feat(api): add completion request cancellation and mermaid rendering

Add support for cancelling in-progress LLM completion requests via new /v1/completions/cancel endpoint with task tracking. Implement mermaid diagram rendering in the Milkdown editor with a new mermaidPlugin. Update copilotPlugin to properly abort requests with descriptive reasons. Refactor settings panel to handle system theme changes reactively. Add camera capture support for image uploads.

backend/llm.py

@@ -1,6 +1,7 @@
 import os
 import time
 import logging
+import asyncio
 from datetime import datetime
 import ollama
 from dotenv import load_dotenv
@@ -97,6 +98,17 @@ async def call_ollama(
             kwargs["think"] = thinking
 
         response = await client.chat(**kwargs)
+    except asyncio.CancelledError:
+        elapsed_ms = (time.perf_counter() - start) * 1000
+        end_dt = datetime.now()
+        logger.info(
+            "[LLM][%s] call_time [%s --> %s]",
+            tag,
+            start_dt.strftime("%H:%M:%S"),
+            end_dt.strftime("%H:%M:%S"),
+        )
+        logger.warning("[LLM][%s] request cancelled after %.1fms", tag, elapsed_ms)
+        raise
     except Exception:
         elapsed_ms = (time.perf_counter() - start) * 1000
         end_dt = datetime.now()