feat: preserve governed OpenAI tool messages in 1.4.0

Add faithful single-choice chat results, tool stream activity, error-frame retries, and isolated protocol caching.

Reject empty cached completions with the same value predicate as transport, add regression coverage, and adopt Apache-2.0.

tests/e2e/conftest.py

@@ -22,7 +22,13 @@ from polygateway.client import (
 )
 from polygateway.providers import get_provider
 from polygateway.transports.openai_compat import OpenAICompatTransport
-from polygateway.types import Effort, EmbeddingTransportResult, SourceConfig, TransportResult
+from polygateway.types import (
+    Effort,
+    EmbeddingTransportResult,
+    ResponseMode,
+    SourceConfig,
+    TransportResult,
+)
 from tests.live_evidence import (
     AttemptEvidence,
     HttpEvidence,
@@ -293,6 +299,7 @@ class ObservedTransport:
         reasoning_effort: Effort | None,
         first_token_event: asyncio.Event | None,
         content_event: asyncio.Event | None,
+        response_mode: ResponseMode,
     ) -> TransportResult:
         """与生产端口逐参数同签名。"""
         with self._capture.attempt_context(call_id):
@@ -306,6 +313,7 @@ class ObservedTransport:
                 reasoning_effort=reasoning_effort,
                 first_token_event=first_token_event,
                 content_event=content_event,
+                response_mode=response_mode,
             )
 
     async def embed(