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。

tests/unit/test_usage_source_domain.py

@@ -9,20 +9,28 @@
 telemetry 三层,放进最内层内核的类型测试会让它反向依赖具体实现。
 
 覆盖的生产点(设计 §3.2 逐处改动表的字面量产出方):
-`_resolve_usage`、`_resolve_embedding_usage`、`EmbeddingClient._merge`、
-`TelemetryEmitter.emit_attempt/emit_cache_hit/emit_terminal_failure`。
+`_resolve_usage`、`_resolve_embedding_usage`、`_resolve_stream_usage`(打捞覆盖)、
+`EmbeddingClient._merge`、`EmbeddingClient.embed` 空输入短路、
+`OcrClient._emit`、`TelemetryEmitter.emit_attempt/emit_cache_hit/emit_terminal_failure`。
 """
 
 import itertools
+import json
 
+import httpx
 import pytest
 
 from polygateway.backends.memory.breaker import InMemoryGate
 from polygateway.backends.memory.limiter import InMemoryLimiter
 from polygateway.embedding import EmbeddingClient, _BatchOutcome
 from polygateway.middleware.telemetry import TelemetryEmitter
+from polygateway.ocr import OcrClient
 from polygateway.sources import RoundRobinSelector
-from polygateway.transports.openai_compat import _resolve_embedding_usage, _resolve_usage
+from polygateway.transports.openai_compat import (
+    OpenAICompatTransport,
+    _resolve_embedding_usage,
+    _resolve_usage,
+)
 from polygateway.types import (
     USAGE_SOURCES,
     BackpressurePolicy,
@@ -31,6 +39,7 @@ from polygateway.types import (
     EmbeddingTransportResult,
     GlobalLimits,
     LLMResponse,
+    OcrTextTransportResult,
     RetryPolicy,
     SourceConfig,
 )
@@ -89,6 +98,94 @@ def test_resolve_embedding_usage_stays_in_domain(data):
     assert _resolve_embedding_usage(data, _src())[1] in USAGE_SOURCES
 
 
+def _sse(*frames, done):
+    """构造 SSE 响应;done=False 触发打捞路径(`_complete_stream` 的覆盖分支)。"""
+    text = "".join(f"data: {json.dumps(f)}\n\n" for f in frames) + (
+        "data: [DONE]\n\n" if done else ""
+    )
+    return httpx.Response(200, content=text.encode(), headers={"content-type": "text/event-stream"})
+
+
+@pytest.mark.parametrize("usage", [{"prompt_tokens": 11, "completion_tokens": 7}, None])
+async def test_salvage_override_stays_in_domain(usage):
+    """打捞覆盖(`openai_compat._complete_stream`)是第三个字面量产出方。"""
+    frames = [{"choices": [{"delta": {"content": "partial"}}]}]
+    if usage is not None:
+        frames.append({"choices": [], "usage": usage})
+    transport = OpenAICompatTransport(
+        client_factory=lambda src: httpx.AsyncClient(
+            base_url=src.base_url,
+            transport=httpx.MockTransport(lambda request: _sse(*frames, done=False)),
+        )
+    )
+    source = SourceConfig(
+        name="s1",
+        provider="qwen",
+        base_url="https://gw.example/v1",
+        api_key="sk",
+        model="m",
+        timeout_s=10.0,
+        est_tokens=4000,
+        missing_done="salvage",
+    )
+    result = await transport.complete(
+        messages=[{"role": "user", "content": "hi"}],
+        source=source,
+        stream=True,
+        overlay={},
+        call_id="cid",
+    )
+    assert result.usage_source in USAGE_SOURCES
+
+
+class _ScriptedOcrTransport:
+    async def recognize_text(self, *, image, source, call_id):
+        return OcrTextTransportResult(text="LINE-1", raw={"task_type": "text"})
+
+    async def parse_layout(self, *, image, source, call_id):
+        raise NotImplementedError
+
+    async def check_health(self, *, source):
+        raise NotImplementedError
+
+
+async def test_ocr_emit_stays_in_domain():
+    """`OcrClient._emit` 的字面量(ocr.py:411)同样纳入封闭性断言。
+
+    值取 `measured` 是设计 §3.3 的裁决(OCR 的 0 token 属事实);此处只断言
+    落在三态内,精确取值的防回归钉在 `test_ocr_client.py`。
+    """
+    source = SourceConfig(
+        name="m1",
+        provider="monkey",
+        base_url="http://gw.example",
+        api_key="none",
+        model="monkey-ocr",
+        timeout_s=10.0,
+    )
+    recorder = _MemoryRecorder()
+    client = OcrClient(
+        scope="ocr",
+        sources=[source],
+        selector=RoundRobinSelector(),
+        limiter=InMemoryLimiter(
+            scope="ocr",
+            sources={source.name: source},
+            global_limits=GlobalLimits(max_concurrency=0, rpm=0, tpm=0),
+            lease_ttl_s=100.0,
+        ),
+        breaker=InMemoryGate(
+            config=BreakerConfig(fail_threshold=3, cooldown_s=60.0, probe_ttl_s=120.0)
+        ),
+        transport=_ScriptedOcrTransport(),
+        retry=RetryPolicy(max_attempts=1, backoff_base_s=0.001, backoff_max_s=0.01),
+        backpressure=BackpressurePolicy(stall_window_s=300.0, poll_interval_s=0.001),
+        telemetry=recorder,
+    )
+    await client.recognize_text(b"jpg")
+    assert recorder.rows[0]["usage_source"] in USAGE_SOURCES
+
+
 def _merge_client():
     """构造仅用于调用 `_merge` 的最小 EmbeddingClient(不发起任何调用)。"""
     source = _src()