feat: 完成数据处理接口与前端接入

backend/tests/test_data_process_generation.py

@@ -0,0 +1,102 @@
+from __future__ import annotations
+
+import json
+
+import httpx
+
+from app.modules.data_process.generation import chat_completions_url, generate_model_records
+
+
+def test_chat_completions_url_accepts_host_base_and_complete_url() -> None:
+    assert chat_completions_url("www.caoxiaozhu.com") == (
+        "https://www.caoxiaozhu.com/v1/chat/completions"
+    )
+    assert chat_completions_url("https://model.example/v1") == (
+        "https://model.example/v1/chat/completions"
+    )
+    complete = "https://model.example/openai/v1/chat/completions"
+    assert chat_completions_url(complete) == complete
+
+
+def test_generate_model_records_uses_prompt_auth_and_stable_split() -> None:
+    requests: list[httpx.Request] = []
+    progress_updates: list[tuple[int, int]] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        requests.append(request)
+        payload = json.loads(request.content)
+        assert payload["model"] == "qwen-plus"
+        assert payload["response_format"] == {"type": "json_object"}
+        assert "客户反馈页面加载慢" in payload["messages"][1]["content"]
+        return httpx.Response(
+            200,
+            json={
+                "choices": [
+                    {
+                        "message": {
+                            "content": json.dumps(
+                                {
+                                    "items": [
+                                        {
+                                            "instruction": "请生成简洁客服回复",
+                                            "input": "客户反馈页面加载慢",
+                                            "output": "已收到反馈，我们正在排查。",
+                                        }
+                                    ]
+                                },
+                                ensure_ascii=False,
+                            )
+                        }
+                    }
+                ]
+            },
+        )
+
+    client = httpx.Client(transport=httpx.MockTransport(handler))
+    records = generate_model_records(
+        [{"id": "preview-1", "edited_content": "客户反馈页面加载慢"}],
+        model={
+            "name": "Qwen",
+            "online_model_name": "qwen-plus",
+            "api_url": "model.example",
+            "api_key": "test-secret",
+        },
+        config={
+            "generation_prompt": "请处理：{{ content }}",
+            "json_mode": True,
+            "temperature": 0.2,
+            "max_tokens": 512,
+        },
+        task_id="task-1",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+        on_progress=lambda processed, total: progress_updates.append((processed, total)),
+    )
+
+    assert len(records) == 1
+    assert records[0]["status"] == "valid"
+    assert records[0]["split"] == "train"
+    assert requests[0].headers["Authorization"] == "Bearer test-secret"
+    assert progress_updates == [(1, 1)]
+
+
+def test_generate_model_records_keeps_partial_failure_for_manual_repair() -> None:
+    client = httpx.Client(
+        transport=httpx.MockTransport(
+            lambda _: httpx.Response(200, json={"choices": [{"message": {"content": "not-json"}}]})
+        )
+    )
+    records = generate_model_records(
+        [{"id": "preview-1", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 1},
+        task_id="task-1",
+        split={"train": 80, "validation": 10, "test": 10},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert len(records) == 1
+    assert records[0]["status"] == "invalid"
+    assert records[0]["error"]