fix(proxy): correct usage accounting on format-conversion paths

Audited all proxy format-conversion paths (Chat<->Message, Chat<->Response,
Gemini<->Message) for usage/cache metering. Five issues found and fixed.
The dedup mechanism (request_id PK, proxy/session source isolation) is
untouched, so no double-counting is introduced.

- A (Claude + openai_chat, streaming): inject stream_options.include_usage
  so OpenAI-compatible upstreams emit usage in the SSE tail. Without it the
  converted Anthropic message_delta was all-zero and the whole request's
  input/output/cache was dropped. Same root cause as the already-fixed
  Codex Chat path; the injection is extracted into a shared helper
  (transform::inject_openai_stream_include_usage) reused by both paths.

- C (Claude + gemini_native): subtract cachedContentTokenCount from
  input_tokens in build_anthropic_usage so input becomes fresh input
  (Anthropic semantics). Previously the cache-hit tokens were billed twice
  because this path meters as app_type="claude" (input_includes_cache_read
  = false) while Gemini's promptTokenCount includes the cache.

- D (Codex + openai_chat, streaming): gate log_usage on
  has_billable_tokens() to skip the synthetic all-zero usage the converter
  emits when a non-compliant upstream omits usage, preventing empty-row
  request-count inflation.

- P2 (from_claude_stream_events): use has_billable_tokens() for the return
  gate instead of input>0||output>0, so a fully-cached streamed request
  (cache_read>0, input==output==0) is still recorded. Affects all
  Claude-streaming paths, not just Gemini.

- P3 (Codex Chat->Responses, non-streaming): apply the same
  has_billable_tokens() filter the streaming branch got, since the
  synthesized all-zero usage makes from_codex_response return Some and
  bypass the `if let Some` guard.

Add TokenUsage::has_billable_tokens() as the unified predicate. New tests
cover include_usage injection, gemini input subtraction, the gate itself,
cache-only stream recording, and synthetic all-zero codex usage.
Full lib suite: 1569 passed.

src-tauri/src/proxy/handlers.rs

@@ -765,6 +765,15 @@ async fn handle_codex_chat_to_responses_transform(
                 move |events, first_token_ms| {
                     let usage =
                         TokenUsage::from_codex_stream_events_auto(&events).unwrap_or_default();
+                    // 上游遵守 OpenAI 语义省略 usage 时，Chat→Responses 转换器会合成一个
+                    // 全 0 的 response.completed，from_codex_response 对 input/output 字段
+                    // 存在（哪怕=0）即返回 Some。缺 nonzero 闸门会让全 0 usage 也被写入：
+                    // message_id=None → dedup_request_id 退化为随机 UUID，无法去重，每笔
+                    // 请求插入一条无意义空行、虚增请求数。对齐 Claude transform handler 的 skip。
+                    if !usage.has_billable_tokens() {
+                        log::debug!("[Codex] 流式响应 usage 全 0 或缺失，跳过消费记录");
+                        return;
+                    }
                     let model = usage.model.clone().unwrap_or_else(|| request_model.clone());
                     let latency_ms = start_time.elapsed().as_millis() as u64;
 
@@ -844,7 +853,13 @@ async fn handle_codex_chat_to_responses_transform(
         .record_response(&responses_response)
         .await;
 
-    if let Some(usage) = TokenUsage::from_codex_response_auto(&responses_response) {
+    // 上游非流式 Chat 省略 usage 时，chat_usage_to_responses_usage 会合成全 0 usage
+    // (transform_codex_chat.rs:1581)，from_codex_response 对 input/output 字段存在(哪怕=0)
+    // 即返回 Some。用 has_billable_tokens 闸门跳过全 0，避免空行虚增请求数——与流式分支
+    // 及 Claude transform handler 的 skip 行为对齐。
+    if let Some(usage) = TokenUsage::from_codex_response_auto(&responses_response)
+        .filter(TokenUsage::has_billable_tokens)
+    {
         let model = responses_response
             .get("model")
             .and_then(|m| m.as_str())