fix(commandcode): preserve images and reasoning_effort on /alpha/generate

Command Code dropped vision and ignored client effort through the router:
image blocks became "[image omitted]", HTTP image URLs were never inlined,
and reasoning_effort landed on the envelope wrapper instead of params (so the
DeepSeek family mapping remapped low -> high). The catalog also treated
deepseek/deepseek-v4.1-flash as text-only, so the vision adapter stole those
requests to another provider.

- Map OpenAI image_url / Claude image blocks (base64 or data-URI) to the
  native {type:"image", image:"data:...;base64,...", mimeType} generate block.
- Add FORMATS.COMMANDCODE to TARGETS_NEED_BASE64 so remote http(s) images are
  inlined by the existing SSRF-safe fetcher before translation.
- Write reasoning_effort inside params for targetFormat commandcode and pass
  low|medium|high|xhigh|max through unmapped; allow it in thinkingLevels.
- Provider-scoped capabilities for commandcode/cmc: vision except the CLI
  text-only denylist, thinkingFormat commandcode, so family patterns
  (deepseek-v4 -> thinkingFormat deepseek, vision false) no longer win.
- Quota Tracker: whoami + billing credits/subscriptions (credits vs plan cap,
  5h and weekly windows), labels from AI_PROVIDERS[].name.

tests/unit/capabilities.test.js

@@ -73,4 +73,26 @@ describe("getCapabilitiesForModel", () => {
       maxOutput: 128000,
     });
   });
+
+  it("CommandCode v4.1-flash is vision + effort capable", () => {
+    expect(getCapabilitiesForModel("commandcode", "deepseek/deepseek-v4.1-flash")).toMatchObject({
+      vision: true,
+      reasoning: true,
+      thinkingFormat: "commandcode",
+      thinkingEffortSupported: true,
+    });
+  });
+
+  it("CommandCode MiniMax-M3 is vision capable", () => {
+    expect(getCapabilitiesForModel("commandcode", "MiniMaxAI/MiniMax-M3").vision).toBe(true);
+  });
+
+  it("CommandCode text-only DeepSeek V4 Flash stays non-vision", () => {
+    expect(getCapabilitiesForModel("commandcode", "deepseek/deepseek-v4-flash").vision).toBe(false);
+    expect(getCapabilitiesForModel("commandcode", "deepseek/deepseek-v4-flash")).toMatchObject({
+      reasoning: true,
+      thinkingFormat: "commandcode",
+      thinkingEffortSupported: true,
+    });
+  });
 });