fix(tests): the prompt arm has no act to hold, so it carries no checkpoint (#4214)

CI 7126: 1 failed, 2227 passed — down from 14. The last one was mine, and a
different mistake from the batch before it: I widened four assertions on the
literal `{"context": "", "rule_ids": []}` by replacing the string, without
checking which arm each test was calling. Three are the tool arm. The fourth,
`test_the_prompt_arm_says_nothing_when_asked_nothing`, is not.

The distinction is real rather than an omission, so the assertion goes back
with it written down. The two ACT arms can hold a call because there is a
composed act to hold. The prompt arm fires on the operator's message, before
anything has been decided — there is nothing to put a rule in front of, and a
checkpoint there would have to guess at an act that does not exist yet.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

tests/test_rule_usage_wiring.py

@@ -508,7 +508,12 @@ async def test_the_prompt_arm_says_nothing_when_asked_nothing():
         stack.enter_context(patch.object(pc, "record_rule_surfaced", MagicMock()))
         out = await pc.build_prompt_rule_hint(1, "   ")
 
-    assert out == {"context": "", "rule_ids": [], "checkpoint": {}}
+    # NO `checkpoint` KEY, and that is the distinction rather than an
+    # oversight (#4214). The two ACT arms can hold a call because there is
+    # a composed act to hold; this arm fires on the operator's message,
+    # before anything has been decided, so there is nothing to put a rule
+    # in front of. A checkpoint here would have to guess at an act.
+    assert out == {"context": "", "rule_ids": []}
     search.assert_not_called()
     log.assert_not_called()