fix(llm): catch "I am unable to" phrasing in refusal detection

The lexical pattern only matched the "I'm unable to" contraction, so
spelled-out refusals like "I am unable to comply with your instruction"
fell through undetected without an embedding model configured.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

src/comfydv/_llm/retry.py

@@ -62,7 +62,7 @@ REFUSAL_LEXICAL_PATTERNS: tuple[re.Pattern, ...] = tuple(
     for p in (
         r"\bI\s*(?:'m|\s+am)?\s*(?:cannot|can't|won't|will not)\b[^.]{0,60}?\b"
         r"(?:generate|create|produce|write|provide|help|assist|describe|depict|continue)\b",
-        r"\bI'm (?:not able|unable) to\b",
+        r"\bI(?:'m|\s+am) (?:not able|unable) to\b",
         r"\bI don't feel comfortable\b",
         r"\bI'm sorry,?\s*(?:but\s+)?I\s*(?:can't|cannot)\b",
         r"\bas an AI\b[^.]{0,60}?\b(?:cannot|can't|unable|not able)\b",

tests/test_llm_retry.py

@@ -50,6 +50,7 @@ class TestLexicalDetection:
         blatant = [
             "I cannot generate that image for you.",
             "I'm not able to help with this request.",
+            "I am unable to comply with your instruction.",
             "I don't feel comfortable creating this content.",
             "I'm sorry, but I can't produce that description.",
             "As an AI, I'm unable to depict this scenario.",