fix(ai): align F-4 chat tests with PR42 LLM routing

[HOKAGO-MEMORIES]

변경 내용

• PR feat(ai): 매물 추천 Text-to-SQL 및 LLM 기반 의도 분류 구현 (#29) #42 이후 agent chat 테스트가 키워드 분류 가정에 의존하지 않도록 수정
• 각 Phase 1~3 관련 chat 테스트에서 LLMClient.classify()를 mock해 RouteDecision 기반 라우팅을 그대로 사용
• property/search, legal, price, safety 분석 경로가 새 route_by_intent 흐름 위에서 검증되도록 정합화

참고

• PR feat(ai): 매물 추천 Text-to-SQL 및 LLM 기반 의도 분류 구현 (#29) #42: feat(ai): 매물 추천 Text-to-SQL 및 LLM 기반 의도 분류 구현
• Phase 4 시작 전 F-4 Phase 1~3 테스트 정합성 보정

테스트

• backend-ai: .\.venv\Scripts\python.exe -m pytest tests\test_agent_chat.py tests\test_classify_intent.py tests\test_spring_client.py
• backend-ai: .\.venv\Scripts\python.exe -m pytest tests
• git diff --check

Summary by CodeRabbit

• Tests
  • Enhanced agent-chat test infrastructure with a new helper function that enables systematic testing of request routing to different intent handlers, including property search, legal consultation, price analysis, and safety analysis scenarios.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 16968e33-6f60-4e6c-badd-0f024d7ee43c

📥 Commits

Reviewing files that changed from the base of the PR and between 4f583b0 and ac314d2.

📒 Files selected for processing (1)

• backend-ai/tests/test_agent_chat.py

---

📝 Walkthrough

Walkthrough

A route_as(monkeypatch, intent) helper is added to backend-ai/tests/test_agent_chat.py. It monkeypatches LLMClient.classify to return a fixed intent and clears the get_agent_graph cache. All existing agent-chat routing tests are updated to call this helper instead of only clearing the cache directly.

Changes

Deterministic Intent Routing in Tests

Layer / File(s)	Summary
route_as helper and LLMClient import backend-ai/tests/test_agent_chat.py	Imports LLMClient and defines route_as(monkeypatch, intent) which stubs LLMClient.classify to return a fixed intent with reasoning and clears get_agent_graph cache.
Apply route_as across all routing tests backend-ai/tests/test_agent_chat.py	Updates test_agent_chat_returns_intent_and_answer to accept monkeypatch, and replaces bare get_agent_graph.cache_clear() calls with route_as(...) in the PROPERTY_SEARCH, LEGAL_CONSULT, PRICE_ANALYSIS (success and fallback), and SAFETY_ANALYSIS test setups.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Poem

🐇 Hop, hop, the classify call is tamed,
A route_as helper takes the blame,
No more cache clears alone to trust—
Monkeypatch the LLM we must!
Fixed intents keep the tests on track,
This bunny won't look back. 🥕

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: updating chat tests to align with PR42's LLM routing changes, replacing keyword classification assumptions with proper mocking.
Description check	✅ Passed	The description covers all required template sections: changes made, related issue references, testing verification, and includes supporting context about PR #42 and project phase alignment.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fix/ai-analysis-pr42-routing

---

_{Comment @coderabbitai help to get the list of available commands.}