824251d328
The structured /cv/* calls funnel through a provider router so production can offload a weak local GPU (GTX 1060) to a cloud provider without any .NET change. Default stays "ollama" (keyless/local) and /summarize remains local distilbart. - AI_PROVIDER=ollama|gemini|groq dispatch inside _ollama_generate_json/_text (entry-point names kept, so no call sites change; Ollama path is byte-identical). - Gemini (x-goog-api-key header, not URL query) and Groq (OpenAI-compatible chat/completions) added via stdlib urllib — zero new dependencies. - /health reports ai_provider + ai_provider_configured. - Keys read from env only; never logged/committed. - Compose + .env.example pass AI_PROVIDER/GEMINI_*/GROQ_* through. Tests: 11 passed (default Ollama unchanged, Gemini/Groq dispatch, missing-key 503, health reports provider). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
248 lines
8.9 KiB
Python
248 lines
8.9 KiB
Python
import importlib
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
from fastapi.testclient import TestClient
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
|
|
def load_app_module(monkeypatch, *, skip_model_load=True, ollama_model=None):
|
|
if skip_model_load:
|
|
monkeypatch.setenv("AI_SERVICE_SKIP_MODEL_LOAD", "1")
|
|
else:
|
|
monkeypatch.delenv("AI_SERVICE_SKIP_MODEL_LOAD", raising=False)
|
|
monkeypatch.delenv("AI_SERVICE_EAGER_MODEL_LOAD", raising=False)
|
|
if ollama_model is None:
|
|
monkeypatch.delenv("OLLAMA_MODEL", raising=False)
|
|
else:
|
|
monkeypatch.setenv("OLLAMA_MODEL", ollama_model)
|
|
if "app" in sys.modules:
|
|
del sys.modules["app"]
|
|
module = importlib.import_module("app")
|
|
return importlib.reload(module)
|
|
|
|
|
|
def test_health_reports_runtime_without_ollama_and_without_forcing_model_load(monkeypatch):
|
|
module = load_app_module(monkeypatch)
|
|
client = TestClient(module.app)
|
|
|
|
response = client.get("/health")
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["ok"] is True
|
|
assert payload["device"] == "cpu"
|
|
assert payload["model_loaded"] is False
|
|
assert payload["model_disabled"] is True
|
|
assert payload["summarize_available"] is False
|
|
assert "disabled" in payload["model_load_error"].lower()
|
|
assert payload["ollama_configured"] is False
|
|
assert payload["ollama_model"] is None
|
|
assert payload["ollama_installed_models"] == []
|
|
assert payload["ollama_loaded_models"] == []
|
|
|
|
|
|
def test_summarize_returns_503_with_explicit_reason_when_model_loading_is_disabled(monkeypatch):
|
|
module = load_app_module(monkeypatch)
|
|
client = TestClient(module.app)
|
|
|
|
response = client.post("/summarize", json={"text": "Platform engineering role with APIs and Python experience."})
|
|
|
|
assert response.status_code == 503
|
|
payload = response.json()
|
|
assert "disabled" in payload["detail"].lower()
|
|
|
|
|
|
def test_health_reports_ollama_unreachable_when_configured_but_not_available(monkeypatch):
|
|
module = load_app_module(monkeypatch, ollama_model="qwen2.5:7b")
|
|
|
|
def boom(path: str):
|
|
raise OSError("connection refused")
|
|
|
|
monkeypatch.setattr(module, "_ollama_json", boom)
|
|
client = TestClient(module.app)
|
|
|
|
response = client.get("/health")
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["ollama_configured"] is True
|
|
assert payload["ollama_reachable"] is False
|
|
assert payload["ollama_model"] == "qwen2.5:7b"
|
|
assert payload["ollama_model_available"] is False
|
|
|
|
|
|
def test_rewrite_cv_returns_plain_rewritten_text(monkeypatch):
|
|
module = load_app_module(monkeypatch, ollama_model="qwen2.5:7b")
|
|
monkeypatch.setattr(module, "_ollama_generate_text", lambda prompt: "# Professional Summary\nBuilt resilient backend systems.\n\n# Skills\n- C#\n- .NET")
|
|
client = TestClient(module.app)
|
|
|
|
response = client.post("/cv/rewrite", json={
|
|
"instruction": "Rewrite this CV into a cleaner master CV.",
|
|
"text": "Professional Summary\nBuilt backend systems.",
|
|
"max_length": 220,
|
|
"min_length": 80,
|
|
})
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["rewritten_text"].startswith("# Professional Summary")
|
|
assert "Role summary:" not in payload["rewritten_text"]
|
|
|
|
|
|
def test_classify_block_returns_structured_json(monkeypatch):
|
|
module = load_app_module(monkeypatch)
|
|
|
|
def fake_generate_json(prompt: str):
|
|
assert "Senior Platform Engineer" in prompt
|
|
return {
|
|
"section": "Work Experience",
|
|
"confidence": 0.91,
|
|
"reason": "job block",
|
|
"title": "Senior Platform Engineer",
|
|
"company": "Atlas Systems",
|
|
"location": "Oslo",
|
|
"start": "2019",
|
|
"end": "Present",
|
|
"bullets": ["Built event-driven APIs and migration tooling."],
|
|
"summary": [],
|
|
"skills": ["Python", "SQL"],
|
|
}
|
|
|
|
monkeypatch.setattr(module, "_ollama_generate_json", fake_generate_json)
|
|
client = TestClient(module.app)
|
|
|
|
response = client.post("/cv/classify-block", json={"block": "Senior Platform Engineer at Atlas Systems, Oslo, 2019 - Present. Built event-driven APIs and migration tooling."})
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["section"] == "Work Experience"
|
|
assert payload["title"] == "Senior Platform Engineer"
|
|
assert payload["company"] == "Atlas Systems"
|
|
assert payload["bullets"] == ["Built event-driven APIs and migration tooling."]
|
|
assert payload["summary"] == []
|
|
assert payload["skills"] == ["Python", "SQL"]
|
|
|
|
|
|
def test_classify_block_defaults_missing_section_to_other(monkeypatch):
|
|
module = load_app_module(monkeypatch)
|
|
monkeypatch.setattr(module, "_ollama_generate_json", lambda prompt: {"bullets": []})
|
|
client = TestClient(module.app)
|
|
|
|
response = client.post("/cv/classify-block", json={"block": "Miscellaneous profile text"})
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload["section"] == "Other"
|
|
assert payload["bullets"] == []
|
|
assert payload["summary"] == []
|
|
assert payload["skills"] == []
|
|
|
|
|
|
# --- AI provider router -------------------------------------------------------
|
|
|
|
class _FakeResponse:
|
|
def __init__(self, payload):
|
|
self._data = json.dumps(payload).encode("utf-8")
|
|
|
|
def read(self):
|
|
return self._data
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *exc):
|
|
return False
|
|
|
|
|
|
def _install_fake_urlopen(monkeypatch, module, response_payload, captured):
|
|
def fake_urlopen(req, timeout=None):
|
|
captured["url"] = req.full_url
|
|
captured["headers"] = {k.lower(): v for k, v in req.header_items()}
|
|
captured["body"] = json.loads(req.data.decode("utf-8"))
|
|
return _FakeResponse(response_payload)
|
|
|
|
monkeypatch.setattr(module.urllib_request, "urlopen", fake_urlopen)
|
|
|
|
|
|
def test_provider_defaults_to_ollama_and_is_unchanged(monkeypatch):
|
|
monkeypatch.delenv("AI_PROVIDER", raising=False)
|
|
monkeypatch.setenv("OLLAMA_BASE_URL", "http://ollama-host:11434")
|
|
module = load_app_module(monkeypatch, ollama_model="qwen2.5:7b")
|
|
assert module.AI_PROVIDER == "ollama"
|
|
|
|
captured = {}
|
|
_install_fake_urlopen(monkeypatch, module, {"response": '{"score": 7}'}, captured)
|
|
|
|
assert module._ollama_generate_json("hi") == {"score": 7}
|
|
assert captured["url"] == "http://ollama-host:11434/api/generate"
|
|
assert captured["body"]["model"] == "qwen2.5:7b"
|
|
assert captured["body"]["format"] == "json"
|
|
assert captured["body"]["options"]["temperature"] == 0.1
|
|
|
|
|
|
def test_provider_gemini_dispatch(monkeypatch):
|
|
monkeypatch.setenv("AI_PROVIDER", "gemini")
|
|
monkeypatch.setenv("GEMINI_API_KEY", "test-key")
|
|
monkeypatch.setenv("GEMINI_MODEL", "gemini-2.0-flash")
|
|
module = load_app_module(monkeypatch)
|
|
|
|
captured = {}
|
|
payload = {"candidates": [{"content": {"parts": [{"text": '{"score": 9}'}]}}]}
|
|
_install_fake_urlopen(monkeypatch, module, payload, captured)
|
|
|
|
assert module._ollama_generate_json("hi") == {"score": 9}
|
|
assert "generativelanguage" in captured["url"]
|
|
assert "gemini-2.0-flash:generateContent" in captured["url"]
|
|
assert "key=" not in captured["url"] # key must not be in the URL
|
|
assert captured["headers"].get("x-goog-api-key") == "test-key"
|
|
assert captured["body"]["generationConfig"]["responseMimeType"] == "application/json"
|
|
|
|
|
|
def test_provider_groq_dispatch(monkeypatch):
|
|
monkeypatch.setenv("AI_PROVIDER", "groq")
|
|
monkeypatch.setenv("GROQ_API_KEY", "test-key")
|
|
module = load_app_module(monkeypatch)
|
|
|
|
captured = {}
|
|
payload = {"choices": [{"message": {"content": "rewritten CV text"}}]}
|
|
_install_fake_urlopen(monkeypatch, module, payload, captured)
|
|
|
|
assert module._ollama_generate_text("rewrite this") == "rewritten CV text"
|
|
assert captured["url"].endswith("/chat/completions")
|
|
assert captured["headers"].get("authorization") == "Bearer test-key"
|
|
assert captured["body"]["messages"][0]["content"] == "rewrite this"
|
|
|
|
|
|
def test_provider_missing_cloud_key_raises_503(monkeypatch):
|
|
monkeypatch.setenv("AI_PROVIDER", "gemini")
|
|
monkeypatch.delenv("GEMINI_API_KEY", raising=False)
|
|
module = load_app_module(monkeypatch)
|
|
|
|
from fastapi import HTTPException
|
|
|
|
try:
|
|
module._ollama_generate_json("hi")
|
|
except HTTPException as ex:
|
|
assert ex.status_code == 503
|
|
assert "GEMINI_API_KEY" in ex.detail
|
|
else:
|
|
raise AssertionError("expected HTTPException for missing GEMINI_API_KEY")
|
|
|
|
|
|
def test_health_reports_active_provider(monkeypatch):
|
|
monkeypatch.setenv("AI_PROVIDER", "gemini")
|
|
monkeypatch.setenv("GEMINI_API_KEY", "test-key")
|
|
module = load_app_module(monkeypatch)
|
|
client = TestClient(module.app)
|
|
|
|
payload = client.get("/health").json()
|
|
|
|
assert payload["ai_provider"] == "gemini"
|
|
assert payload["ai_provider_configured"] is True
|