Enhance LLM functionality with PRO mode support and improved prompt handling

- Added support for PRO mode in LLM with specific instruction handling and context awareness.
- Updated prompt building functions to include prefill options for better context management.
- Introduced new inline examples for PRO mode in JSON format.
- Enhanced system prompts to reflect PRO mode capabilities and rules.
- Modified API endpoints to accommodate new parameters and ensure backward compatibility.
- Improved test cases to validate new functionality and ensure comprehensive coverage.

backend/tests/test_llm.py

@@ -128,9 +128,9 @@ def test_build_chat_stream_payload_with_thinking():
 def test_call_ollama_non_streaming(monkeypatch):
     captured = {}
 
-    async def fake_post(url, json=None):
-        captured["url"] = url
-        captured["json"] = json
+    async def fake_post(*args, **kwargs):
+        captured["url"] = args[1] if len(args) > 1 else kwargs.get("url", "")
+        captured["json"] = kwargs.get("json")
 
         class FakeResp:
             def raise_for_status(self): pass
@@ -138,7 +138,7 @@ def test_call_ollama_non_streaming(monkeypatch):
 
         return FakeResp()
 
-    async def fake_client(*args, **kwargs):
+    def fake_client(*args, **kwargs):
         class Ctx:
             async def __aenter__(self2): return self2
             async def __aexit__(*a): pass
@@ -168,7 +168,8 @@ def test_stream_ollama_text_deltas(monkeypatch):
         ])
 
         class LineIterator:
-            async def __anext__(self):
+            def __aiter__(self2): return self2
+            async def __anext__(self2):
                 try:
                     return next(lines_iter)
                 except StopIteration:
@@ -177,8 +178,8 @@ def test_stream_ollama_text_deltas(monkeypatch):
         class Response:
             def __init__(self2): self2._lines = LineIterator()
 
-            async def raise_for_status(self2): pass
-            async def aiter_lines(self2): return self2._lines
+            def raise_for_status(self2): pass
+            def aiter_lines(self2): return self2._lines
 
         class StreamCtx:
             async def __aenter__(self2): return Response()
@@ -186,10 +187,12 @@ def test_stream_ollama_text_deltas(monkeypatch):
 
         class Client:
             stream = lambda self2, *args, **kw: StreamCtx()
+            async def __aenter__(self2): return self2
+            async def __aexit__(*a): pass
 
         return Client()
 
-    async def fake_client(*args, **kwargs):
+    def fake_client(*args, **kwargs):
         captured["called"] = True
         return make_lines()
 
@@ -217,7 +220,8 @@ def test_stream_ollama_events_thinking_and_content(monkeypatch):
         ])
 
         class LineIterator:
-            async def __anext__(self):
+            def __aiter__(self2): return self2
+            async def __anext__(self2):
                 try:
                     return next(lines_iter)
                 except StopIteration:
@@ -226,8 +230,8 @@ def test_stream_ollama_events_thinking_and_content(monkeypatch):
         class Response:
             def __init__(self2): self2._lines = LineIterator()
 
-            async def raise_for_status(self2): pass
-            async def aiter_lines(self2): return self2._lines
+            def raise_for_status(self2): pass
+            def aiter_lines(self2): return self2._lines
 
         class StreamCtx:
             async def __aenter__(self2): return Response()
@@ -235,10 +239,12 @@ def test_stream_ollama_events_thinking_and_content(monkeypatch):
 
         class Client:
             stream = lambda self2, *args, **kw: StreamCtx()
+            async def __aenter__(self2): return self2
+            async def __aexit__(*a): pass
 
         return Client()
 
-    async def fake_client(*args, **kwargs):
+    def fake_client(*args, **kwargs):
         captured["called"] = True
         return make_lines()
 
@@ -260,9 +266,9 @@ def test_stream_ollama_events_thinking_and_content(monkeypatch):
 def test_call_vlm_ocr(monkeypatch):
     captured = {}
 
-    async def fake_post(url, json=None):
-        captured["url"] = url
-        captured["json"] = json
+    async def fake_post(*args, **kwargs):
+        captured["url"] = args[1] if len(args) > 1 else kwargs.get("url", "")
+        captured["json"] = kwargs.get("json")
 
         class FakeResp:
             def raise_for_status(self): pass
@@ -270,7 +276,7 @@ def test_call_vlm_ocr(monkeypatch):
 
         return FakeResp()
 
-    async def fake_client(*args, **kwargs):
+    def fake_client(*args, **kwargs):
         class Ctx:
             async def __aenter__(self2): return self2
             async def __aexit__(*a): pass

backend/tests/test_main_endpoints.py

@@ -138,7 +138,7 @@ def test_post_completions_privacy_mode(monkeypatch):
         captured["kwargs"] = kwargs
         return {"content": "done", "think": ""}
     monkeypatch.setattr(main, "call_ollama", fake_call)
-    monkeypatch.setattr(main, "build_completion_prompts", lambda *a, **k: ("sys", "user"))
+    monkeypatch.setattr(main, "build_completion_prompts", lambda *a, **k: ("sys", "user", ""))
     monkeypatch.setattr(main, "prepare_prompt_context", lambda *a, **k: ("p", "s"))
 
     client = TestClient(main.app)

backend/tests/test_pro_completions.py

@@ -56,19 +56,22 @@ def test_pro_status_missing_returns_404():
     assert response.status_code == 404
 
 
-def test_pro_prompt_uses_simple_chat_instruction():
+def test_pro_prompt_uses_pro_specific_instruction():
     system_prompt, user_prompt = pro_completions._build_pro_prompts(
         prefix="欢迎使用 LLM-IN-TEXT\n\n即时可用的 LLM 系统",
         suffix="",
         language_id="markdown",
         instruction="",
+        pro_thinking="high",
     )
     combined = f"{system_prompt}\n{user_prompt}".lower()
-    assert "pro block" not in combined
-    assert "replacement" not in combined
-    assert "final answer" not in combined
-    assert "markdown before cursor" in combined
-    assert "markdown after cursor" in combined
+    assert "[pro] model for llm-in-text" in combined
+    assert "pro_mode: true" in combined
+    assert "pro_thinking_level: high" in combined
+    assert "long paragraphs or section-level output are allowed" in combined
+    assert "highest priority" in combined
+    assert "never copy tags to output" in combined
+    assert "write only the markdown that belongs at the cursor" not in combined
     assert "continue the markdown naturally" in combined