feat(web): add web search provider registry mirroring image_gen pattern

This commit is contained in:
kshitijk4poor 2026-05-13 22:55:27 +05:30 committed by Teknium
parent 2cea98e143
commit 007a630b16

View file

@ -0,0 +1,178 @@
"""
Web Search Provider Registry
============================
Central map of registered web providers. Populated by plugins at import-time
via :meth:`PluginContext.register_web_search_provider`; consumed by the
``web_search`` and ``web_extract`` tool wrappers in :mod:`tools.web_tools` to
dispatch each call to the active backend.
Active selection
----------------
The active provider is chosen by configuration with this precedence:
1. ``web.search_backend`` (for search) or ``web.extract_backend`` (for extract)
2. ``web.backend`` (shared fallback)
3. If exactly one capability-eligible provider is registered, use it.
4. Legacy preference order (``brave-free`` ``firecrawl`` ``searxng`` ``ddgs``)
so installs that omitted the config key keep working.
5. Otherwise ``None`` the tool surfaces a helpful error pointing at
``hermes tools``.
The capability filter (``supports_search`` vs ``supports_extract``) is applied
at every step so a search-only provider (``brave-free``) configured as
``web.extract_backend`` correctly falls through.
"""
from __future__ import annotations
import logging
import threading
from typing import Dict, List, Optional
from agent.web_search_provider import WebSearchProvider
logger = logging.getLogger(__name__)
_providers: Dict[str, WebSearchProvider] = {}
_lock = threading.Lock()
def register_provider(provider: WebSearchProvider) -> None:
"""Register a web search/extract provider.
Re-registration (same ``name``) overwrites the previous entry and logs
a debug message makes hot-reload scenarios (tests, dev loops) behave
predictably.
"""
if not isinstance(provider, WebSearchProvider):
raise TypeError(
f"register_provider() expects a WebSearchProvider instance, "
f"got {type(provider).__name__}"
)
name = provider.name
if not isinstance(name, str) or not name.strip():
raise ValueError("Web provider .name must be a non-empty string")
with _lock:
existing = _providers.get(name)
_providers[name] = provider
if existing is not None:
logger.debug(
"Web provider '%s' re-registered (was %r)",
name, type(existing).__name__,
)
else:
logger.debug(
"Registered web provider '%s' (%s)",
name, type(provider).__name__,
)
def list_providers() -> List[WebSearchProvider]:
"""Return all registered providers, sorted by name."""
with _lock:
items = list(_providers.values())
return sorted(items, key=lambda p: p.name)
def get_provider(name: str) -> Optional[WebSearchProvider]:
"""Return the provider registered under *name*, or None."""
if not isinstance(name, str):
return None
with _lock:
return _providers.get(name.strip())
# ---------------------------------------------------------------------------
# Active-provider resolution
# ---------------------------------------------------------------------------
def _read_config_key(*path: str) -> Optional[str]:
"""Resolve a dotted config key from ``config.yaml``. Returns None on miss."""
try:
from hermes_cli.config import load_config
cfg = load_config()
cur = cfg
for segment in path:
if not isinstance(cur, dict):
return None
cur = cur.get(segment)
if isinstance(cur, str) and cur.strip():
return cur.strip()
except Exception as exc:
logger.debug("Could not read config %s: %s", ".".join(path), exc)
return None
# Legacy preference order — preserves behaviour for users who set no config
# at all. brave-free first because it was the shipped default after the
# Brave migration; firecrawl second for back-compat with older configs.
_LEGACY_PREFERENCE = ("brave-free", "firecrawl", "searxng", "ddgs")
def _resolve(configured: Optional[str], *, capability: str) -> Optional[WebSearchProvider]:
"""Resolve the active provider for a capability ("search" | "extract")."""
with _lock:
snapshot = dict(_providers)
def _capable(p: WebSearchProvider) -> bool:
if capability == "search":
return bool(p.supports_search())
if capability == "extract":
return bool(p.supports_extract())
return False
if configured:
provider = snapshot.get(configured)
if provider is not None and _capable(provider):
return provider
if provider is None:
logger.debug(
"web backend '%s' configured but not registered; falling back",
configured,
)
else:
logger.debug(
"web backend '%s' configured but does not support '%s'; falling back",
configured, capability,
)
eligible = [p for p in snapshot.values() if _capable(p)]
if len(eligible) == 1:
return eligible[0]
for legacy in _LEGACY_PREFERENCE:
provider = snapshot.get(legacy)
if provider is not None and _capable(provider):
return provider
return None
def get_active_search_provider() -> Optional[WebSearchProvider]:
"""Resolve the currently-active web search provider.
Reads ``web.search_backend`` (preferred) or ``web.backend`` (shared
fallback) from config.yaml; falls back per the module docstring.
"""
explicit = _read_config_key("web", "search_backend") or _read_config_key("web", "backend")
return _resolve(explicit, capability="search")
def get_active_extract_provider() -> Optional[WebSearchProvider]:
"""Resolve the currently-active web extract provider.
Reads ``web.extract_backend`` (preferred) or ``web.backend`` (shared
fallback) from config.yaml; falls back per the module docstring.
"""
explicit = _read_config_key("web", "extract_backend") or _read_config_key("web", "backend")
return _resolve(explicit, capability="extract")
def _reset_for_tests() -> None:
"""Clear the registry. **Test-only.**"""
with _lock:
_providers.clear()