From e3022470226ef2b1ce29934fc4b03d7108e4646a Mon Sep 17 00:00:00 2001
From: iomgaa <iomgaaycz@gmail.com>
Date: Sun, 16 Aug 2026 06:01:38 -0400
Subject: [PATCH] feat: let every gateway error carry what the gateway said

Issue #10 Task 1: a rejected call's reason had nowhere to live. The
field goes on the base class because these errors all come from one HTTP
response - which class it is and what the peer said are orthogonal.
---
 src/polygateway/errors.py | 34 ++++++++++++++++++++++++++++++--
 tests/unit/test_errors.py | 41 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/src/polygateway/errors.py b/src/polygateway/errors.py
index 1473c91..6fdf8c5 100644
--- a/src/polygateway/errors.py
+++ b/src/polygateway/errors.py
@@ -35,7 +35,26 @@ SOURCE_REASONS = frozenset(
 
 
 class PolyGatewayError(Exception):
-    """库内一切领域错误的基类,携带来源上下文便于遥测与日志定位。"""
+    """库内一切领域错误的基类,携带来源上下文便于遥测与日志定位。
+
+    `body_text` 是**非 2xx 响应体的摘要**——网关拒绝这次调用时说的话(issue #10)。
+    它与 `ResultInvalidError.raw_text` 是两回事,严禁混用:
+
+    ==============  ==================================================
+    ``body_text``   **非 2xx** 的 HTTP 错误响应体: 对方**拒绝**的理由
+    ``raw_text``    **2xx** 但内容不可解析时的模型输出原文
+    ==============  ==================================================
+
+    加在基类而非某个子类,是因为这些错误全部由同一个 HTTP 响应翻译而来——
+    "对方说了什么"与"它属于哪一类"正交。scope 级错误(`GatewayUnavailableError`
+    一族)继承到的恒空值不是噪音,而是"没有单一响应体可言"的如实表达。
+
+    **内容已由 transport 层截断**(`transports/_http_errors.summarize_body`),
+    且可能包含网关对请求的回显——库不做脱敏: 它不知道下游哪些字段敏感,
+    猜测式脱敏只会同时丢掉诊断价值与安全性。
+
+    本字段是**旁路数据**,不参与任何治理判定(重试/换源/熔断计数/限流结算)。
+    """
 
     def __init__(
         self,
@@ -44,11 +63,13 @@ class PolyGatewayError(Exception):
         source_name: str | None = None,
         status_code: int | None = None,
         operation: str | None = None,
+        body_text: str = "",
     ) -> None:
         super().__init__(message)
         self.source_name = source_name
         self.status_code = status_code
         self.operation = operation
+        self.body_text = body_text
 
 
 class TransientError(PolyGatewayError):
@@ -64,7 +85,16 @@ class SourceDeadError(PolyGatewayError):
 
 
 class RequestRejectedError(PolyGatewayError):
-    """请求被拒(400/坏输入): 不重试不换源,直接上抛。"""
+    """请求被拒(400/坏输入): 不重试不换源,直接上抛。
+
+    **经中转部署时请注意**(issue #10 下游实测): 第三方 API 中转服务自身抖动
+    时也会回 400,从状态码上与供应商说"你的输入有问题"无法区分。下游曾观测到
+    同一份字节(sha256 一致)重发 15 次全部成功,且失败那次 `prompt_tokens=0`、
+    耗时远低于任何成功调用——请求在推理开始前就被挡了。本库仍按确定性失败处理
+    (对直连供应商而言重试只会白烧配额),批处理场景的下游宜自备兜底分类;
+    `body_text` 即为此提供判据: 中转抖动的响应体与供应商的 `invalid_request_error`
+    形态不同。
+    """
 
 
 class ResultInvalidError(PolyGatewayError):
diff --git a/tests/unit/test_errors.py b/tests/unit/test_errors.py
index a440f81..ca5646c 100644
--- a/tests/unit/test_errors.py
+++ b/tests/unit/test_errors.py
@@ -34,6 +34,43 @@ class TestBaseShape:
         assert TransientError("429", retry_after_s=2.5).retry_after_s == 2.5
 
 
+class TestBodyText:
+    """issue #10: 非 2xx 的响应体摘要必须有承载处,否则拒绝理由事后不可查。"""
+
+    @pytest.mark.parametrize(
+        "cls", (PolyGatewayError, TransientError, SourceDeadError, RequestRejectedError)
+    )
+    def test_defaults_empty_and_accepts_summary(self, cls):
+        assert cls("boom").body_text == ""
+        assert cls("boom", body_text='{"error":{"code":"bad"}}').body_text == (
+            '{"error":{"code":"bad"}}'
+        )
+
+    def test_result_invalid_keeps_both_fields_apart(self):
+        """`body_text`(非 2xx 的拒绝理由)与 `raw_text`(2xx 的不可解析输出)不得混用。"""
+        exc = ResultInvalidError("bad json", raw_text="{oops", body_text="")
+        assert exc.raw_text == "{oops"
+        assert exc.body_text == ""
+
+    @pytest.mark.parametrize(
+        "exc",
+        (
+            AllSourcesExhausted(scope="llm", reason="stalled", retry_after_s=1.0),
+            CircuitOpenError(scope="llm", retry_after_s=1.0),
+            GovernanceBackendError("redis down", scope="llm"),
+        ),
+    )
+    def test_scope_level_errors_carry_no_body(self, exc):
+        """scope 级失败没有单一响应体可言,空串是如实表达而非噪音。"""
+        assert exc.body_text == ""
+
+    def test_body_text_does_not_leak_into_str(self):
+        """字段是旁路数据: 加了它不得改变任何既有异常的 str() 输出。"""
+        assert str(RequestRejectedError("qwen_1 请求被拒: 400", body_text="whatever")) == (
+            "qwen_1 请求被拒: 400"
+        )
+
+
 class TestResultInvalid:
     def test_carries_diagnosis(self):
         exc = ResultInvalidError(
@@ -134,9 +171,7 @@ class TestGovernanceBackendReason:
         assert "governance_backend_down" in SCOPE_REASONS
 
     def test_gateway_unavailable_accepts_the_new_reason(self):
-        exc = AllSourcesExhausted(
-            scope="LLM", reason="governance_backend_down", retry_after_s=0.0
-        )
+        exc = AllSourcesExhausted(scope="LLM", reason="governance_backend_down", retry_after_s=0.0)
         assert exc.reason == "governance_backend_down"
 
     def test_retry_after_default_is_non_zero(self):