feat: keep the gateway's words on the OCR branches too

Issue #10 Task 4: the OCR side said only 'HTTP 404'. The issue reported
the chat path, but the batch that lost its 400 was reading tables - the
same blind spot, one transport over. Reuses the shared summarizer.

src/polygateway/transports/monkey_ocr.py

@@ -24,6 +24,11 @@ from polygateway.errors import (
     SourceDeadError,
     TransientError,
 )
+from polygateway.transports._http_errors import (
+    compose_message,
+    response_body,
+    summarize_body,
+)
 from polygateway.types import (
     OcrLayoutElement,
     OcrLayoutTransportResult,
@@ -74,13 +79,20 @@ def _translate_http_errors(source_name: str, operation: str) -> Iterator[None]:
 def _classify_status(
     exc: httpx.HTTPStatusError, source_name: str, operation: str
 ) -> TransientError | SourceDeadError | RequestRejectedError:
+    """HTTP 状态码 → 错误四分类,**全部分支**携带响应体摘要(issue #10)。
+
+    分类映射本身零变更;摘要口径与 chat 侧共用同一实现,不得在此另起一份——
+    "只有一个分支用了响应体"正是 issue #10 的成因。
+    """
     status = exc.response.status_code
+    summary = summarize_body(response_body(exc.response))
     ctx: dict[str, Any] = {
         "source_name": source_name,
         "status_code": status,
         "operation": operation,
+        "body_text": summary,
     }
-    message = f"{source_name} OCR {operation} HTTP {status}"
+    message = compose_message(f"{source_name} OCR {operation} HTTP {status}", summary)
     if status >= 500 or status == 429:
         return TransientError(message, **ctx)
     if status in (401, 403):

tests/unit/test_monkey_ocr.py

@@ -19,7 +19,11 @@ from polygateway.errors import (
     SourceDeadError,
     TransientError,
 )
-from polygateway.transports.monkey_ocr import MonkeyOcrTransport, _parse_middle_json
+from polygateway.transports.monkey_ocr import (
+    MonkeyOcrTransport,
+    _classify_status,
+    _parse_middle_json,
+)
 from polygateway.types import SourceConfig
 
 
@@ -306,6 +310,40 @@ class TestErrorTranslation:
             await t.recognize_text(image=b"jpg", source=_source(), call_id="c1")
         assert ei.value.status_code == status
 
+    @pytest.mark.parametrize(
+        ("status", "exc_type"),
+        [(502, TransientError), (401, SourceDeadError), (404, RequestRejectedError)],
+    )
+    async def test_body_survives_every_branch(self, status, exc_type):
+        """issue #10: OCR 侧 message 原本只有 HTTP 状态码,拒绝理由同样丢失。"""
+        body = '{"detail":"unsupported image mode CMYK"}'
+        t = _transport_for(_routes(text_resp=httpx.Response(status, content=body.encode())))
+        with pytest.raises(exc_type) as ei:
+            await t.recognize_text(image=b"jpg", source=_source(), call_id="c1")
+        assert ei.value.body_text == body
+        assert str(ei.value).endswith(f" | {body}")
+
+    def test_unread_body_degrades_without_changing_class(self):
+        """取不到 body 时降级空串: 绝不能让 ResponseNotRead 逃出错误四分类。
+
+        直接测纯函数而非走 MockTransport——真实客户端对非 stream 请求总会读完
+        响应,未读态只可能在将来给 OCR 加 stream 时出现,而那正是要防的场景。
+        """
+
+        class _Unread(httpx.SyncByteStream):
+            def __iter__(self):
+                yield b"body"
+
+        exc = httpx.HTTPStatusError(
+            "404",
+            request=httpx.Request("POST", "http://ocr.example/ocr/text"),
+            response=httpx.Response(404, stream=_Unread()),
+        )
+        err = _classify_status(exc, "monkey_1", "text")
+        assert isinstance(err, RequestRejectedError)
+        assert err.body_text == ""
+        assert str(err) == "monkey_1 OCR text HTTP 404"
+
     async def test_connect_error_transient(self):
         def handler(request):
             raise httpx.ConnectError("refused", request=request)