feat(web): add Brave Search (free tier) and DDGS search providers

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>
This commit is contained in:
Abd0r 2026-05-07 07:23:03 -07:00 committed by Teknium
parent cdc0a47dd5
commit 04193cf71c
8 changed files with 862 additions and 9 deletions

View file

@ -0,0 +1,275 @@
"""Tests for the Brave Search (free tier) web search provider.
Covers:
- BraveFreeSearchProvider.is_configured() env var gating
- BraveFreeSearchProvider.search() happy path, HTTP error, request error, bad JSON
- Result normalization (title, url, description, position)
- Limit truncation + Brave's count cap (20)
- _is_backend_available("brave-free") integration
- _get_backend() recognizes "brave-free" as a valid configured backend
- check_web_api_key() includes brave-free in availability check
- web_extract / web_crawl return search-only errors when brave-free is active
"""
from __future__ import annotations
import json
from unittest.mock import MagicMock, patch
# ---------------------------------------------------------------------------
# BraveFreeSearchProvider unit tests
# ---------------------------------------------------------------------------
class TestBraveFreeProviderIsConfigured:
def test_configured_when_key_set(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
assert BraveFreeSearchProvider().is_configured() is True
def test_not_configured_when_key_missing(self, monkeypatch):
monkeypatch.delenv("BRAVE_SEARCH_API_KEY", raising=False)
from tools.web_providers.brave_free import BraveFreeSearchProvider
assert BraveFreeSearchProvider().is_configured() is False
def test_not_configured_when_key_whitespace(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", " ")
from tools.web_providers.brave_free import BraveFreeSearchProvider
assert BraveFreeSearchProvider().is_configured() is False
def test_provider_name(self):
from tools.web_providers.brave_free import BraveFreeSearchProvider
assert BraveFreeSearchProvider().provider_name() == "brave-free"
def test_implements_web_search_provider(self):
from tools.web_providers.base import WebSearchProvider
from tools.web_providers.brave_free import BraveFreeSearchProvider
assert issubclass(BraveFreeSearchProvider, WebSearchProvider)
class TestBraveFreeProviderSearch:
_SAMPLE_RESPONSE = {
"web": {
"results": [
{"title": "A", "url": "https://a.example.com", "description": "desc A"},
{"title": "B", "url": "https://b.example.com", "description": "desc B"},
{"title": "C", "url": "https://c.example.com", "description": "desc C"},
]
}
}
@staticmethod
def _mock_resp(json_data, status_code=200):
m = MagicMock()
m.status_code = status_code
m.json.return_value = json_data
m.raise_for_status = MagicMock()
return m
def test_happy_path_normalizes_results(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
with patch("httpx.get", return_value=self._mock_resp(self._SAMPLE_RESPONSE)):
result = BraveFreeSearchProvider().search("test query", 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_sends_subscription_token_header_and_count(self, monkeypatch):
"""Brave uses X-Subscription-Token; count maps from limit."""
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
captured = {}
def fake_get(url, **kwargs):
captured["url"] = url
captured["headers"] = kwargs.get("headers", {})
captured["params"] = kwargs.get("params", {})
return self._mock_resp({"web": {"results": []}})
with patch("httpx.get", side_effect=fake_get):
BraveFreeSearchProvider().search("q", limit=5)
assert captured["url"] == "https://api.search.brave.com/res/v1/web/search"
assert captured["headers"].get("X-Subscription-Token") == "BSAkey123"
assert captured["params"].get("q") == "q"
assert captured["params"].get("count") == 5
def test_count_is_capped_at_20(self, monkeypatch):
"""Brave caps count at 20 — limit above that clamps."""
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
captured = {}
def fake_get(url, **kwargs):
captured["params"] = kwargs.get("params", {})
return self._mock_resp({"web": {"results": []}})
with patch("httpx.get", side_effect=fake_get):
BraveFreeSearchProvider().search("q", limit=100)
assert captured["params"].get("count") == 20
def test_limit_is_respected_client_side(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
with patch("httpx.get", return_value=self._mock_resp(self._SAMPLE_RESPONSE)):
result = BraveFreeSearchProvider().search("q", limit=2)
assert result["success"] is True
assert len(result["data"]["web"]) == 2
def test_empty_results(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
with patch("httpx.get", return_value=self._mock_resp({"web": {"results": []}})):
result = BraveFreeSearchProvider().search("nothing", limit=5)
assert result["success"] is True
assert result["data"]["web"] == []
def test_missing_web_key_returns_empty(self, monkeypatch):
"""Responses without a ``web`` block should produce an empty result set, not crash."""
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
with patch("httpx.get", return_value=self._mock_resp({})):
result = BraveFreeSearchProvider().search("q", limit=5)
assert result["success"] is True
assert result["data"]["web"] == []
def test_http_error_returns_failure(self, monkeypatch):
import httpx
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
bad = MagicMock()
bad.status_code = 429
err = httpx.HTTPStatusError("429", request=MagicMock(), response=bad)
with patch("httpx.get", side_effect=err):
result = BraveFreeSearchProvider().search("q", limit=5)
assert result["success"] is False
assert "429" in result["error"]
def test_request_error_returns_failure(self, monkeypatch):
import httpx
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_providers.brave_free import BraveFreeSearchProvider
with patch("httpx.get", side_effect=httpx.RequestError("boom")):
result = BraveFreeSearchProvider().search("q", limit=5)
assert result["success"] is False
assert "boom" in result["error"] or "Brave" in result["error"]
def test_missing_key_returns_failure(self, monkeypatch):
monkeypatch.delenv("BRAVE_SEARCH_API_KEY", raising=False)
from tools.web_providers.brave_free import BraveFreeSearchProvider
result = BraveFreeSearchProvider().search("q", limit=5)
assert result["success"] is False
assert "BRAVE_SEARCH_API_KEY" in result["error"]
# ---------------------------------------------------------------------------
# Integration: _is_backend_available / _get_backend / check_web_api_key
# ---------------------------------------------------------------------------
class TestBraveFreeBackendWiring:
def test_is_backend_available_true_when_key_set(self, monkeypatch):
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
from tools.web_tools import _is_backend_available
assert _is_backend_available("brave-free") is True
def test_is_backend_available_false_when_key_missing(self, monkeypatch):
monkeypatch.delenv("BRAVE_SEARCH_API_KEY", raising=False)
from tools.web_tools import _is_backend_available
assert _is_backend_available("brave-free") is False
def test_configured_backend_accepted(self, monkeypatch):
from tools import web_tools
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "brave-free"})
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
assert web_tools._get_backend() == "brave-free"
def test_auto_detect_picks_brave_free_when_only_key_set(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"):
monkeypatch.delenv(key, raising=False)
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
monkeypatch.setattr(web_tools, "_ddgs_package_importable", lambda: False)
assert web_tools._get_backend() == "brave-free"
def test_brave_free_does_not_override_paid_provider(self, monkeypatch):
"""Tavily (higher priority) should win 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", "EXA_API_KEY", "SEARXNG_URL"):
monkeypatch.delenv(key, raising=False)
monkeypatch.setenv("TAVILY_API_KEY", "tvly")
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
assert web_tools._get_backend() == "tavily"
def test_check_web_api_key_true_when_brave_free_configured(self, monkeypatch):
from tools import web_tools
monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "brave-free"})
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
assert web_tools.check_web_api_key() is True
# ---------------------------------------------------------------------------
# brave-free is search-only: web_extract / web_crawl return clear errors
# ---------------------------------------------------------------------------
class TestBraveFreeSearchOnlyErrors:
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": "brave-free"})
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
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 "brave" 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": "brave-free"})
monkeypatch.setenv("BRAVE_SEARCH_API_KEY", "BSAkey123")
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 "brave" in result["error"].lower()

View file

@ -0,0 +1,246 @@
"""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()