perf: remove model-load polling before generation

wait_for_model_loaded() polled /api/ps for up to 180s waiting for the
model to appear as loaded. But Ollama lazy-loads models on the first
/api/chat request, so the poll will never succeed — it just blocks for
the full 180s after every Ollama restart before proceeding.

Removed the wait entirely. Ollama handles on-demand loading correctly.

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

src/fabledassistant/services/generation_task.py

@@ -22,7 +22,7 @@ from fabledassistant.services.generation_buffer import (
     GenerationBuffer,
     GenerationState,
 )
-from fabledassistant.services.llm import ChatChunk, build_context, generate_completion, stream_chat, stream_chat_with_tools, summarize_history_for_context, wait_for_model_loaded
+from fabledassistant.services.llm import ChatChunk, build_context, generate_completion, stream_chat, stream_chat_with_tools, summarize_history_for_context
 from fabledassistant.services.chat import update_conversation_title
 from fabledassistant.services.logging import log_generation
 from fabledassistant.services.tools import get_tools_for_user, execute_tool
@@ -175,8 +175,10 @@ async def run_generation(
         buf.append_event("status", {"status": "Summarizing conversation history..."})
         history_to_use, history_summary = await summarize_history_for_context(history, model)
 
-    # Phase 3: Build context and wait for model in parallel.
-    model_load_task = asyncio.create_task(wait_for_model_loaded(model, timeout=180.0))
+    # Phase 3: Build context.
+    # Note: Ollama lazy-loads models on the first /api/chat request, so polling
+    # /api/ps for model readiness only causes delay. We proceed immediately and
+    # let Ollama handle loading on demand.
 
     # Fetch voice_speech_style from user settings when voice_mode is active.
     voice_speech_style = "conversational"
@@ -184,7 +186,7 @@ async def run_generation(
         from fabledassistant.services.settings import get_setting
         voice_speech_style = await get_setting(user_id, "voice_speech_style", "conversational")
 
-    context_task = asyncio.create_task(build_context(
+    messages, context_meta = await build_context(
         user_id, history_to_use, context_note_id, user_content,
         history_summary=history_summary,
         include_note_ids=include_note_ids,
@@ -195,21 +197,11 @@ async def run_generation(
         conv_id=conv_id,
         voice_mode=voice_mode,
         voice_speech_style=voice_speech_style,
-    ))
-
-    messages, context_meta = await context_task
+    )
 
     # Emit context event
     buf.append_event("context", {"context": context_meta})
 
-    # Wait for main model to be loaded before starting any generation.
-    # If it's already loaded (common case), this returns immediately.
-    if not model_load_task.done():
-        buf.append_event("status", {"status": "Loading model..."})
-    loaded = await model_load_task
-    if not loaded:
-        logger.warning("Model %s did not load within 180s — proceeding anyway", model)
-
     t_start = time.monotonic()
     timing: dict = {
         "think": think,