthesis Engine**:
   - **Primary**: `openrouter/google/gemini-3.1-flash-image` (Nano Banana 2).