mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 06:12:14 +08:00
76803b826f
* refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
185 lines
8.0 KiB
Python
185 lines
8.0 KiB
Python
"""Tests for InfoQuest client and tools."""
|
|
|
|
import json
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from deerflow.community.infoquest import tools
|
|
from deerflow.community.infoquest.infoquest_client import InfoQuestClient
|
|
|
|
|
|
class TestInfoQuestClient:
|
|
def test_infoquest_client_initialization(self):
|
|
"""Test InfoQuestClient initialization with different parameters."""
|
|
# Test with default parameters
|
|
client = InfoQuestClient()
|
|
assert client.fetch_time == -1
|
|
assert client.fetch_timeout == -1
|
|
assert client.fetch_navigation_timeout == -1
|
|
assert client.search_time_range == -1
|
|
|
|
# Test with custom parameters
|
|
client = InfoQuestClient(fetch_time=10, fetch_timeout=30, fetch_navigation_timeout=60, search_time_range=24)
|
|
assert client.fetch_time == 10
|
|
assert client.fetch_timeout == 30
|
|
assert client.fetch_navigation_timeout == 60
|
|
assert client.search_time_range == 24
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_fetch_success(self, mock_post):
|
|
"""Test successful fetch operation."""
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 200
|
|
mock_response.text = json.dumps({"reader_result": "<html><body>Test content</body></html>"})
|
|
mock_post.return_value = mock_response
|
|
|
|
client = InfoQuestClient()
|
|
result = client.fetch("https://example.com")
|
|
|
|
assert result == "<html><body>Test content</body></html>"
|
|
mock_post.assert_called_once()
|
|
args, kwargs = mock_post.call_args
|
|
assert args[0] == "https://reader.infoquest.bytepluses.com"
|
|
assert kwargs["json"]["url"] == "https://example.com"
|
|
assert kwargs["json"]["format"] == "HTML"
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_fetch_non_200_status(self, mock_post):
|
|
"""Test fetch operation with non-200 status code."""
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 404
|
|
mock_response.text = "Not Found"
|
|
mock_post.return_value = mock_response
|
|
|
|
client = InfoQuestClient()
|
|
result = client.fetch("https://example.com")
|
|
|
|
assert result == "Error: fetch API returned status 404: Not Found"
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_fetch_empty_response(self, mock_post):
|
|
"""Test fetch operation with empty response."""
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 200
|
|
mock_response.text = ""
|
|
mock_post.return_value = mock_response
|
|
|
|
client = InfoQuestClient()
|
|
result = client.fetch("https://example.com")
|
|
|
|
assert result == "Error: no result found"
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_web_search_raw_results_success(self, mock_post):
|
|
"""Test successful web_search_raw_results operation."""
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 200
|
|
mock_response.json.return_value = {"search_result": {"results": [{"content": {"results": {"organic": [{"title": "Test Result", "desc": "Test description", "url": "https://example.com"}]}}}], "images_results": []}}
|
|
mock_post.return_value = mock_response
|
|
|
|
client = InfoQuestClient()
|
|
result = client.web_search_raw_results("test query", "")
|
|
|
|
assert "search_result" in result
|
|
mock_post.assert_called_once()
|
|
args, kwargs = mock_post.call_args
|
|
assert args[0] == "https://search.infoquest.bytepluses.com"
|
|
assert kwargs["json"]["query"] == "test query"
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_web_search_success(self, mock_post):
|
|
"""Test successful web_search operation."""
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 200
|
|
mock_response.json.return_value = {"search_result": {"results": [{"content": {"results": {"organic": [{"title": "Test Result", "desc": "Test description", "url": "https://example.com"}]}}}], "images_results": []}}
|
|
mock_post.return_value = mock_response
|
|
|
|
client = InfoQuestClient()
|
|
result = client.web_search("test query")
|
|
|
|
# Check if result is a valid JSON string with expected content
|
|
result_data = json.loads(result)
|
|
assert len(result_data) == 1
|
|
assert result_data[0]["title"] == "Test Result"
|
|
assert result_data[0]["url"] == "https://example.com"
|
|
|
|
def test_clean_results(self):
|
|
"""Test clean_results method with sample raw results."""
|
|
raw_results = [
|
|
{
|
|
"content": {
|
|
"results": {
|
|
"organic": [{"title": "Test Page", "desc": "Page description", "url": "https://example.com/page1"}],
|
|
"top_stories": {"items": [{"title": "Test News", "source": "Test Source", "time_frame": "2 hours ago", "url": "https://example.com/news1"}]},
|
|
}
|
|
}
|
|
}
|
|
]
|
|
|
|
cleaned = InfoQuestClient.clean_results(raw_results)
|
|
|
|
assert len(cleaned) == 2
|
|
assert cleaned[0]["type"] == "page"
|
|
assert cleaned[0]["title"] == "Test Page"
|
|
assert cleaned[1]["type"] == "news"
|
|
assert cleaned[1]["title"] == "Test News"
|
|
|
|
def test_clean_results_with_image_search(self):
|
|
"""Test clean_results_with_image_search method with sample raw results."""
|
|
raw_results = [{"content": {"results": {"images_results": [{"image_url": "https://example.com/image1.jpg", "thumbnail_url": "https://example.com/thumb1.jpg", "url": "https://example.com/page1"}]}}}]
|
|
cleaned = InfoQuestClient.clean_results_with_image_search(raw_results)
|
|
|
|
assert len(cleaned) == 1
|
|
assert cleaned[0]["image_url"] == "https://example.com/image1.jpg"
|
|
assert cleaned[0]["thumbnail_url"] == "https://example.com/thumb1.jpg"
|
|
assert cleaned[0]["url"] == "https://example.com/page1"
|
|
|
|
@patch("deerflow.community.infoquest.tools._get_infoquest_client")
|
|
def test_web_search_tool(self, mock_get_client):
|
|
"""Test web_search_tool function."""
|
|
mock_client = MagicMock()
|
|
mock_client.web_search.return_value = json.dumps([])
|
|
mock_get_client.return_value = mock_client
|
|
|
|
result = tools.web_search_tool.run("test query")
|
|
|
|
assert result == json.dumps([])
|
|
mock_get_client.assert_called_once()
|
|
mock_client.web_search.assert_called_once_with("test query")
|
|
|
|
@patch("deerflow.community.infoquest.tools._get_infoquest_client")
|
|
def test_web_fetch_tool(self, mock_get_client):
|
|
"""Test web_fetch_tool function."""
|
|
mock_client = MagicMock()
|
|
mock_client.fetch.return_value = "<html><body>Test content</body></html>"
|
|
mock_get_client.return_value = mock_client
|
|
|
|
result = tools.web_fetch_tool.run("https://example.com")
|
|
|
|
assert result == "# Untitled\n\nTest content"
|
|
mock_get_client.assert_called_once()
|
|
mock_client.fetch.assert_called_once_with("https://example.com")
|
|
|
|
@patch("deerflow.community.infoquest.tools.get_app_config")
|
|
def test_get_infoquest_client(self, mock_get_app_config):
|
|
"""Test _get_infoquest_client function with config."""
|
|
mock_config = MagicMock()
|
|
mock_config.get_tool_config.side_effect = [MagicMock(model_extra={"search_time_range": 24}), MagicMock(model_extra={"fetch_time": 10, "timeout": 30, "navigation_timeout": 60})]
|
|
mock_get_app_config.return_value = mock_config
|
|
|
|
client = tools._get_infoquest_client()
|
|
|
|
assert client.search_time_range == 24
|
|
assert client.fetch_time == 10
|
|
assert client.fetch_timeout == 30
|
|
assert client.fetch_navigation_timeout == 60
|
|
|
|
@patch("deerflow.community.infoquest.infoquest_client.requests.post")
|
|
def test_web_search_api_error(self, mock_post):
|
|
"""Test web_search operation with API error."""
|
|
mock_post.side_effect = Exception("Connection error")
|
|
|
|
client = InfoQuestClient()
|
|
result = client.web_search("test query")
|
|
|
|
assert "Error" in result
|