aaafa78883
- Introduced `card_language` attribute in ProjectRecord and Workspace classes to handle multiple languages for project cards. - Updated project creation and renaming methods to accept and store the card language. - Enhanced ZoteroReader to read and return attachment metadata, including language-specific summaries and claims. - Modified LLM client to generate card content based on the specified language, supporting both English and Chinese. - Updated tests to cover new functionality, ensuring correct handling of multilingual card generation and retrieval. - Adjusted UI tests to verify the presence of language selection options and proper rendering of multilingual content.
93 lines
3.7 KiB
Python
93 lines
3.7 KiB
Python
import json
|
|
|
|
import pytest
|
|
|
|
from zotero_kb.llm import DeepSeekCardGenerationClient, create_card_generation_client
|
|
|
|
|
|
def test_create_card_generation_client_requires_deepseek_api_key() -> None:
|
|
with pytest.raises(ValueError, match="DEEPSEEK_API_KEY"):
|
|
create_card_generation_client("deepseek", "deepseek-chat", env={})
|
|
|
|
|
|
def test_deepseek_client_uses_env_api_key_and_parses_json() -> None:
|
|
captured = {}
|
|
|
|
def fake_request(url: str, payload: dict[str, object], headers: dict[str, str]) -> dict[str, object]:
|
|
captured["url"] = url
|
|
captured["payload"] = payload
|
|
captured["headers"] = headers
|
|
return {
|
|
"choices": [
|
|
{
|
|
"message": {
|
|
"content": json.dumps(
|
|
{
|
|
"summary": "DeepSeek summary",
|
|
"core_claims": ["Claim A"],
|
|
"methods": ["Method A"],
|
|
"evidence": ["Evidence A"],
|
|
"citations": [
|
|
{
|
|
"claim": "Claim A",
|
|
"quote": "Exact supporting quote.",
|
|
"paraphrase": "Paraphrased support.",
|
|
"quote_source": "attachment_texts",
|
|
"use_case": "direct_quote",
|
|
}
|
|
],
|
|
"quotable_passages": ["Quote A"],
|
|
"writing_hints": ["Hint A"],
|
|
"keywords": ["kw-a"],
|
|
}
|
|
)
|
|
}
|
|
}
|
|
]
|
|
}
|
|
|
|
client = create_card_generation_client(
|
|
"deepseek",
|
|
"deepseek-chat",
|
|
env={"DEEPSEEK_API_KEY": "sk-test"},
|
|
request_fn=fake_request,
|
|
)
|
|
result = client.generate_card(
|
|
{
|
|
"title": "Scoped Retrieval for Drafting",
|
|
"abstract": "Merged metadata improves drafting.",
|
|
"card_language": "zh",
|
|
"notes": ["Project scoping helps."],
|
|
"attachment_texts": ["Attachment evidence."],
|
|
"tags": ["retrieval"],
|
|
}
|
|
)
|
|
|
|
assert result["summary"] == "DeepSeek summary"
|
|
assert "locator" not in result["citations"][0]
|
|
assert captured["url"] == "https://api.deepseek.com/v1/chat/completions"
|
|
assert captured["payload"]["model"] == "deepseek-chat"
|
|
assert "Return 1-3 citations whenever the source bundle contains usable supporting text" in captured["payload"]["messages"][1]["content"]
|
|
assert "quote_source must identify where the quote came from" in captured["payload"]["messages"][1]["content"]
|
|
assert "Write summary, core_claims, methods, evidence, paraphrase fields, and writing_hints in Chinese." in captured["payload"]["messages"][1]["content"]
|
|
assert captured["headers"]["Authorization"] == "Bearer sk-test"
|
|
|
|
|
|
def test_deepseek_client_strips_markdown_fences() -> None:
|
|
client = DeepSeekCardGenerationClient(
|
|
api_key="sk-test",
|
|
request_fn=lambda *_args, **_kwargs: {
|
|
"choices": [
|
|
{
|
|
"message": {
|
|
"content": "```json\n{\"summary\":\"Fence summary\",\"core_claims\":[],\"methods\":[],\"evidence\":[],\"citations\":[],\"quotable_passages\":[],\"writing_hints\":[],\"keywords\":[]}\n```"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
)
|
|
|
|
result = client.generate_card({"title": "Paper"})
|
|
|
|
assert result["summary"] == "Fence summary"
|