fix(onboard): infer custom model image input

docs/start/wizard-cli-automation.md

@@ -166,11 +166,13 @@ openclaw onboard --non-interactive \
       --custom-api-key "$CUSTOM_API_KEY" \
       --custom-provider-id "my-custom" \
       --custom-compatibility anthropic \
+      --custom-image-input \
       --gateway-port 18789 \
       --gateway-bind loopback
     ```
 
     `--custom-api-key` is optional. If omitted, onboarding checks `CUSTOM_API_KEY`.
+    OpenClaw marks common vision model IDs as image-capable automatically. Add `--custom-image-input` for unknown custom vision IDs, or `--custom-text-input` to force text-only metadata.
 
     Ref-mode variant:
 
@@ -184,6 +186,7 @@ openclaw onboard --non-interactive \
       --secret-input-mode ref \
       --custom-provider-id "my-custom" \
       --custom-compatibility anthropic \
+      --custom-image-input \
       --gateway-port 18789 \
       --gateway-bind loopback
     ```

docs/start/wizard-cli-reference.md

@@ -202,6 +202,7 @@ What you set:
     - `--custom-api-key` (optional; falls back to `CUSTOM_API_KEY`)
     - `--custom-provider-id` (optional)
     - `--custom-compatibility <openai|anthropic>` (optional; default `openai`)
+    - `--custom-image-input` / `--custom-text-input` (optional; override inferred model input capability)
 
   </Accordion>
   <Accordion title="Skip">
@@ -212,6 +213,7 @@ What you set:
 Model behavior:
 
 - Pick default model from detected options, or enter provider and model manually.
+- Custom-provider onboarding infers image support for common model IDs and asks only when the model name is unknown.
 - When onboarding starts from a provider auth choice, the model picker prefers
   that provider automatically. For Volcengine and BytePlus, the same preference
   also matches their coding-plan variants (`volcengine-plan/*`,