Refactor settings store to rename proModel to proThinking and update related logic; enhance CSS for energy efficiency and reduced motion preferences; improve i18n translations for better clarity and consistency; modify proBlock utility functions for clearer instruction handling; streamline Vite configuration by removing unnecessary Univer.js dependencies.

backend/tests/test_main_endpoints.py

@@ -17,6 +17,7 @@ if "tts_asr" not in sys.modules:
     sys.modules["tts_asr"] = fake_tts_asr
 
 import main  # type: ignore
+import pro_completions  # type: ignore
 
 API_KEY = main.API_KEY
 HEADERS = {"X-API-Key": API_KEY}
@@ -25,8 +26,10 @@ HEADERS = {"X-API-Key": API_KEY}
 @pytest.fixture(autouse=True)
 def _clear_active_completions():
     main.ACTIVE_COMPLETIONS.clear()
+    pro_completions.PRO_STATES.clear()
     yield
     main.ACTIVE_COMPLETIONS.clear()
+    pro_completions.PRO_STATES.clear()
 
 
 class DummyRequest:
@@ -76,6 +79,33 @@ def test_sanitize_markdown_normalize_crlf():
     assert "\r" not in result
 
 
+def test_sanitize_inline_completion_strips_prefill():
+    assert main.sanitize_inline_completion_content(
+        "系统非常适合写作",
+        prefill="系统",
+    ) == "非常适合写作"
+
+
+def test_sanitize_inline_completion_extracts_fim_middle():
+    assert main.sanitize_inline_completion_content(
+        "<|fim_middle|>系统非常适合写作<|end|>",
+        prefill="系统",
+    ) == "非常适合写作"
+
+
+def test_sanitize_inline_completion_extracts_polluted_chat_output():
+    polluted = (
+        "on new line? Prefix ends with newline already. The suffix starts with no newline. "
+        "We need to consider if output should end with newline? The suffix starts with no newline. "
+        "So we output: \"让我们一起探索 AI 的无限可能。\""
+        "<|end|><|start|>assistant<|channel|>final|fim_middle|>系统让我们一起探索 AI 的无限可能。"
+    )
+    assert main.sanitize_inline_completion_content(
+        polluted,
+        prefill="系统",
+    ) == "让我们一起探索 AI 的无限可能。"
+
+
 def test_get_client_ip_from_host():
     req = DummyRequest(host="1.2.3.4", headers={})
     assert main.get_client_ip(req) == "1.2.3.4"
@@ -102,7 +132,10 @@ def test_post_completions_wrong_api_key_returns_401():
 
 
 def test_post_completions_privacy_mode(monkeypatch):
+    captured = {}
+
     async def fake_call(*args, **kwargs):
+        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"))
@@ -116,39 +149,58 @@ def test_post_completions_privacy_mode(monkeypatch):
     assert resp.status_code == 200
     data = resp.json()
     assert data.get("content") == "done"
+# enable_thinking removed in OpenAI-compatible rewrite
+    assert captured["kwargs"]["thinking"] == "low"
 
 
-def test_post_pro_stream_returns_sse(monkeypatch):
-    captured = {}
-
-    async def fake_stream(*args, **kwargs):
-        captured["kwargs"] = kwargs
-        yield "深度"
-        yield "回答"
-
-    monkeypatch.setattr(main, "stream_ollama", fake_stream)
-    monkeypatch.setattr(main, "build_completion_prompts", lambda *a, **k: ("sys", "user"))
-    monkeypatch.setattr(main, "prepare_prompt_context", lambda *a, **k: ("p", "s"))
-
+def test_old_post_pro_stream_returns_404():
     client = TestClient(main.app)
-    with client.stream("POST", "/v1/pro/completions/stream", headers=HEADERS, json={
+    resp = client.post("/v1/pro/completions/stream", headers=HEADERS, json={
         "prefix": "hello",
         "suffix": "",
         "languageId": "markdown",
         "model_thinking": "high",
         "privacy_mode": True,
-        "model": "pro-model",
-        "temperature": 0.95,
+    })
+    assert resp.status_code == 404
+
+
+def test_post_pro_completion_returns_sse_and_status(monkeypatch):
+    captured = {}
+
+    async def fake_stream_events(*args, **kwargs):
+        captured["kwargs"] = kwargs
+        yield "thinking", ""
+        yield "content", "深度"
+        yield "content", "回答"
+
+    monkeypatch.setattr(pro_completions, "stream_ollama_events", fake_stream_events)
+    client = TestClient(main.app)
+    with client.stream("POST", "/v1/pro/completions", headers=HEADERS, json={
+        "prefix": "hello",
+        "suffix": "",
+        "languageId": "markdown",
+        "instruction": "expand",
+        "pro_thinking": "high",
+        "privacy_mode": True,
     }) as resp:
         assert resp.status_code == 200
         body = "".join(resp.iter_text())
 
+    assert "event: queued" in body
+    assert "event: started" in body
+    assert "event: thinking" in body
     assert "event: chunk" in body
     assert "event: done" in body
     assert "深度" in body
     assert "回答" in body
-    assert captured["kwargs"]["model"] == "pro-model"
     assert captured["kwargs"]["use_pro_model"] is True
+    assert captured["kwargs"]["thinking"] == "high"
+
+    request_id = next(iter(pro_completions.PRO_STATES))
+    status_resp = client.get(f"/v1/pro/completions/status/{request_id}", headers=HEADERS)
+    assert status_resp.status_code == 200
+    assert status_resp.json()["status"] == "done"
     assert main.ACTIVE_COMPLETIONS == {}