mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-25 05:52:34 +00:00
feat(web): extend ABC with supports_crawl and async-extract semantics
Two ABC additions to cover the surface area of the remaining four providers (exa, parallel, tavily, firecrawl) which were untouched by the initial spike: 1. supports_crawl() + crawl() — Tavily natively crawls a seed URL via its /crawl endpoint. Exposing supports_crawl=True lets the crawl tool's dispatcher route to Tavily when configured, falling back to the auxiliary-model summarization path otherwise. Firecrawl could add this in a follow-up (the SDK supports it; we just don't surface it as a tool today). 2. Async-or-sync extract() — Parallel's SDK is natively async (AsyncParallel.beta.extract); Exa and Tavily are sync; Firecrawl is sync but called inside asyncio.to_thread() with a 60s timeout. The ABC docstring now permits either shape: implementations declare their own sync/async signature and the dispatcher uses inspect.iscoroutinefunction to detect and await. Also adds get_active_crawl_provider() to web_search_registry mirroring the search/extract resolvers, with web.crawl_backend as the explicit override config key. No behavior change on its own — these are scaffolds for the four remaining provider migrations.
This commit is contained in:
parent
0a7cbd3342
commit
e3f0a88891
2 changed files with 84 additions and 4 deletions
|
|
@ -114,7 +114,7 @@ _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").
|
||||
"""Resolve the active provider for a capability ("search" | "extract" | "crawl").
|
||||
|
||||
Resolution rules (in order):
|
||||
|
||||
|
|
@ -147,6 +147,8 @@ def _resolve(configured: Optional[str], *, capability: str) -> Optional[WebSearc
|
|||
return bool(p.supports_search())
|
||||
if capability == "extract":
|
||||
return bool(p.supports_extract())
|
||||
if capability == "crawl":
|
||||
return bool(p.supports_crawl())
|
||||
return False
|
||||
|
||||
def _is_available_safe(p: WebSearchProvider) -> bool:
|
||||
|
|
@ -218,6 +220,20 @@ def get_active_extract_provider() -> Optional[WebSearchProvider]:
|
|||
return _resolve(explicit, capability="extract")
|
||||
|
||||
|
||||
def get_active_crawl_provider() -> Optional[WebSearchProvider]:
|
||||
"""Resolve the currently-active web crawl provider.
|
||||
|
||||
Reads ``web.crawl_backend`` (preferred) or ``web.backend`` (shared
|
||||
fallback) from config.yaml; falls back per the module docstring.
|
||||
|
||||
Crawl is a niche capability — only Tavily implements it among built-in
|
||||
providers. Most callers should expect ``None`` and fall back to a
|
||||
different strategy (e.g. summarize-via-LLM).
|
||||
"""
|
||||
explicit = _read_config_key("web", "crawl_backend") or _read_config_key("web", "backend")
|
||||
return _resolve(explicit, capability="crawl")
|
||||
|
||||
|
||||
def _reset_for_tests() -> None:
|
||||
"""Clear the registry. **Test-only.**"""
|
||||
with _lock:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue