fix: stop passing est_tokens off as measured usage

usage 帧缺失/非法时不再拿 est_tokens(最坏情形上界)当实测值,chat 与
embedding 两处兜底改记 0 并标 unavailable;打捞覆盖加 measured 前置条件,
避免 0/0 被洗成 estimated 而算出假的 0.0。embedding 全批合并扩三态(任一批
不可得 → 整体不可得),_total_cost 遇不可得批整体记 NULL。

src/polygateway/embedding.py

@@ -385,14 +385,21 @@ class EmbeddingClient:
             vectors = [_l2_normalize(v) for v in vectors]
         first = outcomes[0]
         prompt_tokens = sum(o.result.prompt_tokens for o in outcomes)
-        estimated = any(o.result.usage_source == "estimated" for o in outcomes)
+        # 三态合并优先级(解耦设计 §3.2 #10): 任一批不可得 → 整体不可得
+        sources = {o.result.usage_source for o in outcomes}
+        if "unavailable" in sources:
+            merged_source = "unavailable"
+        elif "estimated" in sources:
+            merged_source = "estimated"
+        else:
+            merged_source = "measured"
         return EmbeddingResponse(
             vectors=vectors,
             dim=first.result.dim,
             model=first.source.model,
             provider=first.source.provider,
             prompt_tokens=prompt_tokens,
-            usage_source="estimated" if estimated else "measured",
+            usage_source=merged_source,
             latency_ms=sum(o.latency_ms for o in outcomes),
             call_id=first.call_id,
             source_name=first.source.name,
@@ -400,8 +407,15 @@ class EmbeddingClient:
         )
 
     def _total_cost(self, outcomes: list[_BatchOutcome]) -> float | None:
+        """全批成本;任一批用量不可得则整体记 NULL(解耦设计 §3.2 #11)。
+
+        逐批求和会把不可得的批当 0 计入,给出一个偏低却看似有效的金额——
+        与"宁可算不出成本,也不算错成本"的不变式相悖。
+        """
         if self._pricing is None:
             return None
+        if any(o.result.usage_source == "unavailable" for o in outcomes):
+            return None
         costs = [self._pricing.cost(o.source.model, o.result.prompt_tokens, 0) for o in outcomes]
         known = [c for c in costs if c is not None]
         return sum(known) if known else None

src/polygateway/transports/openai_compat.py

@@ -139,11 +139,31 @@ def _strip_think(content: str) -> tuple[str, str]:
 
 
 def _resolve_usage(usage: dict[str, Any], source: SourceConfig) -> tuple[int, int, str]:
-    """usage 帧读取;缺失/非法按 est_tokens 保守兜底并标 estimated(CHS invokers.py:241)。"""
+    """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。
+    """
     prompt, completion = usage.get("prompt_tokens"), usage.get("completion_tokens")
     if isinstance(prompt, int) and isinstance(completion, int) and prompt + completion > 0:
         return prompt, completion, "measured"
-    return 0, source.est_tokens, "estimated"
+    return 0, 0, "unavailable"
+
+
+def _resolve_stream_usage(
+    sink: dict[str, Any], salvaged: bool, source: SourceConfig
+) -> 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)
+    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"
+    return prompt, completion, usage_source
 
 
 def _extract_vectors(
@@ -169,11 +189,11 @@ def _extract_vectors(
 
 
 def _resolve_embedding_usage(data: dict[str, Any], source: SourceConfig) -> tuple[int, str]:
-    """usage 读取;缺失/非法按 est_tokens 保守兜底并标 estimated(与 chat 同口径)。"""
+    """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:
         return prompt, "measured"
-    return source.est_tokens, "estimated"
+    return 0, "unavailable"
 
 
 def _parse_embedding_payload(
@@ -331,9 +351,7 @@ 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_usage(sink.get("usage") or {}, source)
-        if salvaged:
-            usage_source = "estimated"  # 打捞路径强制 estimated(设计 §6)
+        prompt, completion, usage_source = _resolve_stream_usage(sink, salvaged, source)
         return TransportResult(
             content=content,
             thinking=thinking,

src/polygateway/types.py

@@ -284,7 +284,7 @@ class EmbeddingTransportResult:
     vectors: list[list[float]]
     dim: int
     prompt_tokens: int
-    usage_source: str  # measured | estimated
+    usage_source: str  # measured | estimated | unavailable
     raw: dict[str, Any]