refactor(web): remove legacy in-tree provider modules

Deletes tools/web_providers/{brave_free,ddgs,searxng}.py — the three
providers that moved to plugins/web/ in prior commits. tools/web_tools.py
no longer imports them (registry dispatch as of d8735963f), so removing
them is purely a cleanup pass.

Also migrates the existing tests to the new import paths:
  tests/tools/test_web_providers_brave_free.py
  tests/tools/test_web_providers_ddgs.py
  tests/tools/test_web_providers_searxng.py

Mechanical rewrites:
  - `from tools.web_providers.X import YSearchProvider`
      -> `from plugins.web.X.provider import YWebSearchProvider`
  - `.is_configured()` -> `.is_available()`        (legacy method  -> new method)
  - `.provider_name()` -> `.name`                  (legacy method  -> new property)
  - `from tools.web_providers.base import WebSearchProvider`
      -> `from agent.web_search_provider import WebSearchProvider`
      (the subclass-check asserts membership in the new plugin-facing ABC)
  - `sys.modules.delitem("tools.web_providers.ddgs")` updated to point at
    `plugins.web.ddgs.provider` (cache-busting for lazy ddgs imports)

The TestXBackendWiring / TestXSearchOnlyErrors classes (covering
_is_backend_available, _get_backend, check_web_api_key, and the
"search-only" error paths in web_extract/web_crawl) are untouched —
those still test web_tools.py's backend-selection logic, which continues
to recognize the names "brave-free" / "ddgs" / "searxng" even after the
modules behind them moved to plugins.

tools/web_providers/base.py is intentionally NOT deleted by this commit
— it's the parent ABC of the legacy modules and shares its name with
agent/web_search_provider.py::WebSearchProvider. Removing it surfaces the
naming collision (see PR description Finding 0); the real migration PR
deletes it in the same commit that drops the _WEB_PLUGIN_SKIPLIST
guards in hermes_cli/tools_config.py.

Test results:
  bash scripts/run_tests.sh tests/tools/test_web_providers_*.py
  -> 65 passed in 3.41s (all rewritten unit tests + unchanged integration tests)
  bash scripts/run_tests.sh tests/tools/test_web_*.py
  -> 141 passed in 4.70s (full web test set, post-deletion)
This commit is contained in:
kshitijk4poor 2026-05-13 23:52:02 +05:30 committed by Teknium
parent 714630110b
commit 6b219f5af6
9 changed files with 105 additions and 462 deletions

View file

@ -1,8 +1,8 @@
"""Tests for the SearXNG web search provider.
Covers:
- SearXNGSearchProvider.is_configured() env var gating
- SearXNGSearchProvider.search() happy path, HTTP error, request error, bad JSON
- SearXNGWebSearchProvider.is_available() env var gating
- SearXNGWebSearchProvider.search() happy path, HTTP error, request error, bad JSON
- Result normalization (title, url, description, position)
- Score-based sorting and limit truncation
- _is_backend_available("searxng") integration
@ -19,38 +19,38 @@ import pytest
# ---------------------------------------------------------------------------
# SearXNGSearchProvider unit tests
# SearXNGWebSearchProvider unit tests
# ---------------------------------------------------------------------------
class TestSearXNGSearchProviderIsConfigured:
def test_configured_when_url_set(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
assert SearXNGSearchProvider().is_configured() is True
from plugins.web.searxng.provider import SearXNGWebSearchProvider
assert SearXNGWebSearchProvider().is_available() is True
def test_not_configured_when_url_missing(self, monkeypatch):
monkeypatch.delenv("SEARXNG_URL", raising=False)
from tools.web_providers.searxng import SearXNGSearchProvider
assert SearXNGSearchProvider().is_configured() is False
from plugins.web.searxng.provider import SearXNGWebSearchProvider
assert SearXNGWebSearchProvider().is_available() is False
def test_not_configured_when_url_empty_string(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", " ")
from tools.web_providers.searxng import SearXNGSearchProvider
assert SearXNGSearchProvider().is_configured() is False
from plugins.web.searxng.provider import SearXNGWebSearchProvider
assert SearXNGWebSearchProvider().is_available() is False
def test_provider_name(self):
from tools.web_providers.searxng import SearXNGSearchProvider
assert SearXNGSearchProvider().provider_name() == "searxng"
from plugins.web.searxng.provider import SearXNGWebSearchProvider
assert SearXNGWebSearchProvider().name == "searxng"
def test_implements_web_search_provider(self):
from tools.web_providers.base import WebSearchProvider
from tools.web_providers.searxng import SearXNGSearchProvider
assert issubclass(SearXNGSearchProvider, WebSearchProvider)
from agent.web_search_provider import WebSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
assert issubclass(SearXNGWebSearchProvider, WebSearchProvider)
class TestSearXNGSearchProviderSearch:
"""Happy path and error handling for SearXNGSearchProvider.search()."""
"""Happy path and error handling for SearXNGWebSearchProvider.search()."""
_SAMPLE_RESPONSE = {
"results": [
@ -69,11 +69,11 @@ class TestSearXNGSearchProviderSearch:
def test_happy_path_returns_normalized_results(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("test query", limit=5)
result = SearXNGWebSearchProvider().search("test query", limit=5)
assert result["success"] is True
web = result["data"]["web"]
@ -86,7 +86,7 @@ class TestSearXNGSearchProviderSearch:
def test_results_sorted_by_score_descending(self, monkeypatch):
"""Results should be sorted by score before limit is applied."""
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
unordered = {
"results": [
{"title": "Low", "url": "https://low.example.com", "content": "", "score": 0.1},
@ -97,7 +97,7 @@ class TestSearXNGSearchProviderSearch:
mock_resp = self._make_mock_response(unordered)
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
assert result["success"] is True
assert result["data"]["web"][0]["title"] == "High"
@ -106,33 +106,33 @@ class TestSearXNGSearchProviderSearch:
def test_limit_is_respected(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("query", limit=2)
result = SearXNGWebSearchProvider().search("query", limit=2)
assert result["success"] is True
assert len(result["data"]["web"]) == 2
def test_position_is_one_indexed(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
positions = [r["position"] for r in result["data"]["web"]]
assert positions == [1, 2, 3]
def test_empty_results(self, monkeypatch):
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = self._make_mock_response({"results": []})
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("nothing", limit=5)
result = SearXNGWebSearchProvider().search("nothing", limit=5)
assert result["success"] is True
assert result["data"]["web"] == []
@ -140,7 +140,7 @@ class TestSearXNGSearchProviderSearch:
def test_missing_score_falls_back_to_zero(self, monkeypatch):
"""Results without a score field should sort to the bottom."""
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
data = {
"results": [
{"title": "No score", "url": "https://noscore.example.com", "content": ""},
@ -150,7 +150,7 @@ class TestSearXNGSearchProviderSearch:
mock_resp = self._make_mock_response(data)
with patch("httpx.get", return_value=mock_resp):
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
assert result["success"] is True
# Has score should sort first (0.8 > 0)
@ -159,14 +159,14 @@ class TestSearXNGSearchProviderSearch:
def test_http_error_returns_failure(self, monkeypatch):
import httpx
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = MagicMock()
mock_resp.status_code = 500
http_err = httpx.HTTPStatusError("500", request=MagicMock(), response=mock_resp)
with patch("httpx.get", side_effect=http_err):
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
assert result["success"] is False
assert "500" in result["error"]
@ -174,26 +174,26 @@ class TestSearXNGSearchProviderSearch:
def test_request_error_returns_failure(self, monkeypatch):
import httpx
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
with patch("httpx.get", side_effect=httpx.RequestError("connection refused")):
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
assert result["success"] is False
assert "localhost:8080" in result["error"] or "connection" in result["error"].lower()
def test_missing_url_returns_failure(self, monkeypatch):
monkeypatch.delenv("SEARXNG_URL", raising=False)
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
result = SearXNGSearchProvider().search("query", limit=5)
result = SearXNGWebSearchProvider().search("query", limit=5)
assert result["success"] is False
assert "SEARXNG_URL" in result["error"]
def test_trailing_slash_stripped_from_url(self, monkeypatch):
"""Base URL trailing slash should not produce double-slash in endpoint."""
monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080/")
from tools.web_providers.searxng import SearXNGSearchProvider
from plugins.web.searxng.provider import SearXNGWebSearchProvider
mock_resp = self._make_mock_response({"results": []})
calls = []
@ -202,7 +202,7 @@ class TestSearXNGSearchProviderSearch:
return mock_resp
with patch("httpx.get", side_effect=capture_get):
SearXNGSearchProvider().search("query", limit=5)
SearXNGWebSearchProvider().search("query", limit=5)
assert calls[0] == "http://localhost:8080/search", f"Got: {calls[0]}"