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_live_evidence.py

@@ -279,6 +279,7 @@ async def _complete(observed, *, call_id="a", stream=False):
         reasoning_effort=None,
         first_token_event=None,
         content_event=None,
+        response_mode="text",
     )
 
 
@@ -1270,6 +1271,7 @@ async def test_structured_first_attempt_requires_exact_initial_messages():
                 reasoning_effort=None,
                 first_token_event=None,
                 content_event=None,
+                response_mode="text",
             )
         event = capture.attempts(session_id="first", parent_call_id="parent")[0].http[0]
         assert not request_is_valid(event)