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/unit/test_client.py

@@ -232,6 +232,7 @@ class _ScriptedGenClockTransport:
         reasoning_effort,
         first_token_event,
         content_event,
+        response_mode,
     ):
         self.calls.append(call_id)
         result = self._results.pop(0)
@@ -1844,6 +1845,7 @@ class _ClockJumpTransport:
         reasoning_effort,
         first_token_event,
         content_event,
+        response_mode,
     ):
         self.calls.append(call_id)
         self._clock.advance(self._jump)