Stabilize pro editing without heavy office runtime

The workspace now carries the pro editing flow, streaming completion path, and lighter Office preview state as one checkpoint so the remote has the current runnable project shape.

Constraint: Preserve the current workspace as a single reviewable project commit while excluding local agent state and verification artifacts. Removed stale Univer runtime dependencies from the lockfile so installs match package.json.

Rejected: Commit runtime screenshots, .omx state, and coverage files | they are local artifacts rather than source state.

Confidence: medium

Scope-risk: broad

Directive: Keep package.json and package-lock.json synchronized when changing frontend dependencies.

Tested: npm run build; C:\Users\ydy\.conda\envs\llmwebsite\python.exe -m pytest backend/tests/test_main_endpoints.py backend/tests/test_main_cancel.py backend/tests/test_llm.py backend/tests/test_llm_extended.py -v -o addopts= (44 passed).

Not-tested: Full pytest with repository coverage addopts currently reports 0% coverage because pytest-cov watches backend.* module names while tests import top-level backend modules.

Co-authored-by: OmX <omx@oh-my-codex.dev>

backend/tests/test_main_endpoints.py

@@ -1,6 +1,7 @@
 import os
 import sys
 import base64
+import types
 import pytest
 from unittest.mock import MagicMock
 from fastapi.testclient import TestClient
@@ -10,6 +11,11 @@ BACKEND_DIR = os.path.abspath(os.path.join(CURRENT_DIR, ".."))
 if BACKEND_DIR not in sys.path:
     sys.path.insert(0, BACKEND_DIR)
 
+if "tts_asr" not in sys.modules:
+    fake_tts_asr = types.ModuleType("tts_asr")
+    fake_tts_asr.register_tts_asr_routes = lambda app: None
+    sys.modules["tts_asr"] = fake_tts_asr
+
 import main  # type: ignore
 
 API_KEY = main.API_KEY
@@ -112,6 +118,40 @@ def test_post_completions_privacy_mode(monkeypatch):
     assert data.get("content") == "done"
 
 
+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"))
+
+    client = TestClient(main.app)
+    with client.stream("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,
+    }) as resp:
+        assert resp.status_code == 200
+        body = "".join(resp.iter_text())
+
+    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 main.ACTIVE_COMPLETIONS == {}
+
+
 def test_post_ocr_mocked(monkeypatch):
     async def fake_ocr(*args, **kwargs):
         return "OCR result text"