Phase 10: CalDAV full lifecycle, update_note, dashboard inline streaming, keyboard shortcuts

Backend:
- caldav.py: Full event lifecycle — update_event, delete_event; VTODO suite —
  create_todo, list_todos, complete_todo, delete_todo; list_calendars; timezone
  support via ZoneInfo; reminders via VALARM; attendees; multi-calendar search
  (_get_all_calendars scans all calendars when no specific one is configured)
- tools.py: New update_note tool (find by title + replace/append modes),
  7 new CalDAV tool definitions, corresponding execute_tool cases
- llm.py: Update system prompt — add update_note guidance, full CalDAV action list
- intent.py: Confidence scoring (high/medium/low) + should_execute property;
  conversation history support for anaphora resolution; routing rules for
  update/delete events, todos, update_note vs create_note disambiguation,
  time-period → list_events (not search_events), reminder_minutes conversion
- generation_task.py: Parallel fetch of tools + intent_model setting; dedicated
  intent model (OLLAMA_INTENT_MODEL env var or per-user intent_model setting)
- config.py: Add OLLAMA_INTENT_MODEL env var

Frontend:
- HomeView.vue: Inline streaming response (no navigation); quick action chips;
  isConversational computed — prominent "Continue this conversation" CTA when
  no tool calls; auto-focus chat input on mount via chatInputRef
- DashboardChatInput.vue: defineExpose({ focus }) for external focus control
- ChatView.vue: Escape key handler — close picker → close sidebar → clear
  textarea → navigate home; onUnmounted cleanup
- App.vue: Global ? key shortcut toggles keyboard shortcuts overlay; shared
  state via useShortcuts composable; Transition animation
- AppHeader.vue: ? button for shortcuts overlay discoverability
- useShortcuts.ts (new): Shared showShortcuts ref + open/close/toggle helpers
- ToolCallCard.vue: note_updated, event_updated, event_deleted, calendars,
  todo, todos, todo_completed, todo_deleted label cases + render blocks
- SettingsView.vue: Intent model field + caldav_timezone setting

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

src/fabledassistant/services/generation_task.py

@@ -4,6 +4,7 @@ Streams from Ollama into a GenerationBuffer, periodically flushing to DB.
 Runs independently of any HTTP connection.
 """
 
+import asyncio
 import json
 import logging
 import re
@@ -11,12 +12,14 @@ import time
 
 from sqlalchemy import update
 
+from fabledassistant.config import Config
 from fabledassistant.models import async_session
 from fabledassistant.models.conversation import Message
 from fabledassistant.services.generation_buffer import GenerationBuffer, GenerationState
 from fabledassistant.services.llm import ChatChunk, generate_completion, stream_chat, stream_chat_with_tools
 from fabledassistant.services.chat import update_conversation_title
 from fabledassistant.services.intent import classify_intent
+from fabledassistant.services.settings import get_setting
 from fabledassistant.services.tools import get_tools_for_user, execute_tool
 
 logger = logging.getLogger(__name__)
@@ -92,9 +95,16 @@ async def run_generation(
     last_flush = time.monotonic()
     all_tool_calls: list[dict] = []
 
-    # Resolve tools based on user's configured integrations
-    tools = await get_tools_for_user(user_id)
-    logger.info("Starting generation for conv %d: model=%s, tools=%d", conv_id, model, len(tools))
+    # Resolve tools and intent model in parallel
+    tools, intent_model_setting = await asyncio.gather(
+        get_tools_for_user(user_id),
+        get_setting(user_id, "intent_model", ""),
+    )
+    intent_model = intent_model_setting or Config.OLLAMA_INTENT_MODEL or model
+    logger.info(
+        "Starting generation for conv %d: model=%s, intent_model=%s, tools=%d",
+        conv_id, model, intent_model, len(tools),
+    )
 
     try:
         cancelled = False
@@ -105,9 +115,24 @@ async def run_generation(
 
             # Intent routing — first round only
             if _round == 0 and tools:
-                intent = await classify_intent(user_content, tools, model)
-                if intent.tool_name:
-                    logger.info("Intent router detected tool: %s(%s)", intent.tool_name, json.dumps(intent.arguments)[:200])
+                # Pass last 3 user/assistant pairs (6 messages) for anaphora resolution.
+                # messages = [system, *history, current_user] — exclude system and current user.
+                intent_history = [
+                    m for m in messages[1:-1]
+                    if m.get("role") in ("user", "assistant") and m.get("content")
+                ][-6:]
+                intent = await classify_intent(user_content, tools, intent_model, history=intent_history)
+                if intent.should_execute:
+                    logger.info(
+                        "Intent router detected tool (confidence=%s): %s(%s)",
+                        intent.confidence, intent.tool_name, json.dumps(intent.arguments)[:200],
+                    )
+                elif intent.tool_name:
+                    logger.info(
+                        "Intent router low confidence (%s) for tool=%s — falling through to streaming",
+                        intent.confidence, intent.tool_name,
+                    )
+                if intent.should_execute:
                     result = await execute_tool(user_id, intent.tool_name, intent.arguments)
                     logger.info("Intent-routed tool %s result: success=%s", intent.tool_name, result.get("success"))