refactor: drop the now-unused source parameter from usage resolvers

三态兜底不再读源配置,_resolve_usage / _resolve_stream_usage /
_resolve_embedding_usage 的 source 形参已成死参数;保留它等于在签名上继续
宣称用量口径依赖源配置,与本次改动切断该依赖的意图相悖。同步三个调用点
与测试的直接调用;SourceConfig 仍被文件内错误翻译等函数使用,import 保留。

src/polygateway/transports/openai_compat.py

@@ -138,12 +138,13 @@ def _strip_think(content: str) -> tuple[str, str]:
     return _THINK_PATTERN.sub("", content).strip(), match.group(1).strip()
 
 
-def _resolve_usage(usage: dict[str, Any], source: SourceConfig) -> tuple[int, int, str]:
+def _resolve_usage(usage: dict[str, Any]) -> tuple[int, int, str]:
     """usage 帧读取;缺失/非法记 0/0 并标 unavailable(est_tokens 解耦设计 §3.2 #3)。
 
     不再拿 `est_tokens` 兜底: 它按 CHS 定义是"最坏情形上界",拿上界当实测值
     只会系统性高估账单;宁可把用量记成显式的"不可得"(cost 随之为 NULL),
-    让缺口可被统计,也不编一个看似有效的数字。
+    让缺口可被统计,也不编一个看似有效的数字。用量口径自此不依赖源配置,
+    故不再收 `SourceConfig`。
     """
     prompt, completion = usage.get("prompt_tokens"), usage.get("completion_tokens")
     if isinstance(prompt, int) and isinstance(completion, int) and prompt + completion > 0:
@@ -151,15 +152,13 @@ def _resolve_usage(usage: dict[str, Any], source: SourceConfig) -> tuple[int, in
     return 0, 0, "unavailable"
 
 
-def _resolve_stream_usage(
-    sink: dict[str, Any], salvaged: bool, source: SourceConfig
-) -> tuple[int, int, str]:
+def _resolve_stream_usage(sink: dict[str, Any], salvaged: bool) -> tuple[int, int, str]:
     """流式用量口径: 打捞路径把 measured 降级为 estimated,unavailable 原样保留。
 
     前置条件不可省(解耦设计 §3.2 #4): usage 帧本就缺失时 `0/0` 会被洗成
     `estimated`,进而按 token 换算出一个假的 `0.0` 成本。
     """
-    prompt, completion, usage_source = _resolve_usage(sink.get("usage") or {}, source)
+    prompt, completion, usage_source = _resolve_usage(sink.get("usage") or {})
     if salvaged and usage_source == "measured":
         # 收到 usage 帧但流被截断: 数字真实、可信度降级(M1 设计 §6)
         usage_source = "estimated"
@@ -188,7 +187,7 @@ def _extract_vectors(
     return vectors
 
 
-def _resolve_embedding_usage(data: dict[str, Any], source: SourceConfig) -> tuple[int, str]:
+def _resolve_embedding_usage(data: dict[str, Any]) -> tuple[int, str]:
     """usage 读取;缺失/非法记 0 并标 unavailable(与 chat 同口径,设计 §3.2 #3)。"""
     prompt = (data.get("usage") or {}).get("prompt_tokens")
     if isinstance(prompt, int) and prompt > 0:
@@ -206,7 +205,7 @@ def _parse_embedding_payload(
     except json.JSONDecodeError as exc:
         raise ResultInvalidError(f"{source.name} embedding 响应非 JSON: {exc}", **ctx) from exc
     vectors = _extract_vectors(data, source, expected_count, ctx)
-    prompt_tokens, usage_source = _resolve_embedding_usage(data, source)
+    prompt_tokens, usage_source = _resolve_embedding_usage(data)
     return EmbeddingTransportResult(
         vectors=vectors,
         dim=len(vectors[0]),
@@ -351,7 +350,7 @@ class OpenAICompatTransport:
         salvaged = self._check_done(sink, content_parts, thinking_parts, source)
         content, thinking = self._finalize_text(content_parts, thinking_parts, profile)
         self._reject_empty_completion(content, source)
-        prompt, completion, usage_source = _resolve_stream_usage(sink, salvaged, source)
+        prompt, completion, usage_source = _resolve_stream_usage(sink, salvaged)
         return TransportResult(
             content=content,
             thinking=thinking,
@@ -433,7 +432,7 @@ class OpenAICompatTransport:
             [message.get("content") or ""], [message.get("reasoning_content") or ""], profile
         )
         self._reject_empty_completion(content, source)
-        prompt, completion, usage_source = _resolve_usage(body.get("usage") or {}, source)
+        prompt, completion, usage_source = _resolve_usage(body.get("usage") or {})
         return TransportResult(
             content=content,
             thinking=thinking,