fix(advice): keep the advice when the reply is over-long

The review found a way to store the model's WORKING instead of its
advice.

The advice is at the END of the reply, so the length cap was cutting
from the front - which took the advice off and left only the working.
That is worse than no advice at all, because it looks like advice: the
brew sees a full paragraph of the model thinking about their beer, and
nothing about what to do.

Reproduced:

    input len: 2515 -> final len: 1199
    advice present? False
    TAIL: 'padding padding padding padding padding'

Two changes:

- The length cap keeps the END of the reply and cuts at a sentence
  boundary near the end, so the advice survives.
- The stripper now also catches a reply that is entirely working - no
  marker phrase, and no paragraph that reads like advice - instead of
  only catching one that says "let me think".

    input: 2515 -> stripped: 2515 -> final: 1199
    advice present? True

A short reply is untouched.

171 tests (up from 169).

src/flask/brew_advice.py

@@ -202,7 +202,28 @@ def call_ollama(prompt: str, *, url: str | None = None, model: str | None = None
     content = content.strip()
     if not content:
         raise RuntimeError("the model returned an empty response")
-    return _strip_reasoning(content)[:MAX_ADVICE_CHARS]
+    return _trim_advice(_strip_reasoning(content))
+
+
+def _trim_advice(text: str) -> str:
+    """Cut the advice down to the readable length, keeping the END.
+
+    The advice is at the end of the reply, so a plain truncation from the
+    front would cut the advice off and leave only the model's working -
+    which is worse than no advice at all, because it looks like advice.
+    So an over-long reply is cut at a sentence boundary near the end.
+    """
+    if len(text) <= MAX_ADVICE_CHARS:
+        return text
+
+    tail = text[-MAX_ADVICE_CHARS:]
+    # Start at the first sentence break in the tail, so it does not begin
+    # mid-word.
+    for separator in (". ", "? ", "! "):
+        index = tail.find(separator)
+        if index != -1 and index < 200:
+            return tail[index + 2:].strip()
+    return tail.strip()
 
 
 #: The reasoning models sometimes put their working IN the content, even
@@ -233,6 +254,16 @@ def _strip_reasoning(text: str) -> str:
     starts straight into the advice is left alone.
     """
     lowered = text.lower()
+
+    # A reply that is ALL working - no advice paragraph at all - has to
+    # be caught too.  The marker phrases are a hint, not the only signal:
+    # a reply can be pure working without ever saying "let me think".
+    paragraphs = [p.strip() for p in text.split("\n\n") if p.strip()]
+    if len(paragraphs) > 1 and not any(_looks_like_advice(p) for p in paragraphs):
+        # No paragraph reads like advice, so the whole thing is working.
+        # There is nothing to keep - the caller stores what is left.
+        return text
+
     for marker in _PREAMBLE_MARKERS:
         index = lowered.find(marker)
         # index 0 is fine - a reply can START with "Let me look at this".