refactor(editor): migrate to ProseMirror Mark-based ghost text system

- Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system
- Add AI toggle button with enable/disable functionality
- Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions
- Fix cursor position offset in prompt.py by moving first suffix char to prefix
- Improve API error handling with abort signal support and debug logging
- Update model configuration from gpt-oss:120b to gpt-oss:20b
- Add button tooltips and improve editor styling
- Remove deprecated inlineSuggestionPlugin.ts
- Update README with new architecture diagram and feature documentation

backend/.env

@@ -1,3 +1,3 @@
 OPENAI_API_KEY=ollama
 OLLAMA_HOST=http://192.168.0.120:11434
-OLLAMA_MODEL=gpt-oss:120b
+OLLAMA_MODEL=gpt-oss:20b

backend/llm.py

@@ -3,8 +3,8 @@ import json
 import ollama
 from typing import AsyncGenerator
 
-OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
-OLLAMA_HOST = os.getenv('OLLAMA_BASE_URL', 'http://192.168.0.120:11434')
+OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
+OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
 
 # 移除 /v1/ 后缀（如果有的话），因为 Ollama Python 包使用原生 API
 if OLLAMA_HOST.endswith('/v1/'):

backend/main.py

@@ -71,7 +71,7 @@ async def create_completion(request: CompletionRequest):
     print(f"[Backend] POST /v1/completions called")
     print(f"[Backend] Received request - prefix length: {len(request.prefix)}, suffix length: {len(request.suffix)}")
     
-    OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:120b')
+    OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
     OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
     
     print(f"[LLM] Using host: {OLLAMA_HOST}, model: {OLLAMA_MODEL}")
@@ -123,8 +123,9 @@ async def create_completion(request: CompletionRequest):
         # 返回完整内容
         async def generate():
             if content:
+                print(f"[LLM] Yielding full content: {repr(content)}")
                 yield f"data: {json.dumps({'content': content})}\n\n"
-            yield f"data: {json.dumps({'done': true})}\n\n"
+            yield f"data: {json.dumps({'done': True})}\n\n"
         
         return StreamingResponse(generate(), media_type="text/event-stream")
         

backend/prompt.py

@@ -8,6 +8,12 @@ def build_prompt(prefix: str, suffix: str) -> str:
     """
     MAX_CONTEXT_LINES = 30
     
+    # 修正：把suffix的第一个字符移到prefix末尾（解决光标位置偏差）
+    if suffix:
+        first_char = suffix[0]
+        prefix = prefix + first_char
+        suffix = suffix[1:]
+    
     prefix_lines = prefix.split('\n')
     suffix_lines = suffix.split('\n') if suffix else []
     
@@ -25,6 +31,7 @@ RULES:
 - Match existing style, tone, and terminology
 - Maintain logical flow
 - Write only the continuation, nothing else
+- IMPORTANT: Start continuation directly from ⟨CURSOR⟩ position
 
 TEXT:
 {recent_prefix}⟨CURSOR⟩{recent_suffix}