fix(advice): find the marker however the model formats it

The instruction asks for "ADVICE:", but the model writes "**ADVICE:**",
"## ADVICE:" or puts it in a code block.  The extraction has to cope,
because leftover markdown in the advice is visible to the brewer.

The marker is now matched case-insensitively and with the decoration the
model puts around it, and the leftover formatting is stripped.

    plain marker         -> 'Warm it to 20C and wait.'
    bold marker          -> 'Warm it to 20C and wait.'
    in a code block      -> 'Warm it to 20C and wait.'
    marker mid-text      -> 'Warm it to 20C and wait.'
    markdown heading     -> 'Warm it to 20C and wait.'
    lowercase marker     -> 'Warm it to 20C and wait.'
    no marker            -> 'Warm it to 20C and wait.'
    bold + code block    -> 'Warm it to 20C and wait.'

182 tests (up from 181).

tests/test_brew_advice.py

@@ -274,6 +274,28 @@ def test_a_reply_with_the_marker_is_kept_whole():
     assert brew_advice._strip_reasoning(reply) == advice
 
 
+def test_the_marker_is_found_however_the_model_formats_it():
+    """The model formats the marker its own way often enough to matter.
+
+    The instruction asks for "ADVICE:", but the model writes
+    "**ADVICE:**", "## ADVICE:" or puts it in a code block.  Each of
+    those has to extract the advice cleanly, with no leftover markdown.
+    """
+    advice = "Warm it to 20C and wait."
+
+    for reply in (
+        f"ADVICE:\n{advice}",
+        f"**ADVICE:**\n{advice}",
+        f"## ADVICE:\n{advice}",
+        f"```\nADVICE:\n{advice}\n```",
+        f"**ADVICE:**\n```\n{advice}\n```",
+        f"advice:\n{advice}",
+    ):
+        assert brew_advice._strip_reasoning(reply) == advice, (
+            f"the marker was not extracted cleanly from {reply!r}"
+        )
+
+
 def test_a_reply_without_the_marker_is_used_as_it_stands():
     """The safe direction when the model does not use the marker.