feat: builder 简历生成 + 轻度优化 + 简历导入交付副本

自内部仓库剥离深度优化与 RAG 知识库后的交付版本： - Builder 对话式简历生成（FSM + 意图路由 LLM 兜底增强） - 条目级轻度优化：事实覆盖门禁 + STAR/bullet 修复链，功能/简介/成果与技术栈同级保护 - 简历导入：DOCX/PDF 解析、结构归一、手机号脱敏 - PostgreSQL 运行时 + Alembic 迁移链 Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-05 11:08:30 +08:00
commit ae2d9b128d
191 changed files with 27719 additions and 0 deletions
@@ -0,0 +1,118 @@
+"""Chat intent classifier tests: rule fallback, LLM client, fallback composition."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from app.chat_intents import CHAT_INTENT_REGISTRY_VERSION, ChatIntent, ChatTurnClassification
+from app.chat_intent_classifier import (
+    ChatIntentClassifier,
+    FallbackChatIntentClassifier,
+    LLMChatIntentClassifier,
+    RuleBasedChatIntentClassifier,
+    build_chat_intent_classifier,
+    build_chat_state_summary,
+)
+from app.settings import Settings
+
+PROFILE = {
+    "job_type": "campus",
+    "target_position": "后端工程师",
+    "resume_content": {
+        "sections": [
+            {"kind": "project_experience", "items": [{"project_name": "AI Career Copilot"}]},
+        ]
+    },
+}
+SUMMARY = build_chat_state_summary(PROFILE, {"draft": {"section": "education"}})
+
+
+def classify_rule(message: str) -> ChatTurnClassification:
+    return RuleBasedChatIntentClassifier().classify(message, state_summary=SUMMARY)
+
+
+def test_rule_classifier_implements_protocol() -> None:
+    assert isinstance(RuleBasedChatIntentClassifier(), ChatIntentClassifier)
+
+
+def test_rule_classifier_maps_legacy_keyword_signals() -> None:
+    assert classify_rule("没有").intent is ChatIntent.NO_INFO
+    revise = classify_rule("保留原文，不要用这版优化稿")
+    assert revise.intent is ChatIntent.REVISE_PROPOSAL
+    assert revise.revision_instruction
+    assert classify_rule("把学校名字改成东莞城市学院").intent is ChatIntent.EDIT_IDENTITY
+    new_entry = classify_rule("新增一段教育经历")
+    assert new_entry.intent is ChatIntent.NEW_ENTRY
+    assert new_entry.target_section == "education"
+
+
+def test_rule_classifier_routes_edit_question_chitchat_and_facts() -> None:
+    edit = classify_rule("修改一下我之前写的那个 AI Career Copilot 项目经历")
+    assert edit.intent is ChatIntent.EDIT_ENTRY
+    assert edit.target_entry_hint == "AI Career Copilot"
+    question = classify_rule("这段经历怎么写比较好？")
+    assert question.intent is ChatIntent.ASK_QUESTION
+    assert question.user_question
+    assert classify_rule("好的，谢谢").intent is ChatIntent.CHITCHAT
+    facts = classify_rule("负责后端接口开发，使用 Python 和 FastAPI")
+    assert facts.intent is ChatIntent.PROVIDE_FACTS
+    assert facts.facts and facts.facts[0].text
+    assert facts.confidence < 0.5
+
+
+def test_state_summary_compacts_profile_and_draft() -> None:
+    assert SUMMARY["job_type"] == "campus"
+    assert SUMMARY["target_position"] == "后端工程师"
+    assert SUMMARY["confirmed_entries"] == [
+        {"section": "project_experience", "label": "AI Career Copilot"}
+    ]
+    assert SUMMARY["draft_section"] == "education"
+    assert build_chat_state_summary(PROFILE)["draft_section"] is None
+
+
+class _StubClient:
+    def __init__(self, result: Any) -> None:
+        self.result = result
+        self.calls: list[dict[str, Any]] = []
+
+    def complete(self, **kwargs: Any) -> Any:
+        self.calls.append(kwargs)
+        return self.result
+
+
+def test_llm_classifier_uses_registry_prompt_and_schema() -> None:
+    expected = ChatTurnClassification(intent="ask_question", user_question="怎么写？")
+    client = _StubClient(expected)
+    result = LLMChatIntentClassifier(client).classify("怎么写？", state_summary=SUMMARY)
+
+    assert result is expected
+    call = client.calls[0]
+    assert call["schema"] is ChatTurnClassification
+    assert call["schema_name"] == "chat_intent_classification"
+    assert call["payload"]["message"] == "怎么写？"
+    assert call["payload"]["state_summary"] is SUMMARY
+    assert call["payload"]["registry_version"] == CHAT_INTENT_REGISTRY_VERSION
+    prompt = call["system_prompt"]
+    assert CHAT_INTENT_REGISTRY_VERSION in prompt
+    for intent in ChatIntent:
+        assert intent.value in prompt
+    assert "保留原文" in prompt  # few-shot examples reach the prompt
+
+
+class _FailingClassifier:
+    def classify(self, message: str, *, state_summary: dict[str, Any]) -> ChatTurnClassification:
+        raise RuntimeError("boom")
+
+
+def test_fallback_classifier_degrades_to_rules_on_llm_failure() -> None:
+    classifier = FallbackChatIntentClassifier(_FailingClassifier(), RuleBasedChatIntentClassifier())
+    result = classifier.classify("没有", state_summary=SUMMARY)
+    assert result.intent is ChatIntent.NO_INFO
+
+
+def test_factory_returns_rules_without_openai_and_fallback_with_openai() -> None:
+    rule_only = build_chat_intent_classifier(Settings(llm_provider="rule"))
+    assert isinstance(rule_only, RuleBasedChatIntentClassifier)
+    composed = build_chat_intent_classifier(Settings(llm_provider="openai", openai_api_key="k"))
+    assert isinstance(composed, FallbackChatIntentClassifier)
+    assert isinstance(composed.fallback, RuleBasedChatIntentClassifier)