Fix research_topic loop when intent misses and main model calls tool directly

When the intent model doesn't classify a research request (low confidence,
long message, etc.), the main model (qwen3) would correctly identify
research_topic itself and call it via the streaming tool loop. But
execute_tool("research_topic") only returns a dummy research_pending
placeholder, causing the model to see the result and retry — looping
up to MAX_TOOL_ROUNDS times.

Fix: filter research_topic out of stream_tools (the tool list given to
the main model via stream_chat_with_tools). research_topic is an
intent-only routing tool; the main model should never call it directly.
The full tools list (including research_topic) is still passed to
classify_intent so intent routing continues to work.

The _INTENT_ONLY_TOOLS frozenset makes this pattern explicit and
extensible for future intent-only tools.

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

src/fabledassistant/services/generation_task.py

@@ -237,9 +237,20 @@ async def run_generation(
         get_setting(user_id, "intent_model", ""),
     )
     intent_model = intent_model_setting or Config.OLLAMA_INTENT_MODEL or model
+
+    # research_topic is handled exclusively by the intent-first pipeline (round 0).
+    # Remove it from the tool list given to the main model so it can never be called
+    # directly via the streaming tool loop (which would just return a placeholder result
+    # and cause the model to retry in a loop).
+    _INTENT_ONLY_TOOLS = frozenset({"research_topic"})
+    stream_tools = [
+        t for t in tools
+        if t.get("function", {}).get("name") not in _INTENT_ONLY_TOOLS
+    ]
+
     logger.info(
-        "Starting generation for conv %d: model=%s, intent_model=%s, tools=%d",
-        conv_id, model, intent_model, len(tools),
+        "Starting generation for conv %d: model=%s, intent_model=%s, tools=%d (stream_tools=%d)",
+        conv_id, model, intent_model, len(tools), len(stream_tools),
     )
 
     # Phase 2: Summarize long conversation history if needed.
@@ -443,7 +454,7 @@ async def run_generation(
                 buf.append_event("status", {"status": "Generating response..."})
                 t_stream = time.monotonic()
 
-                async for chunk in _stream_with_retry(messages, model, tools, think):
+                async for chunk in _stream_with_retry(messages, model, stream_tools, think):
                     if buf.cancel_event.is_set():
                         cancelled = True
                         break
@@ -515,7 +526,7 @@ async def run_generation(
 
             buf.append_event("status", {"status": "Generating response..." if _round == 0 else "Composing response..."})
             t_stream = time.monotonic()
-            async for chunk in _stream_with_retry(messages, model, tools, think):
+            async for chunk in _stream_with_retry(messages, model, stream_tools, think):
                 if buf.cancel_event.is_set():
                     cancelled = True
                     break