llm-proxy(app): gemma 反向代理 + token 鉴权 + /chat web UI

新 service，ns `llm-proxy`，域 `llm.famzheng.me`。
- POST /v1/chat/completions — OpenAI 兼容透传到 mochi 同款 backend
  gateway (gemma-4-31b-it)；一期强制 stream=false，SSE 留二期
- 鉴权: `Authorization: token <PROXY_AUTH_TOKEN>` 或同款 Bearer；
  常时间比较防 timing；空 expected 一律拒
- GET /chat — 自带极简 HTML chat UI（token 走 localStorage，
  附 curl example details）；/ 跳转到 /chat
- Secrets `llm-proxy/proxy-credentials` 已 kubectl 手工创建：
  BACKEND_TOKEN (上游) + PROXY_AUTH_TOKEN (对外)
- 13 个 cargo test 覆盖 auth 多个 scheme / 边界 + body
  改写 (stream=false 强制注入)

Cargo.lock

@@ -649,6 +649,20 @@ version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
+[[package]]
+name = "llm-proxy"
+version = "0.1.0"
+dependencies = [
+ "axum",
+ "cube-core",
+ "reqwest",
+ "serde",
+ "serde_json",
+ "tokio",
+ "tower-http",
+ "tracing",
+]
+
 [[package]]
 name = "lock_api"
 version = "0.4.14"