mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
27aa05f54e
* feat(community): add Jsonify dataset rows tool Adds deerflow.community.jsonify.tools:dataset_rows_tool, a read-only tool that returns rows from maintained Jsonify datasets. Jsonify pipelines run on a schedule and repair themselves when a source changes, so the agent reads a current table instead of scraping. - operator configures a named map of dataset -> serve URL; the model picks by name and never sees the URL - serve URLs must be https without userinfo and pass validate_public_http_url before any request; the URL is redacted from error text - paging with has_more/next_offset, version pinned after the first page, limit clamped to the configured max_rows, system columns stripped - config.example.yaml entry under tools; unit tests cover paging, clamping, unknown dataset, unconfigured tool, http/userinfo rejection, private address block and error redaction Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QrmeK98ZKoxZNiUiz8kVeX * fix(community): harden Jsonify tool paging, logging and error handling - Stop paging on an empty page or a next_offset that does not advance - Log config validation failures by field location and error type only - Validate page shape; malformed or non-JSON pages return a clean error - Transport errors report the exception type, never the URL - Add truncated flag when rows were clipped or more rows remain - Tests for each case Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QrmeK98ZKoxZNiUiz8kVeX --------- Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
277 lines
11 KiB
Python
277 lines
11 KiB
Python
"""Unit tests for the Jsonify community tool."""
|
|
|
|
import ipaddress
|
|
import json
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
SERVE_URL = "https://factory.jsonify.com/api/serve/abc123"
|
|
PAGE_ONE = {
|
|
"dataset": "abc123",
|
|
"dataset_name": "LLM API pricing",
|
|
"table": "models",
|
|
"version": 3,
|
|
"updated_at": 1791979608,
|
|
"row_count": 2,
|
|
"has_more": True,
|
|
"next_offset": 2,
|
|
"rows": [
|
|
{"_row_id": "r1", "_parent_row_id": "p1", "_source_key": "anthropic", "provider": "Anthropic", "model": "a"},
|
|
{"_row_id": "r2", "_parent_row_id": "p2", "_source_key": "anthropic", "provider": "Anthropic", "model": "b"},
|
|
],
|
|
}
|
|
PAGE_TWO = {**PAGE_ONE, "row_count": 1, "has_more": False, "next_offset": None, "rows": [{"_row_id": "r3", "provider": "Anthropic", "model": "c"}]}
|
|
|
|
|
|
@pytest.fixture
|
|
def public_dns():
|
|
with patch(
|
|
"deerflow.community.url_safety.resolve_host_addresses",
|
|
return_value=[ipaddress.ip_address("93.184.216.34")],
|
|
):
|
|
yield
|
|
|
|
|
|
def _config(extra: dict | None):
|
|
tool_config = MagicMock()
|
|
tool_config.model_extra = extra
|
|
app_config = MagicMock()
|
|
app_config.get_tool_config.return_value = tool_config
|
|
return app_config
|
|
|
|
|
|
def _response(payload: dict, status: int = 200) -> httpx.Response:
|
|
return httpx.Response(status, json=payload, request=httpx.Request("GET", SERVE_URL))
|
|
|
|
|
|
def _client_with(responses: list[httpx.Response]) -> MagicMock:
|
|
client = MagicMock()
|
|
client.get = AsyncMock(side_effect=responses)
|
|
client.__aenter__ = AsyncMock(return_value=client)
|
|
client.__aexit__ = AsyncMock(return_value=None)
|
|
return client
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_reads_pages_strips_system_columns_and_pins_version():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response(PAGE_ONE), _response(PAGE_TWO)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = json.loads(await dataset_rows_tool.ainvoke({"dataset": "pricing", "filters": {"provider": "Anthropic"}, "columns": ["provider", "model"], "limit": 10}))
|
|
|
|
assert result["dataset_name"] == "LLM API pricing"
|
|
assert result["row_count"] == 3
|
|
assert result["rows"][0] == {"_row_id": "r1", "provider": "Anthropic", "model": "a"}
|
|
first = client.get.call_args_list[0].kwargs["params"]
|
|
second = client.get.call_args_list[1].kwargs["params"]
|
|
assert first == {"limit": 10, "offset": 0, "columns": "provider,model", "filter[provider]": "Anthropic"}
|
|
assert second["offset"] == 2
|
|
assert second["version"] == 3
|
|
assert second["limit"] == 8
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_limit_is_capped_by_configured_max_rows():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response(PAGE_ONE)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}, "max_rows": 1})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = json.loads(await dataset_rows_tool.ainvoke({"dataset": "pricing", "limit": 500}))
|
|
|
|
assert client.get.call_args.kwargs["params"]["limit"] == 1
|
|
assert result["row_count"] == 1
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_unknown_dataset_lists_available_names():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
with patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL, "releases": SERVE_URL + "0"}})):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "nope"})
|
|
|
|
assert result == "Error: Unknown dataset 'nope'. Available datasets: pricing, releases"
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_unconfigured_tool_returns_error_without_request():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config(None)),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient") as client_cls,
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
|
|
assert result.startswith("Error: jsonify_dataset_rows is not configured")
|
|
client_cls.assert_not_called()
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_rejects_http_serve_url_and_userinfo():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
for bad in ("http://factory.jsonify.com/api/serve/abc", "https://user:pw@factory.jsonify.com/api/serve/abc"):
|
|
with patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": bad}})):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
assert result.startswith("Error: jsonify_dataset_rows is not configured")
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_private_address_blocked_before_request():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"meta": "https://169.254.169.254/latest/meta-data"}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient") as client_cls,
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "meta"})
|
|
|
|
assert result.startswith("Error:")
|
|
client_cls.assert_not_called()
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_http_error_is_redacted():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response({"error": "nope"}, status=404)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
|
|
assert result == "Error: Jsonify returned HTTP 404"
|
|
assert SERVE_URL not in result
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_truncated_flag_when_more_rows_match():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response(PAGE_ONE)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = json.loads(await dataset_rows_tool.ainvoke({"dataset": "pricing", "limit": 2}))
|
|
|
|
assert result["row_count"] == 2
|
|
assert result["truncated"] is True
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_complete_read_is_not_truncated():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response(PAGE_TWO)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = json.loads(await dataset_rows_tool.ainvoke({"dataset": "pricing"}))
|
|
|
|
assert result["truncated"] is False
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
@pytest.mark.parametrize(
|
|
"page",
|
|
[
|
|
{**PAGE_ONE, "next_offset": 0},
|
|
{**PAGE_ONE, "next_offset": "2"},
|
|
{**PAGE_ONE, "rows": []},
|
|
],
|
|
)
|
|
async def test_stops_when_cursor_does_not_advance_or_page_is_empty(page):
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([_response(page), _response(PAGE_TWO)])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = json.loads(await dataset_rows_tool.ainvoke({"dataset": "pricing", "limit": 100}))
|
|
|
|
assert client.get.call_count == 1
|
|
assert result["row_count"] == len(page["rows"])
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
@pytest.mark.parametrize("payload", [["not", "a", "page"], {"rows": "nope"}, {"rows": ["r1"]}, {"has_more": False}])
|
|
async def test_malformed_page_returns_redacted_error(payload):
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = MagicMock()
|
|
client.get = AsyncMock(return_value=httpx.Response(200, json=payload, request=httpx.Request("GET", SERVE_URL)))
|
|
client.__aenter__ = AsyncMock(return_value=client)
|
|
client.__aexit__ = AsyncMock(return_value=None)
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
|
|
assert result == "Error: Jsonify returned an unexpected response shape"
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_non_json_page_returns_error():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = _client_with([httpx.Response(200, text="<html>", request=httpx.Request("GET", SERVE_URL))])
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
|
|
assert result == "Error: Jsonify returned a response that is not JSON"
|
|
|
|
|
|
def test_invalid_config_warning_omits_serve_url(caplog):
|
|
from deerflow.community.jsonify.tools import _load_settings
|
|
|
|
secret = "http://factory.jsonify.com/api/serve/supersecret"
|
|
with patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": secret}})):
|
|
result = _load_settings()
|
|
|
|
assert isinstance(result, str)
|
|
assert "supersecret" not in caplog.text
|
|
assert "datasets: value_error" in caplog.text
|
|
|
|
|
|
@pytest.mark.anyio
|
|
@pytest.mark.usefixtures("public_dns")
|
|
async def test_transport_error_omits_url():
|
|
from deerflow.community.jsonify.tools import dataset_rows_tool
|
|
|
|
client = MagicMock()
|
|
client.get = AsyncMock(side_effect=httpx.ConnectError(f"failed to connect to {SERVE_URL}"))
|
|
client.__aenter__ = AsyncMock(return_value=client)
|
|
client.__aexit__ = AsyncMock(return_value=None)
|
|
with (
|
|
patch("deerflow.community.jsonify.tools.get_app_config", return_value=_config({"datasets": {"pricing": SERVE_URL}})),
|
|
patch("deerflow.community.jsonify.tools.httpx.AsyncClient", return_value=client),
|
|
):
|
|
result = await dataset_rows_tool.ainvoke({"dataset": "pricing"})
|
|
|
|
assert result == "Error: Could not reach Jsonify: ConnectError"
|