fix(advice): judge the working by its shape, not by its length

A length threshold is a blunt instrument: a legitimate advice reply can
run to a thousand characters, and a short working reply can be a few
hundred - so a threshold gets both wrong.  A 995-character advice reply
with no marker word in it was being emptied.

The reliable signal is the SHAPE.  The model's working is about
INTERPRETING the numbers - what the reading might mean, what could be
causing it, what it is unsure about.  The advice is about what to DO.

So a reply is working when it is full of the model's hedging about the
data AND contains no instruction at all.  Length is only a tie-breaker
for a reply that is both hedged and short.

    995-char legitimate advice  -> kept
    long pure working           -> dropped
    short legitimate advice     -> kept
    long working + advice       -> advice kept

Checked against the live model - a real reply comes back clean, with no
reasoning in it:

    At two weeks in, dropping from 1.055 to 1.020 is a healthy 35-point
    fall - about 64% attenuation - which is right in the normal range for
    a pale ale, though you likely still have 5 to 8 points to go...

184 tests (up from 183).

src/flask/brew_advice.py

@@ -356,31 +356,48 @@ _WORKING_LENGTH = 600
 def _is_all_working(text: str, paragraphs: list[str]) -> bool:
     """True when the reply is the model's working rather than advice.
 
-    Two signals, because either alone is unreliable:
+    The reliable signal is SHAPE, not length.  A legitimate advice reply
+    can be a thousand characters, and a short working reply can be a
+    few hundred - so length alone gets both wrong.
 
-    - **Length.** The working runs to thousands of characters; the
+    The model's working is about INTERPRETING the numbers: what the
-      advice is two to five sentences.
+    reading might mean, what could be causing it, what it is unsure
-    - **Shape.** The working interprets the numbers ("perhaps the yeast
+    about.  The advice is about what to DO.
-      is stressed, it could be that..."); the advice tells the brewer
-      what to do.
 
-    A reply that is SHORT is kept even if it has no marker word - real
+    So a reply is working when it is full of the model's hedging about
-    advice is often phrased without one ("Actually the drop is fine.
+    the data AND contains no instruction at all.
-    Wait a couple of days and check again.").
     """
-    if len(text) <= _WORKING_LENGTH:
-        # Too short to be the model's working.  It is advice, whatever
-        # it is worded like.
-        return False
-
     if _has_advice_marker(text):
         # It contains an instruction, so part of it is advice.
         return False
 
-    # Long, and nothing in it reads like an instruction.
+    lowered = text.lower()
+    hedging = sum(lowered.count(word) for word in _HEDGING_WORDS)
+
+    if hedging == 0:
+        # No instruction and no hedging about the data.  This is advice,
+        # however long it is.
+        return False
+
+    if len(text) <= _WORKING_LENGTH:
+        # Some hedging, but it is short - that is a brewer's note that
+        # happens to use a hedging word, not a page of working.
+        return False
+
+    # Hedging, no instruction, and long: the working.
     return True
 
 
+#: The words the model uses when it is working through the data rather
+#: than telling the brewer what to do.
+_HEDGING_WORDS = (
+    "perhaps", "maybe", "possibly", "could be", "might be", "might",
+    "i think", "i am not sure", "i'm not sure", "actually", "hmm",
+    "wait,", "let me", "i need to", "the question is", "unclear",
+    "i am unsure", "not sure", "unfortunately",
+)
+
+
 def _has_advice_marker(text: str) -> bool:
     """True when the text contains any advice marker at all.
 

tests/test_brew_advice.py

@@ -688,6 +688,35 @@ def test_a_short_reply_is_advice_even_without_a_marker_word():
     assert brew_advice._strip_reasoning(reply) == reply
 
 
+def test_a_long_legitimate_advice_reply_is_kept():
+    """Length alone is a blunt instrument.
+
+    A legitimate advice reply can run to a thousand characters, and a
+    short working reply can be a few hundred - so a length threshold
+    gets both wrong.  What separates them is the SHAPE: the working
+    hedges about the data, the advice tells the brewer what to do.
+    """
+    advice = (
+        "The ferment has dropped steadily since brew day and the numbers "
+        "line up with a healthy fermentation, so the yeast is clearly "
+        "working through the wort rather than sitting on it. At 19 degrees "
+        "this is on the cool side for an ale yeast and it will finish "
+        "slowly, but that is not a problem in itself. Give the ferment "
+        "another three or four days before you draw any conclusions, and "
+        "take a reading on the eighteenth so you can see whether it is "
+        "still moving. Do not raise the temperature in a hurry either, "
+        "because a sudden change while the yeast is finishing can make it "
+        "give up what it has left to give. If it is still stuck at the "
+        "same gravity after that, then it is worth rousing the yeast with "
+        "a gentle swirl and considering a fresh sachet of dry yeast, "
+        "rehydrated in the usual way and pitched at the same temperature "
+        "the beer is sitting at."
+    )
+    assert len(advice) > 600, "the sample should be longer than the threshold"
+
+    assert brew_advice._strip_reasoning(advice) == advice
+
+
 def test_a_long_reply_with_no_instruction_is_dropped():
     """Long, and nothing in it reads like an instruction - all working."""
     working = ("Let me think about this.\n\n" +