mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
04193cf71c
Both implement WebSearchProvider via tools/web_providers/ — matching the
existing SearXNG pattern (PR #5c906d702). Search-only; pair with any
extract provider via web.extract_backend.
- tools/web_providers/brave_free.py — Brave Search API (free tier, 2k
queries/mo). Uses BRAVE_SEARCH_API_KEY as X-Subscription-Token.
- tools/web_providers/ddgs.py — DuckDuckGo via the ddgs Python package.
No API key; gated on package importability.
- tools/web_tools.py: both backends added to _get_backend() config list
and auto-detect chain (trails paid providers), _is_backend_available,
web_search_tool dispatch, web_extract_tool + web_crawl_tool search-only
refusals, check_web_api_key, and the __main__ diagnostic. Introduces
_ddgs_package_importable() helper so tests can monkeypatch a single
symbol for the ddgs availability check.
- hermes_cli/tools_config.py: picker entries for both providers; ddgs
gets a post_setup handler that runs `pip install ddgs`.
- hermes_cli/config.py: BRAVE_SEARCH_API_KEY in OPTIONAL_ENV_VARS.
- scripts/release.py: AUTHOR_MAP entry for @Abd0r.
- tests: 14 new tests (brave-free) + 15 new tests (ddgs) covering
provider unit behavior, backend wiring, and search-only refusals.
Salvages the brave-free + ddgs portion of PR #19796. Not included: the
in-line helpers in web_tools.py (replaced with provider modules to match
the shipped architecture), the lynx-based extract path (these backends
should refuse extract with a clear error — users pair with a real
extract provider), and scripts/start-llama-server.sh (unrelated).
Co-authored-by: Abd0r <223003280+Abd0r@users.noreply.github.com>
246 lines
11 KiB
Python
246 lines
11 KiB
Python
"""Tests for the DuckDuckGo (ddgs) web search provider.
|
|
|
|
Covers:
|
|
- DDGSSearchProvider.is_configured() — reflects package importability
|
|
- DDGSSearchProvider.search() — happy path, missing package, runtime error
|
|
- Result normalization (title, url, description, position)
|
|
- _is_backend_available("ddgs") / _get_backend() integration
|
|
- web_extract / web_crawl return search-only errors when ddgs is active
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import sys
|
|
import types
|
|
from unittest.mock import MagicMock
|
|
|
|
|
|
def _install_fake_ddgs(monkeypatch, *, text_results=None, text_raises=None):
|
|
"""Install a stub ``ddgs`` module in sys.modules for the duration of a test.
|
|
|
|
``text_results``: iterable of dicts to yield from DDGS().text(...).
|
|
``text_raises``: if set, DDGS().text raises this exception instead.
|
|
"""
|
|
fake = types.ModuleType("ddgs")
|
|
|
|
class _FakeDDGS:
|
|
def __enter__(self):
|
|
return self
|
|
def __exit__(self, *_a):
|
|
return False
|
|
def text(self, query, max_results=5):
|
|
if text_raises is not None:
|
|
raise text_raises
|
|
for hit in (text_results or []):
|
|
yield hit
|
|
|
|
fake.DDGS = _FakeDDGS
|
|
monkeypatch.setitem(sys.modules, "ddgs", fake)
|
|
return fake
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# DDGSSearchProvider unit tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestDDGSProviderIsConfigured:
|
|
def test_configured_when_package_importable(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch)
|
|
# Drop any cached ``tools.web_providers.ddgs`` so is_configured re-imports ddgs fresh
|
|
monkeypatch.delitem(sys.modules, "tools.web_providers.ddgs", raising=False)
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
assert DDGSSearchProvider().is_configured() is True
|
|
|
|
def test_not_configured_when_package_missing(self, monkeypatch):
|
|
monkeypatch.delitem(sys.modules, "ddgs", raising=False)
|
|
monkeypatch.delitem(sys.modules, "tools.web_providers.ddgs", raising=False)
|
|
# Block the import so ``import ddgs`` raises ImportError even if the package is actually installed
|
|
import builtins
|
|
orig_import = builtins.__import__
|
|
|
|
def blocked_import(name, *args, **kwargs):
|
|
if name == "ddgs":
|
|
raise ImportError("blocked for test")
|
|
return orig_import(name, *args, **kwargs)
|
|
|
|
monkeypatch.setattr(builtins, "__import__", blocked_import)
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
assert DDGSSearchProvider().is_configured() is False
|
|
|
|
def test_provider_name(self):
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
assert DDGSSearchProvider().provider_name() == "ddgs"
|
|
|
|
def test_implements_web_search_provider(self):
|
|
from tools.web_providers.base import WebSearchProvider
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
assert issubclass(DDGSSearchProvider, WebSearchProvider)
|
|
|
|
|
|
class TestDDGSProviderSearch:
|
|
def test_happy_path_normalizes_results(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch, text_results=[
|
|
{"title": "A", "href": "https://a.example.com", "body": "desc A"},
|
|
{"title": "B", "href": "https://b.example.com", "body": "desc B"},
|
|
{"title": "C", "href": "https://c.example.com", "body": "desc C"},
|
|
])
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("q", limit=5)
|
|
|
|
assert result["success"] is True
|
|
web = result["data"]["web"]
|
|
assert len(web) == 3
|
|
assert web[0] == {"title": "A", "url": "https://a.example.com", "description": "desc A", "position": 1}
|
|
assert web[2]["position"] == 3
|
|
|
|
def test_accepts_url_key_as_fallback_for_href(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch, text_results=[
|
|
{"title": "A", "url": "https://a.example.com", "body": "desc A"},
|
|
])
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("q", limit=5)
|
|
|
|
assert result["success"] is True
|
|
assert result["data"]["web"][0]["url"] == "https://a.example.com"
|
|
|
|
def test_limit_is_respected(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch, text_results=[
|
|
{"title": f"R{i}", "href": f"https://r{i}.example.com", "body": ""}
|
|
for i in range(10)
|
|
])
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("q", limit=3)
|
|
|
|
assert result["success"] is True
|
|
assert len(result["data"]["web"]) == 3
|
|
|
|
def test_missing_package_returns_failure(self, monkeypatch):
|
|
monkeypatch.delitem(sys.modules, "ddgs", raising=False)
|
|
monkeypatch.delitem(sys.modules, "tools.web_providers.ddgs", raising=False)
|
|
import builtins
|
|
orig_import = builtins.__import__
|
|
|
|
def blocked_import(name, *args, **kwargs):
|
|
if name == "ddgs":
|
|
raise ImportError("blocked for test")
|
|
return orig_import(name, *args, **kwargs)
|
|
|
|
monkeypatch.setattr(builtins, "__import__", blocked_import)
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("q", limit=5)
|
|
assert result["success"] is False
|
|
assert "ddgs" in result["error"].lower()
|
|
|
|
def test_runtime_error_returns_failure(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch, text_raises=RuntimeError("rate limited 202"))
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("q", limit=5)
|
|
assert result["success"] is False
|
|
assert "rate limited" in result["error"] or "failed" in result["error"].lower()
|
|
|
|
def test_empty_results(self, monkeypatch):
|
|
_install_fake_ddgs(monkeypatch, text_results=[])
|
|
from tools.web_providers.ddgs import DDGSSearchProvider
|
|
|
|
result = DDGSSearchProvider().search("nothing", limit=5)
|
|
assert result["success"] is True
|
|
assert result["data"]["web"] == []
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Integration: _is_backend_available / _get_backend / check_web_api_key
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestDDGSBackendWiring:
|
|
def test_is_backend_available_true_when_package_importable(self, monkeypatch):
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
assert web_tools._is_backend_available("ddgs") is True
|
|
|
|
def test_is_backend_available_false_when_package_missing(self, monkeypatch):
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: False)
|
|
assert web_tools._is_backend_available("ddgs") is False
|
|
|
|
def test_configured_backend_accepted(self, monkeypatch):
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "ddgs"})
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
assert web_tools._get_backend() == "ddgs"
|
|
|
|
def test_ddgs_trails_paid_providers_in_auto_detect(self, monkeypatch):
|
|
"""Exa (priority) should win over ddgs in auto-detect."""
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {})
|
|
for key in ("FIRECRAWL_API_KEY", "FIRECRAWL_API_URL", "PARALLEL_API_KEY",
|
|
"TAVILY_API_KEY", "SEARXNG_URL", "BRAVE_SEARCH_API_KEY"):
|
|
monkeypatch.delenv(key, raising=False)
|
|
monkeypatch.setenv("EXA_API_KEY", "exa-key")
|
|
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
assert web_tools._get_backend() == "exa"
|
|
|
|
def test_auto_detect_picks_ddgs_as_last_resort(self, monkeypatch):
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {})
|
|
for key in ("FIRECRAWL_API_KEY", "FIRECRAWL_API_URL", "PARALLEL_API_KEY",
|
|
"TAVILY_API_KEY", "EXA_API_KEY", "SEARXNG_URL", "BRAVE_SEARCH_API_KEY"):
|
|
monkeypatch.delenv(key, raising=False)
|
|
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
assert web_tools._get_backend() == "ddgs"
|
|
|
|
def test_check_web_api_key_true_when_ddgs_configured(self, monkeypatch):
|
|
from tools import web_tools
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "ddgs"})
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
assert web_tools.check_web_api_key() is True
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ddgs is search-only: web_extract / web_crawl return clear errors
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestDDGSSearchOnlyErrors:
|
|
def test_web_extract_returns_search_only_error(self, monkeypatch):
|
|
import asyncio
|
|
from tools import web_tools
|
|
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "ddgs"})
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
|
|
monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False, raising=False)
|
|
|
|
result_str = asyncio.get_event_loop().run_until_complete(
|
|
web_tools.web_extract_tool(["https://example.com"])
|
|
)
|
|
result = json.loads(result_str)
|
|
assert result["success"] is False
|
|
assert "search-only" in result["error"].lower()
|
|
assert "duckduckgo" in result["error"].lower() or "ddgs" in result["error"].lower()
|
|
|
|
def test_web_crawl_returns_search_only_error(self, monkeypatch):
|
|
import asyncio
|
|
from tools import web_tools
|
|
|
|
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "ddgs"})
|
|
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: True)
|
|
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
|
|
monkeypatch.setattr(web_tools, "check_firecrawl_api_key", lambda: False)
|
|
monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False, raising=False)
|
|
|
|
result_str = asyncio.get_event_loop().run_until_complete(
|
|
web_tools.web_crawl_tool("https://example.com")
|
|
)
|
|
result = json.loads(result_str)
|
|
assert result["success"] is False
|
|
assert "search-only" in result["error"].lower()
|
|
assert "duckduckgo" in result["error"].lower() or "ddgs" in result["error"].lower()
|