feat: add resume agent MVP

2026-07-20 14:48:41 +08:00
commit 48599bf55b
65 changed files with 10988 additions and 0 deletions
@@ -0,0 +1,277 @@
+from __future__ import annotations
+
+import json
+from types import SimpleNamespace
+from typing import Any
+
+from app.llm_services import (
+    AnchorExtractionOutput,
+    OpenAICompatibleStructuredClient,
+    OpenAIExperienceExtractor,
+    OpenAIResumeRewriter,
+)
+from app.main import create_app
+from app.settings import Settings, load_settings
+
+
+class FakeCompletions:
+    def __init__(self, responses: list[str | Exception]) -> None:
+        self.responses = list(responses)
+        self.calls: list[dict[str, Any]] = []
+
+    def create(self, **kwargs: Any) -> Any:
+        self.calls.append(kwargs)
+        response = self.responses.pop(0)
+        if isinstance(response, Exception):
+            raise response
+        message = SimpleNamespace(content=response, parsed=None, refusal=None)
+        return SimpleNamespace(choices=[SimpleNamespace(message=message)])
+
+
+class FakeOpenAI:
+    def __init__(self, responses: list[str | Exception]) -> None:
+        self.completions = FakeCompletions(responses)
+        self.chat = SimpleNamespace(completions=self.completions)
+
+
+def llm_settings(**overrides: Any) -> Settings:
+    values: dict[str, Any] = {
+        "llm_provider": "openai",
+        "openai_api_key": "test-key-not-a-secret",
+        "openai_base_url": "https://example.test/v1",
+        "openai_model": "test-model",
+        "openai_timeout_seconds": 12.0,
+        "openai_max_retries": 2,
+        "structured_output_retries": 1,
+        "structured_output_mode": "json_schema",
+        "fallback_to_rules": False,
+    }
+    values.update(overrides)
+    return Settings(**values)
+
+
+def anchor_response() -> str:
+    return json.dumps(
+        {
+            "record_type": "work_experience",
+            "field_updates": {
+                "school": None,
+                "major": None,
+                "degree": None,
+                "company": "星河科技有限公司",
+                "position": "产品经理",
+                "project_name": None,
+                "project_role": None,
+                "start_date": "2022-03",
+                "end_date_or_present": "present",
+            },
+            "evidence_spans": [
+                {"field": "company", "quote": "星河科技有限公司"},
+                {"field": "position", "quote": "产品经理"},
+                {"field": "start_date", "quote": "2022年3月"},
+                {"field": "end_date_or_present", "quote": "至今"},
+            ],
+            "ambiguities": [],
+        },
+        ensure_ascii=False,
+    )
+
+
+def test_anchor_extraction_retries_validates_and_redacts_phone() -> None:
+    fake = FakeOpenAI(["not-json", anchor_response()])
+    completion = OpenAICompatibleStructuredClient(llm_settings(), fake)
+    extractor = OpenAIExperienceExtractor(completion)
+
+    patch = extractor.extract_anchor(
+        "我从2022年3月至今在星河科技有限公司担任产品经理，电话13800138000",
+        "work_experience",
+        ["company", "position", "start_date", "end_date_or_present"],
+    )
+
+    assert patch == {
+        "company": "星河科技有限公司",
+        "position": "产品经理",
+        "start_date": "2022-03",
+        "end_date_or_present": "present",
+    }
+    assert len(fake.completions.calls) == 2
+    call = fake.completions.calls[-1]
+    assert call["model"] == "test-model"
+    assert call["timeout"] == 12.0
+    assert call["response_format"]["type"] == "json_schema"
+    serialized_messages = json.dumps(call["messages"], ensure_ascii=False)
+    assert "13800138000" not in serialized_messages
+    assert "[手机号已脱敏]" in serialized_messages
+
+
+def test_experience_extraction_uses_pydantic_and_exact_evidence() -> None:
+    response = json.dumps(
+        {
+            "title": "后端工程师",
+            "organization": "星河科技",
+            "role": "后端工程师",
+            "highlights": ["优化接口耗时，降低30%"],
+            "metrics": ["30%", "99%"],
+            "confidence": 0.93,
+            "evidence_spans": [
+                {"field": "organization", "quote": "星河科技"},
+                {"field": "role", "quote": "后端工程师"},
+                {"field": "highlights", "quote": "优化接口耗时，降低30%"},
+            ],
+            "ambiguities": [],
+        },
+        ensure_ascii=False,
+    )
+    extractor = OpenAIExperienceExtractor(
+        OpenAICompatibleStructuredClient(llm_settings(), FakeOpenAI([response]))
+    )
+
+    result = extractor.extract("在星河科技担任后端工程师，优化接口耗时，降低30%")
+
+    assert result.organization == "星河科技"
+    assert result.highlights == ["优化接口耗时，降低30%"]
+    assert result.metrics == ["30%"]
+    assert result.confidence == 0.95
+
+
+def test_sdk_boundary_redacts_email_wechat_and_split_phone() -> None:
+    fake = FakeOpenAI([anchor_response()])
+    completion = OpenAICompatibleStructuredClient(llm_settings(), fake)
+    completion.complete(
+        schema=AnchorExtractionOutput,
+        schema_name="resume_anchor_extraction",
+        system_prompt="extract",
+        payload={
+            "user_text": (
+                "手机 138-0013-8000，邮箱 user@example.com，微信号: resume_helper"
+            )
+        },
+    )
+
+    request_text = json.dumps(fake.completions.calls[0]["messages"], ensure_ascii=False)
+    assert "138-0013-8000" not in request_text
+    assert "user@example.com" not in request_text
+    assert "resume_helper" not in request_text
+    assert "[手机号已脱敏]" in request_text
+    assert "[邮箱已脱敏]" in request_text
+    assert "[微信号已脱敏]" in request_text
+
+
+def test_json_object_mode_includes_the_pydantic_schema() -> None:
+    fake = FakeOpenAI([anchor_response()])
+    settings = llm_settings(structured_output_mode="json_object")
+    completion = OpenAICompatibleStructuredClient(settings, fake)
+
+    completion.complete(
+        schema=AnchorExtractionOutput,
+        schema_name="resume_anchor_extraction",
+        system_prompt="提取事实。",
+        payload={"user_text": "在星河科技担任产品经理"},
+    )
+
+    call = fake.completions.calls[0]
+    assert call["response_format"] == {"type": "json_object"}
+    assert "output_json_schema" in call["messages"][1]["content"]
+    assert "只返回" in call["messages"][0]["content"]
+
+
+def test_rewriter_sends_allow_listed_facts_and_rejects_new_numbers() -> None:
+    response = json.dumps(
+        {
+            "items": [
+                {
+                    "source_id": "experience_0",
+                    "bullets": [
+                        {
+                            "text": "优化接口性能，将接口耗时降低30%",
+                            "evidence": ["优化接口耗时，降低30%"],
+                        },
+                        {
+                            "text": "支持100万用户稳定访问",
+                            "evidence": ["优化接口耗时，降低30%"],
+                        },
+                    ],
+                }
+            ]
+        },
+        ensure_ascii=False,
+    )
+    fake = FakeOpenAI([response])
+    rewriter = OpenAIResumeRewriter(
+        OpenAICompatibleStructuredClient(llm_settings(), fake)
+    )
+    profile = {
+        "name": "张三",
+        "phone": "13800138000",
+        "account_phone": "13900139000",
+        "phone_source": "manual",
+        "metadata": {"private_note": "never-send-this"},
+        "job_type": "social",
+        "anchor_type": "work_experience",
+        "anchor": {
+            "company": "星河科技",
+            "position": "后端工程师",
+            "start_date": "2022-01",
+            "end_date_or_present": "present",
+        },
+        "experiences": [
+            {
+                "raw_text": "联系电话13800138000",
+                "title": "后端工程师",
+                "organization": "星河科技",
+                "role": "后端工程师",
+                "highlights": ["优化接口耗时，降低30%"],
+                "metrics": ["30%"],
+                "confidence": 0.9,
+            }
+        ],
+    }
+
+    resume = rewriter.rewrite(profile)
+
+    assert resume["basics"]["masked_phone"] == "138****8000"
+    item = resume["sections"][1]["items"][0]
+    assert item["resume_bullets"] == ["优化接口性能，将接口耗时降低30%"]
+    request_text = json.dumps(fake.completions.calls[0]["messages"], ensure_ascii=False)
+    assert "13800138000" not in request_text
+    assert "13900139000" not in request_text
+    assert "never-send-this" not in request_text
+    assert "张三" not in request_text
+
+
+def test_settings_load_dotenv_and_create_app_wires_openai_defaults(
+    tmp_path, monkeypatch
+) -> None:
+    env_file = tmp_path / ".env"
+    env_file.write_text(
+        "\n".join(
+            [
+                "RESUME_AGENT_LLM_PROVIDER=openai",
+                "OPENAI_API_KEY=dummy-key",
+                "OPENAI_BASE_URL=https://gateway.test",
+                "OPENAI_MODEL=test-model",
+                "RESUME_AGENT_LLM_FALLBACK_TO_RULES=false",
+            ]
+        ),
+        encoding="utf-8",
+    )
+    for name in (
+        "RESUME_AGENT_LLM_PROVIDER",
+        "OPENAI_API_KEY",
+        "OPENAI_BASE_URL",
+        "OPENAI_MODEL",
+        "RESUME_AGENT_LLM_FALLBACK_TO_RULES",
+    ):
+        monkeypatch.delenv(name, raising=False)
+    settings = load_settings(env_file)
+    fake = FakeOpenAI([anchor_response()])
+
+    application = create_app(
+        database_path=tmp_path / "llm.db",
+        settings=settings,
+        openai_client=fake,
+    )
+
+    assert isinstance(application.state.resume_agent.extractor, OpenAIExperienceExtractor)
+    assert settings.openai_base_url == "https://gateway.test"
+    assert "dummy-key" not in repr(settings)