feat: strip extra_body on the embedding and OCR paths with a warning

Stripping is load-bearing, not tidying: those transports never send the
value, so leaving it would make telemetry record a parameter never sent.

tests/unit/test_embedding.py

@@ -4,11 +4,13 @@
 VT adapters/embedding.py(归一化);库裁决见设计 §7.3 表。
 """
 
+import contextlib
 import dataclasses
 import json
 
 import httpx
 import pytest
+from loguru import logger
 
 from polygateway.errors import (
     RequestRejectedError,
@@ -350,6 +352,48 @@ class TestEmbedTelemetry:
         assert len(rec.rows[1]["messages"]) < 1000  # 长文本截断后入库
 
 
+@contextlib.contextmanager
+def _captured_warnings():
+    """捕获库发出的 WARNING;loguru 不经标准 logging,pytest 的 caplog 抓不到。"""
+    messages: list[str] = []
+    sink_id = logger.add(messages.append, level="WARNING")
+    try:
+        yield messages
+    finally:
+        logger.remove(sink_id)
+
+
+class TestExtraBodyStripped:
+    """issue #4 决策 G: embedding 路径不消费 extra_body,剥离并 warning。"""
+
+    async def test_stripped_with_warning_but_assembly_succeeds(self):
+        """报错会让下游整个装配起不来,而这条路径本无采样语义(人类拍板)。"""
+        with _captured_warnings() as warnings:
+            client, _ = _embed_client([_src(extra_body={"temperature": 0})], ["ok"])
+        assert client._sources[0].extra_body == {}
+        assert any("extra_body" in m for m in warnings)
+        assert any("dimensions" in m for m in warnings)  # 文案须指路,不能只说不支持
+        await client.embed(["hi"])  # 装配后可正常工作
+
+    async def test_telemetry_never_records_a_parameter_that_was_not_sent(self):
+        """剥离的真正理由: embed payload 硬编码 {model, input},不剥离则审计表
+
+        会显示这次调用带了 temperature=0——那是数据造假,比参数失效更坏。
+        """
+        rec = _MemoryRecorder()
+        client, _ = _embed_client(
+            [_src(extra_body={"temperature": 0})], ["ok"], telemetry=rec
+        )
+        await client.embed(["hi"])
+        assert rec.rows[0]["sampling"] is None
+
+    async def test_no_warning_without_extra_body(self):
+        with _captured_warnings() as warnings:
+            client, _ = _embed_client([_src()], ["ok"])
+        assert client._sources[0].extra_body == {}
+        assert not [m for m in warnings if "extra_body" in m]
+
+
 class TestEmbeddingSettings:
     _ENV = {
         "EMBED__QWEN__1__BASE_URL": "https://gw.example/v1",

tests/unit/test_ocr_client.py

@@ -7,6 +7,7 @@ retry_exhausted/circuit_open/stalled 三组断言即设计 §6 ③ 的 G1 契约
 import asyncio
 
 import pytest
+from loguru import logger
 
 from polygateway.backends.memory.breaker import InMemoryGate
 from polygateway.backends.memory.limiter import InMemoryLimiter
@@ -377,6 +378,29 @@ class TestCheckHealth:
             await task
 
 
+class TestExtraBodyStripped:
+    """issue #4 决策 G: OCR 路径只发 multipart 表单,剥离 extra_body 并 warning。"""
+
+    def test_stripped_with_warning_but_assembly_succeeds(self):
+        messages: list[str] = []
+        sink_id = logger.add(messages.append, level="WARNING")
+        try:
+            client, _, _ = _client([_src(extra_body={"temperature": 0})], ["text"])
+        finally:
+            logger.remove(sink_id)
+        assert client._sources[0].extra_body == {}
+        assert any("extra_body" in m for m in messages)
+
+    async def test_telemetry_never_records_a_parameter_that_was_not_sent(self):
+        """不剥离则审计表会显示这次 OCR 带了 temperature=0——数据造假。"""
+        recorder = _MemoryRecorder()
+        client, _, _ = _client(
+            [_src(extra_body={"temperature": 0})], ["text"], telemetry=recorder
+        )
+        await client.recognize_text(b"IMG")
+        assert recorder.rows[0]["sampling"] is None
+
+
 class TestTelemetry:
     async def test_success_and_failure_recorded_without_image_bytes(self):
         recorder = _MemoryRecorder()