feat(generation): add conditional thinking classifier

Routes simple/conversational messages to think=false automatically,
even when the user has thinking enabled. Patterns checked: word count
thresholds, complexity keywords, code blocks, skip patterns for greetings
and simple CRUD. Workspace mode (think=true from frontend) still benefits
from the classifier on short messages.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/fabledassistant/services/generation_task.py

@@ -35,6 +35,65 @@ _TOOL_CALL_MARKER = re.compile(r"^\s*\[TOOL_CALLS\]\s*", re.IGNORECASE)
 
 DB_FLUSH_INTERVAL = 5.0  # seconds between partial DB flushes
 
+# ---------------------------------------------------------------------------
+# Conditional thinking classifier
+# ---------------------------------------------------------------------------
+
+# Patterns that force think=True even on short messages
+_THINK_FORCE = re.compile(
+    r"\b("
+    r"analyz|compar|explain\s+why|help\s+me\s+(think|plan|understand|figure\s+out)|"
+    r"step[- ]by[- ]step|debug|troubleshoot|diagnos|"
+    r"pros\s+and\s+cons|trade[- ]?off|"
+    r"architect|design\s+(a|the|my|this)|"
+    r"write\s+a\s+(detailed|long|comprehensive|full)|"
+    r"brainstorm|outline\s+(a|the|my)|"
+    r"what\s+(are|is)\s+the\s+(best|difference|relationship|impact|implication)|"
+    r"how\s+(do|does|should|would|can)\s+.{0,40}\s+work|"
+    r"why\s+(is|are|does|do|did|would|should)\b"
+    r")",
+    re.IGNORECASE,
+)
+
+# Patterns that force think=False regardless of message length
+_THINK_SKIP = re.compile(
+    r"^(hi|hey|hello|thanks|thank\s+you|ok|okay|got\s+it|sounds\s+good|"
+    r"great|perfect|sure|yes|no|yep|nope|nice|cool|awesome|"
+    r"what('s| is) \d|what time|how many|remind me|add (a |an )?(task|note|reminder)|"
+    r"create (a |an )?(task|note)|delete|update|mark .{0,30} (done|complete))\b",
+    re.IGNORECASE,
+)
+
+_WORD_COUNT_THRESHOLD = 60  # messages over this word count always use think=True
+_SHORT_MESSAGE_THRESHOLD = 12  # messages under this always use think=False
+
+
+def _should_think(user_content: str, think_requested: bool) -> bool:
+    """Return whether extended thinking should be used for this request.
+
+    If the caller didn't request thinking, we never enable it. If they did,
+    we check whether the message is complex enough to warrant the overhead.
+    """
+    if not think_requested:
+        return False
+
+    text = user_content.strip()
+    word_count = len(text.split())
+
+    if word_count <= _SHORT_MESSAGE_THRESHOLD:
+        return False
+    if _THINK_SKIP.match(text):
+        return False
+    if word_count >= _WORD_COUNT_THRESHOLD:
+        return True
+    if "```" in text:
+        return True
+    if _THINK_FORCE.search(text):
+        return True
+
+    return False
+
+
 # Human-readable labels for each tool, shown in the status indicator
 _TOOL_LABELS: dict[str, str] = {
     "create_task": "Creating task",
@@ -202,6 +261,9 @@ async def run_generation(
     # Emit context event
     buf.append_event("context", {"context": context_meta})
 
+    # Apply thinking classifier — downgrade think=True for simple/conversational messages
+    think = _should_think(user_content, think)
+
     t_start = time.monotonic()
     timing: dict = {
         "think": think,