feat(editor): add image insertion with OCR support and size limit handling

Add image button with dropdown menu for uploading local images or inserting from URL.
Integrate VLM-based OCR to extract text context from images and include in AI suggestions.
Implement document size limits to disable AI when exceeding threshold.
Refactor copilot plugin with per-view runtime state and OCR context injection.
Add OCR cache utility for managing image metadata.
Add code splitting configuration for optimized bundle size.

backend/llm.py

@@ -1,4 +1,6 @@
 import os
+import time
+import logging
 import ollama
 from dotenv import load_dotenv
 
@@ -6,27 +8,40 @@ load_dotenv()
 
 OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
 OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
+VLM_MODEL = os.getenv('VLM_MODEL', 'qwen3-vl:30b')
 
 client = ollama.AsyncClient(host=OLLAMA_HOST)
+logger = logging.getLogger("llm")
 
-async def call_ollama(prompt: str) -> dict:
-    """
-    调用 Ollama API 并返回 content 和 thinking。
-    """
-    response = await client.chat(
-        model=OLLAMA_MODEL,
-        messages=[{'role': 'user', 'content': prompt}],
-        stream=False,
-        options={
-            'temperature': 0.7,
-            'repeat_penalty': 1.1,
-        },
-        think='high'
-    )
-    
+VLM_OCR_CONTEXT_PROMPT = """You are an OCR and visual-context extractor for markdown writing assistance.
+
+Your output will be embedded inside an HTML comment as hidden context for a text-completion model.
+
+Requirements:
+- Keep output compact: maximum 120 words.
+- Use plain text only (no markdown code fences).
+- Never output <!-- or -->.
+- Do not invent unreadable text; mark uncertain characters with ?.
+- Preserve original script for recognized text (do not forcibly translate).
+
+Return exactly this format:
+
+TEXT:
+<exact transcription of visible text; use " | " for line breaks; write "(none)" if no readable text>
+
+KEY_DETAILS:
+- <3-5 short factual bullets about relevant objects/layout>
+
+LANGUAGE:
+<dominant language(s) in visible text, e.g. English / Chinese / Mixed>
+
+SUMMARY:
+<one short sentence, <= 20 words>"""
+
+def _extract_message(response) -> tuple[str, str]:
     content = ""
     thinking = ""
-    
+
     if hasattr(response, 'message') and response.message:
         content = response.message.content or ""
         thinking = getattr(response.message, 'thinking', '') or ""
@@ -34,5 +49,92 @@ async def call_ollama(prompt: str) -> dict:
         msg = response.get('message', {})
         content = msg.get('content', '') or ""
         thinking = msg.get('thinking', '') or ""
-    
+
+    return content, thinking
+
+
+async def call_ollama(prompt: str, *, tag: str = "default", temperature: float = 0.7) -> dict:
+    """
+    调用 Ollama API 并返回 content 和 thinking。
+    """
+    start = time.perf_counter()
+    logger.info(
+        "[LLM][%s] request model=%s host=%s prompt_chars=%d temp=%.2f",
+        tag,
+        OLLAMA_MODEL,
+        OLLAMA_HOST,
+        len(prompt),
+        temperature,
+    )
+
+    try:
+        response = await client.chat(
+            model=OLLAMA_MODEL,
+            messages=[{'role': 'user', 'content': prompt}],
+            stream=False,
+            options={
+                'temperature': temperature,
+                'repeat_penalty': 1.1,
+            },
+        )
+    except Exception:
+        elapsed_ms = (time.perf_counter() - start) * 1000
+        logger.exception("[LLM][%s] request failed after %.1fms", tag, elapsed_ms)
+        raise
+
+    content, thinking = _extract_message(response)
+    elapsed_ms = (time.perf_counter() - start) * 1000
+    logger.info(
+        "[LLM][%s] response in %.1fms response_type=%s content_chars=%d thinking_chars=%d",
+        tag,
+        elapsed_ms,
+        type(response).__name__,
+        len(content),
+        len(thinking),
+    )
+
+    if not content.strip():
+        logger.warning("[LLM][%s] empty content returned by model", tag)
+
     return {"content": content, "thinking": thinking}
+
+async def call_vlm_ocr(image_bytes: bytes, language: str = 'auto') -> str:
+    start = time.perf_counter()
+    logger.info(
+        "[VLM][ocr] request model=%s host=%s image_bytes=%d language=%s",
+        VLM_MODEL,
+        OLLAMA_HOST,
+        len(image_bytes),
+        language,
+    )
+
+    try:
+        response = await client.chat(
+            model=VLM_MODEL,
+            messages=[{
+                'role': 'user',
+                'content': VLM_OCR_CONTEXT_PROMPT,
+                'images': [image_bytes]
+            }],
+            stream=False,
+            options={'temperature': 0.3}
+        )
+    except Exception:
+        elapsed_ms = (time.perf_counter() - start) * 1000
+        logger.exception("[VLM][ocr] request failed after %.1fms", elapsed_ms)
+        raise
+
+    content, thinking = _extract_message(response)
+    elapsed_ms = (time.perf_counter() - start) * 1000
+    logger.info(
+        "[VLM][ocr] response in %.1fms response_type=%s content_chars=%d thinking_chars=%d",
+        elapsed_ms,
+        type(response).__name__,
+        len(content),
+        len(thinking),
+    )
+
+    if not content.strip():
+        logger.warning("[VLM][ocr] empty content returned by model")
+
+    return content