refactor(web): delete legacy tools/web_providers/ directory + migrate ABC tests

Removes the legacy in-tree provider scaffolding that PR #25182 fully
replaced with the plugin architecture:

  tools/web_providers/__init__.py        (6 lines)
  tools/web_providers/base.py            (89 lines — old ABCs)
  tools/web_providers/ARCHITECTURE.md    (73 lines — old design doc)

These were the staging-ground ABCs and provider modules that the
plugin migration absorbed. All seven web providers now implement the
single :class:`agent.web_search_provider.WebSearchProvider` ABC and
live under ``plugins/web/<vendor>/``. Nothing else in the tree imports
``tools.web_providers`` — verified via grep before deletion.

Test migration (tests/tools/test_web_providers.py)
--------------------------------------------------
Rewrote ``TestWebProviderABCs`` to test the new unified ABC at
:mod:`agent.web_search_provider`:

  - test_cannot_instantiate_abc_directly — abstract ``name`` + ``is_available``
  - test_concrete_search_only_provider_works — exercise default
    ``supports_extract=False`` / ``supports_crawl=False`` flags
  - test_concrete_multi_capability_provider_works — exercise all three
    capabilities, async extract supported (declared sync here for
    simplicity; real plugins like parallel + firecrawl use async)
  - test_search_only_provider_skips_extract_and_crawl — verify
    ``supports_*()`` flags default to False so search-only providers
    don't have to implement extract() or crawl()

The 9 other tests in the file (per-capability backend selection,
DEFAULT_CONFIG merge, dispatcher routing) test public helpers in
``tools.web_tools`` that still exist and pass unchanged.

agent/web_search_provider.py docstring updated to reflect that the
legacy ABCs no longer exist; the response-shape contract is preserved
bit-for-bit so external consumers see no behavioral change.

Net diff
--------
- tools/web_providers/ removed (-168 lines)
- tests/tools/test_web_providers.py rewritten ABC section (+78/-30 net,
  same coverage, new API)
- agent/web_search_provider.py docstring (-3/+5 lines)

Verified
--------
- 173/173 targeted web tests pass
- 12/12 ABC contract tests pass with the new interface
- No remaining grep hits for ``tools.web_providers`` outside of
  intentional historical references in plugin docstrings.
This commit is contained in:
kshitijk4poor 2026-05-14 00:56:11 +05:30 committed by Teknium
parent 24fe60faa2
commit 39b4ebfcea
5 changed files with 102 additions and 198 deletions

View file

@ -20,50 +20,121 @@ import pytest
class TestWebProviderABCs:
"""The ABCs enforce the interface contract."""
"""The unified WebSearchProvider ABC enforces the interface contract.
def test_cannot_instantiate_search_provider(self):
from tools.web_providers.base import WebSearchProvider
After PR #25182, all seven providers are subclasses of
:class:`agent.web_search_provider.WebSearchProvider`. The legacy
in-tree ABCs at ``tools.web_providers.base`` (separate
``WebSearchProvider`` + ``WebExtractProvider``) were deleted in the
same PR providers now advertise capabilities via
``supports_search() / supports_extract() / supports_crawl()`` flags.
"""
def test_cannot_instantiate_abc_directly(self):
from agent.web_search_provider import WebSearchProvider
with pytest.raises(TypeError):
WebSearchProvider() # type: ignore[abstract]
def test_cannot_instantiate_extract_provider(self):
from tools.web_providers.base import WebExtractProvider
with pytest.raises(TypeError):
WebExtractProvider() # type: ignore[abstract]
def test_concrete_search_provider_works(self):
from tools.web_providers.base import WebSearchProvider
def test_concrete_search_only_provider_works(self):
from agent.web_search_provider import WebSearchProvider
class Dummy(WebSearchProvider):
def provider_name(self) -> str:
@property
def name(self) -> str:
return "dummy"
def is_configured(self) -> bool:
@property
def display_name(self) -> str:
return "Dummy Search"
def is_available(self) -> bool:
return True
def supports_search(self) -> bool:
return True
def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
return {"success": True, "data": {"web": []}}
d = Dummy()
assert d.provider_name() == "dummy"
assert d.is_configured() is True
assert d.name == "dummy"
assert d.display_name == "Dummy Search"
assert d.is_available() is True
assert d.supports_search() is True
assert d.supports_extract() is False # default
assert d.supports_crawl() is False # default
assert d.search("test")["success"] is True
def test_concrete_extract_provider_works(self):
from tools.web_providers.base import WebExtractProvider
def test_concrete_multi_capability_provider_works(self):
from agent.web_search_provider import WebSearchProvider
class Dummy(WebExtractProvider):
def provider_name(self) -> str:
class Dummy(WebSearchProvider):
@property
def name(self) -> str:
return "dummy"
def is_configured(self) -> bool:
@property
def display_name(self) -> str:
return "Dummy Multi"
def is_available(self) -> bool:
return True
def extract(self, urls: List[str], **kwargs) -> Dict[str, Any]:
return {"success": True, "data": [{"url": urls[0], "content": "x"}]}
def supports_search(self) -> bool:
return True
def supports_extract(self) -> bool:
return True
def supports_crawl(self) -> bool:
return True
def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
return {"success": True, "data": {"web": []}}
def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
return [{"url": urls[0], "content": "x"}]
def crawl(self, url: str, **kwargs: Any) -> Dict[str, Any]:
return {"results": [{"url": url, "content": "x"}]}
d = Dummy()
assert d.provider_name() == "dummy"
assert d.extract(["https://example.com"])["success"] is True
assert d.supports_search() is True
assert d.supports_extract() is True
assert d.supports_crawl() is True
assert d.extract(["https://example.com"])[0]["url"] == "https://example.com"
assert d.crawl("https://example.com")["results"][0]["url"] == "https://example.com"
def test_search_only_provider_skips_extract_and_crawl(self):
"""Search-only providers don't have to implement extract() / crawl()."""
from agent.web_search_provider import WebSearchProvider
class SearchOnly(WebSearchProvider):
@property
def name(self) -> str:
return "search-only"
@property
def display_name(self) -> str:
return "Search Only"
def is_available(self) -> bool:
return True
def supports_search(self) -> bool:
return True
def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
return {"success": True, "data": {"web": []}}
# Should instantiate fine — extract/crawl have default
# supports_*() returning False and aren't required to be
# overridden when not advertised.
s = SearchOnly()
assert s.supports_search() is True
assert s.supports_extract() is False
assert s.supports_crawl() is False
# ---------------------------------------------------------------------------