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/main.py

@@ -3,9 +3,18 @@ from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse, JSONResponse
 from pydantic import BaseModel
 import json
+import base64
+import uuid
+import logging
 
 from prompt import build_prompt
-from llm import call_ollama
+from llm import call_ollama, call_vlm_ocr
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s %(levelname)s %(name)s - %(message)s",
+)
+logger = logging.getLogger("api")
 
 app = FastAPI()
 
@@ -22,24 +31,100 @@ class CompletionRequest(BaseModel):
     suffix: str
     languageId: str = 'markdown'
 
+class OCRRequest(BaseModel):
+    image: str
+    filename: str = "image.jpg"
+    language: str = 'auto'
+
+
+def _preview(text: str, limit: int = 80) -> str:
+    value = (text or "").replace("\n", "\\n")
+    if len(value) <= limit:
+        return value
+    return value[:limit] + "..."
+
+
+def _build_force_non_empty_prompt(base_prompt: str) -> str:
+    return (
+        base_prompt
+        + "\n\nStrict override for this request:\n"
+        + "- Output must be non-empty.\n"
+        + "- If you would otherwise output empty, output a single space.\n"
+        + "- Keep it short and do not repeat SUFFIX.\n"
+    )
+
+
 @app.post("/v1/completions")
 async def create_completion(request: CompletionRequest):
+    request_id = str(uuid.uuid4())[:8]
     try:
-        prompt = build_prompt(request.prefix, request.suffix)
-        result = await call_ollama(prompt)
-        
-        content = result["content"]
-        
+        logger.info(
+            "[%s] /v1/completions prefix_chars=%d suffix_chars=%d lang=%s prefix_tail='%s' suffix_head='%s'",
+            request_id,
+            len(request.prefix or ""),
+            len(request.suffix or ""),
+            request.languageId,
+            _preview((request.prefix or "")[-120:]),
+            _preview((request.suffix or "")[:120]),
+        )
+        prompt = build_prompt(request.prefix, request.suffix, request.languageId)
+        result = await call_ollama(prompt, tag=f"{request_id}-primary", temperature=0.7)
+
+        content = result["content"] or ""
+        source = "primary"
+        if not content.strip():
+            logger.warning("[%s] primary returned empty content, starting retry", request_id)
+            retry_prompt = _build_force_non_empty_prompt(prompt)
+            retry_result = await call_ollama(retry_prompt, tag=f"{request_id}-retry1", temperature=0.4)
+            content = retry_result["content"] or ""
+            source = "retry1"
+
+        if not content.strip():
+            content = " "
+            source = "fallback-space"
+            logger.warning("[%s] retry still empty, forcing single-space fallback", request_id)
+
+        logger.info(
+            "[%s] completion resolved source=%s content_chars=%d content_preview='%s'",
+            request_id,
+            source,
+            len(content),
+            _preview(content, 120),
+        )
+
         async def generate():
-            if content:
-                yield f"data: {json.dumps({'content': content})}\n\n"
+            yield f"data: {json.dumps({'content': content})}\n\n"
             yield f"data: {json.dumps({'done': True})}\n\n"
-        
+
         return StreamingResponse(generate(), media_type="text/event-stream")
-        
+
     except Exception as e:
-        import traceback
-        traceback.print_exc()
+        logger.exception("[%s] /v1/completions failed: %s", request_id, e)
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+@app.post("/v1/ocr")
+async def ocr_image(request: OCRRequest):
+    request_id = str(uuid.uuid4())[:8]
+    try:
+        logger.info(
+            "[%s] /v1/ocr filename=%s language=%s image_base64_chars=%d",
+            request_id,
+            request.filename,
+            request.language,
+            len(request.image or ""),
+        )
+        image_bytes = base64.b64decode(request.image)
+        logger.info("[%s] /v1/ocr decoded image_bytes=%d", request_id, len(image_bytes))
+        result = await call_vlm_ocr(image_bytes, request.language)
+        logger.info(
+            "[%s] /v1/ocr success text_chars=%d text_preview='%s'",
+            request_id,
+            len(result or ""),
+            _preview(result or "", 120),
+        )
+        return {"text": result, "filename": request.filename}
+    except Exception as e:
+        logger.exception("[%s] /v1/ocr failed: %s", request_id, e)
         return JSONResponse(content={"error": str(e)}, status_code=500)
 
 if __name__ == "__main__":