feat(translator): add vision support for commandcode provider

Map OpenAI image_url / Claude-style image blocks to the {type:"image",
image:"<data URI|url>"} shape the command-code CLI sends to /alpha/generate
instead of dropping them to "[image omitted]". Handles data URIs, raw base64
(with media_type / image/png fallback), and remote URLs.

- Promote bugs-gemini-cursor-commandcode "image content is preserved" from
  it.fails to a real assertion (bug fixed)
- Add vision unit tests to openai-to-commandcode.test.js
- Add test-commandcode-vision.sh curl helper for live verification

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>

test-commandcode-vision.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# Test vision support for the commandcode provider in 9router.
+#
+# Usage:
+#   ./test-commandcode-vision.sh [base_url] [model]
+#   BASE_URL=http://localhost:20128 ./test-commandcode-vision.sh
+#
+# Defaults: base_url=http://localhost:20128, model=commandcode/Qwen/Qwen3.6-Max-Preview
+
+set -euo pipefail
+
+BASE_URL="${1:-${BASE_URL:-http://localhost:20128}}"
+MODEL="${2:-${MODEL:-commandcode/Qwen/Qwen3.6-Max-Preview}}"
+
+# 1x1 red pixel PNG (base64) — enough to prove the image reaches the model.
+PNG_B64="iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg=="
+
+echo "==> POST $BASE_URL/v1/chat/completions"
+echo "==> model: $MODEL"
+echo
+
+curl -sS -N "$BASE_URL/v1/chat/completions" \
+	-H "Content-Type: application/json" \
+	-d "$(
+		cat <<JSON
+{
+  "model": "$MODEL",
+  "messages": [
+    {
+      "role": "user",
+      "content": [
+        {"type": "text", "text": "What color is this image? Reply with just the color name."},
+        {"type": "image_url", "image_url": {"url": "data:image/png;base64,$PNG_B64"}}
+      ]
+    }
+  ],
+  "stream": false
+}
+JSON
+	)"
+echo