3861f1da62
Desktop's web picker had no way to send one capability through the Nous Tool Gateway while the other used your own key. "Use for Search/Extract" on the Nous Subscription row wrote the row's vendor string (firecrawl) into web.<cap>_backend, which the runtime reads as BYOK Firecrawl: the gateway was never used, and the managed and BYOK rows lit up together. - The managed per-capability pick now stores `nous`; search/extract dispatch, the registry and the Firecrawl client resolve the route per capability (search: managed Perplexity, extract: managed Firecrawl). - A whole-toolset Nous pick clears stale per-capability pins (they outranked the new selection). - /api/tools/toolsets/web/config reports search_via_nous / extract_via_nous and each row's managed_nous_feature; the panel lights the right row, labels the route, and refetches after a pick instead of mirroring the vendor string. Fixes #100513. Builds on the approach in #100539 by @liuhao1024 and the self-healing pin clear from #122676 by @praggybuilds. Co-authored-by: liuhao1024 <sunsky.lau@gmail.com> Co-authored-by: Murphy (praggybuilds) <praggybuilds@users.noreply.github.com>
574 lines
29 KiB
Python
574 lines
29 KiB
Python
#!/usr/bin/env python3
|
|
"""Generic web_search / web_extract tools over pluggable backends.
|
|
|
|
Backend is selected during ``hermes tools`` (``web.backend`` in config.yaml; per
|
|
capability via ``web.search_backend`` / ``web.extract_backend``). Every vendor
|
|
implementation lives in ``plugins/web/<vendor>/provider.py`` and registers with
|
|
``agent.web_search_registry``; this module owns selection, safety gates,
|
|
caching, keyless rescue, and the truncate-and-store result pipeline.
|
|
Debug: ``WEB_TOOLS_DEBUG=true`` writes ``logs/web_tools_debug_<UUID>.json``.
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
import os
|
|
from typing import List, Any, Optional
|
|
# Per-vendor client cache slots; plugins read/write these via tools.web_tools (tests reset them to None).
|
|
_firecrawl_client = _firecrawl_client_config = _parallel_client = _async_parallel_client = _exa_client = None
|
|
|
|
from plugins.web.firecrawl.provider import _is_tool_gateway_ready, check_firecrawl_api_key
|
|
from tools.debug_helpers import DebugSession
|
|
from tools.tool_backend_helpers import NOUS_MANAGED_PROVIDER, read_selection, selection_exists
|
|
from tools.url_safety import async_is_safe_url
|
|
from tools.web_tools_rescue import _managed_search_fallback, _rescue_eligible, _rescue_search
|
|
from tools.web_tools_truncate import _effective_char_limit, _trim_results, _truncate_results, convert_base64_images_to_links
|
|
from tools.web_tools_extract import (
|
|
_extract_safe_urls, _merge_in_order, _no_provider_error, _resolve_extract_provider, _result_entry,
|
|
_strict_selection_error, _validate_extract_urls,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
# ─── Backend Selection ────────────────────────────────────────────────────────
|
|
|
|
def _env_value(name: str) -> str:
|
|
"""Resolve ``name`` via the config-aware env layer (``hermes config set`` values), then process env.
|
|
|
|
Mirrors the SearXNG provider's ``_searxng_url()`` so that values set through Hermes' config/.env layer
|
|
(``hermes config set``, ``hermes tools``) are honored here too — not just raw process-env exports.
|
|
Without this, a config-only ``SEARXNG_URL`` (or any provider key) leaves the backend auto-detect cascade
|
|
and ``check_web_api_key()`` blind to it. See #34290.
|
|
"""
|
|
try:
|
|
from hermes_cli.config import get_env_value
|
|
val = get_env_value(name)
|
|
except Exception:
|
|
val = None
|
|
return ((os.getenv(name, "") if val is None else val) or "").strip()
|
|
|
|
|
|
def _has_env(name: str) -> bool:
|
|
return bool(_env_value(name))
|
|
|
|
|
|
def _load_web_config() -> dict:
|
|
"""Load the ``web:`` section from config.yaml; always a dict (a null section yields ``{}``)."""
|
|
try:
|
|
from hermes_cli.config import load_config
|
|
return load_config().get("web") or {}
|
|
except Exception:
|
|
return {}
|
|
|
|
|
|
def _configured_backend(key: str = "backend") -> str:
|
|
"""Lower-cased, stripped ``web.<key>`` value ("" when unset/null)."""
|
|
return (_load_web_config().get(key) or "").lower().strip()
|
|
|
|
|
|
def _registry_call(func_name: str, default, *args):
|
|
"""``agent.web_search_registry.<func_name>(*args)``, or *default* if it raised (registry never fatal)."""
|
|
try:
|
|
import agent.web_search_registry as registry_mod
|
|
return getattr(registry_mod, func_name)(*args)
|
|
except Exception as exc: # noqa: BLE001 — registry optional; never fatal
|
|
logger.debug("web provider registry %s%r failed: %s", func_name, args, exc)
|
|
return default
|
|
|
|
|
|
def _registered_web_provider(backend: str):
|
|
"""Plugin-registered web provider by name, or ``None``."""
|
|
return _registry_call("get_provider", None, backend) if backend else None
|
|
|
|
|
|
def _list_registered_web_providers():
|
|
"""All plugin-registered web providers (empty list on failure)."""
|
|
return _registry_call("list_providers", [])
|
|
|
|
|
|
def _probe(provider, method: str, context: str = "") -> Optional[bool]:
|
|
"""``bool(provider.<method>())``, or ``None`` if it raised (a broken provider is unavailable; *context* is
|
|
appended to the debug log line, e.g. " during readiness check")."""
|
|
try:
|
|
return bool(getattr(provider, method)())
|
|
except Exception as exc: # noqa: BLE001 — a broken provider is "unavailable"
|
|
name = getattr(provider, "name", provider)
|
|
logger.debug("web provider %r.%s() raised%s: %s", name, method, context, exc)
|
|
return None
|
|
|
|
|
|
def _get_backend() -> str:
|
|
"""Shared web backend name. A stored ``web.backend`` is returned as-is — no availability probe, no
|
|
fallback — so a broken selection surfaces the vendor's honest error rather than silently rerouting.
|
|
The managed ``use_gateway`` selection also resolves to firecrawl with no ladder. Autodetect runs
|
|
whenever no SHARED web selection was ever stored: per-capability keys (``web.search_backend``,
|
|
``web.extract_backend``) name only their own capability and never reroute the other (#113017)."""
|
|
configured = _configured_backend()
|
|
if configured:
|
|
# "nous" (managed subscription) is serviced by firecrawl, routed through the managed Tool Gateway.
|
|
return "firecrawl" if configured == NOUS_MANAGED_PROVIDER else configured
|
|
if read_selection("web") is not None:
|
|
# Shared selection exists (use_gateway) but no shared name: firecrawl, no ladder.
|
|
return "firecrawl"
|
|
|
|
# Never-configured install.
|
|
return _autodetect_backend() or _keyless_backend() or "firecrawl" # default (backward compat)
|
|
|
|
|
|
def _autodetect_backend() -> Optional[str]:
|
|
"""Autodetect rungs above the keyless tier, or None. Explicit user credentials beat the managed-gateway
|
|
probe (a Nous OAuth token's tier may not grant web access; the gateway then fails at runtime with no
|
|
fallback). Free tiers trail paid."""
|
|
backend_candidates = (
|
|
("tavily", _has_env("TAVILY_API_KEY")), ("perplexity", _has_env("PERPLEXITY_API_KEY")),
|
|
("exa", _has_env("EXA_API_KEY")),
|
|
("parallel", _has_env("PARALLEL_API_KEY")), ("keenable", _has_env("KEENABLE_API_KEY")),
|
|
("firecrawl", _has_env("FIRECRAWL_API_KEY") or _has_env("FIRECRAWL_API_URL")),
|
|
("firecrawl", _is_tool_gateway_ready()), ("searxng", _has_env("SEARXNG_URL")),
|
|
("brave-free", _has_env("BRAVE_SEARCH_API_KEY")), ("ddgs", _ddgs_package_importable()),
|
|
)
|
|
for backend, available in backend_candidates:
|
|
if available:
|
|
return backend
|
|
|
|
# Plugin-contributed providers (built-ins are covered above); probe the held object directly.
|
|
for provider in _list_registered_web_providers():
|
|
if provider.name not in _LEGACY_WEB_BACKENDS and _probe(provider, "is_available"):
|
|
return provider.name
|
|
return None
|
|
|
|
|
|
def _keyless_backend() -> Optional[str]:
|
|
"""Keyless free-tier backend name, or None. Strictly the last autodetect rung so it never
|
|
pre-empts a keyed backend. Discovery must run first: reachable from contexts that haven't
|
|
loaded plugins (subprocess runs, delegate children)."""
|
|
try:
|
|
_ensure_web_plugins_loaded()
|
|
from agent.web_search_registry import _keyless_preference, _keyless_tier_enabled
|
|
if _keyless_tier_enabled():
|
|
for name in _keyless_preference():
|
|
provider = _registered_web_provider(name)
|
|
if provider is not None and _probe(provider, "is_keyless_available"):
|
|
return name
|
|
except Exception as exc: # noqa: BLE001 — registry optional; never fatal
|
|
logger.debug("keyless fallback walk failed: %s", exc)
|
|
return None
|
|
|
|
|
|
def _managed_web_search() -> bool:
|
|
"""True when web_search is on the managed Nous route: the stored ``nous`` selection (a
|
|
``web.search_backend: nous`` pin, else the shared one), or a never-configured install whose
|
|
autodetect lands on the gateway — the entitled Firecrawl gateway, or free Perplexity fast search
|
|
for any Nous identity when nothing else is configured (search-only: the extract ladder is
|
|
untouched). A stored vendor selection never is."""
|
|
search_pin = _configured_backend("search_backend")
|
|
if search_pin:
|
|
return search_pin == NOUS_MANAGED_PROVIDER
|
|
selected = read_selection("web")
|
|
if selected is not None:
|
|
return selected == NOUS_MANAGED_PROVIDER
|
|
backend = _autodetect_backend()
|
|
if backend == "firecrawl":
|
|
return not (_has_env("FIRECRAWL_API_KEY") or _has_env("FIRECRAWL_API_URL")) and _is_tool_gateway_ready()
|
|
from tools.managed_tool_gateway import peek_nous_access_token, resolve_free_search_gateway
|
|
return backend is None and resolve_free_search_gateway(token_reader=peek_nous_access_token) is not None
|
|
|
|
|
|
def _get_search_backend() -> str:
|
|
"""Backend for web_search: ``web.search_backend`` (strict, no probe) > ``web.backend`` > autodetect.
|
|
The managed Nous route (a ``nous`` pin or shared selection) serves search from Perplexity (extract
|
|
stays on Firecrawl); managed Firecrawl is the per-call fallback, see ``_memoized_search``."""
|
|
pin = _configured_backend("search_backend")
|
|
if pin and pin != NOUS_MANAGED_PROVIDER:
|
|
return pin
|
|
return "perplexity" if _managed_web_search() else _get_backend()
|
|
|
|
|
|
def _get_extract_backend() -> str:
|
|
"""Backend for web_extract: ``web.extract_backend`` (strict, no probe) > ``web.backend`` > autodetect.
|
|
A ``nous`` pin is managed Firecrawl; the client picks the gateway route for that capability."""
|
|
pin = _configured_backend("extract_backend")
|
|
return "firecrawl" if pin == NOUS_MANAGED_PROVIDER else pin or _get_backend()
|
|
|
|
|
|
def _ddgs_package_importable() -> bool:
|
|
"""ddgs is the only backend gated on package presence; single symbol so tests can patch it."""
|
|
try:
|
|
import ddgs # noqa: F401
|
|
return True
|
|
except ImportError:
|
|
return False
|
|
|
|
|
|
def _xai_available() -> bool:
|
|
# Cheap probe only (env var OR auth.json OAuth): resolve_xai_http_credentials() may hit the network.
|
|
try:
|
|
from tools.xai_http import has_xai_credentials
|
|
return has_xai_credentials()
|
|
except Exception:
|
|
return False
|
|
|
|
|
|
# Built-in backends -> cheap availability probes; any other name is a plugin provider resolved via the
|
|
# registry's ``is_available()``. Lambdas so test patches of module-level helpers (_ddgs_package_importable,
|
|
# check_firecrawl_api_key) are honored at call time. ``xai`` is probed via has_xai_credentials(), not a
|
|
# registered provider, though the registry's _LEGACY_PREFERENCE omits it — drop it if xai ever registers.
|
|
_BUILTIN_AVAILABILITY = {
|
|
"exa": lambda: _has_env("EXA_API_KEY"),
|
|
"parallel": lambda: _has_env("PARALLEL_API_KEY"),
|
|
"keenable": lambda: _has_env("KEENABLE_API_KEY"),
|
|
"firecrawl": lambda: check_firecrawl_api_key(),
|
|
"tavily": lambda: _has_env("TAVILY_API_KEY")
|
|
or any(_configured_backend(k) == "tavily" for k in ("backend", "search_backend", "extract_backend")),
|
|
"perplexity": lambda: _has_env("PERPLEXITY_API_KEY") or _managed_web_search(),
|
|
"searxng": lambda: _has_env("SEARXNG_URL"),
|
|
"brave-free": lambda: _has_env("BRAVE_SEARCH_API_KEY"),
|
|
"ddgs": lambda: _ddgs_package_importable(),
|
|
"xai": _xai_available,
|
|
}
|
|
_LEGACY_WEB_BACKENDS = frozenset(_BUILTIN_AVAILABILITY)
|
|
|
|
|
|
def _is_backend_available(backend: str) -> bool:
|
|
"""True when *backend* is usable — the single availability chokepoint. Non-legacy names delegate to the
|
|
registered provider's ``is_available()`` (unregistered names fall through); built-ins use cheap probes.
|
|
|
|
For plugin-registered backends (any name outside :data:`_LEGACY_WEB_BACKENDS`), availability is
|
|
delegated to the provider's ``is_available()`` via the web_search_registry. This is the single
|
|
chokepoint through which ``_get_backend``, ``_get_capability_backend``, and ``check_web_api_key`` all
|
|
resolve availability — fixing custom-provider discovery for every caller at once (issues #28651, #31873,
|
|
#32698). Built-in backends keep their cheap hardcoded probes below.
|
|
"""
|
|
backend = (backend or "").lower().strip()
|
|
provider = None if backend in _LEGACY_WEB_BACKENDS else _registered_web_provider(backend)
|
|
if provider is not None:
|
|
return _probe(provider, "is_available") or False
|
|
probe = _BUILTIN_AVAILABILITY.get(backend)
|
|
return probe() if probe else False
|
|
|
|
|
|
# ─── Firecrawl Client ──────────────────────────────────────────────────────── After PR #25182, the
|
|
# firecrawl client, lazy SDK proxy, dual-auth config resolution, response normalizers, and
|
|
# check_firecrawl_api_key() all live in plugins.web.firecrawl.provider.
|
|
def _web_requires_env() -> list[str]:
|
|
"""Tool-registry metadata env vars for the web backends. Gateway vars are always listed: gating them
|
|
on ``managed_nous_tools_enabled()`` cost a synchronous portal HTTP refresh at every CLI startup.
|
|
Contract: set var -> tool sees it; extras are harmless for the not-logged-in."""
|
|
return [
|
|
"EXA_API_KEY", "PARALLEL_API_KEY", "TAVILY_API_KEY", "PERPLEXITY_API_KEY", "KEENABLE_API_KEY", "FIRECRAWL_API_KEY",
|
|
"FIRECRAWL_API_URL", "FIRECRAWL_GATEWAY_URL", "PERPLEXITY_GATEWAY_URL", "TOOL_GATEWAY_DOMAIN", "TOOL_GATEWAY_SCHEME",
|
|
"TOOL_GATEWAY_USER_TOKEN",
|
|
]
|
|
|
|
_debug = DebugSession("web_tools", env_var="WEB_TOOLS_DEBUG")
|
|
|
|
|
|
# ─── Dispatch ─────────────────────────────────────────────────────────────────
|
|
|
|
# ─── Exa / Parallel inline helpers — moved into plugins ────────────────────── After PR #25182, the exa
|
|
# client + search/extract and parallel client + search/extract helpers all live in their respective plugins:
|
|
# - plugins/web/exa/provider.py - plugins/web/parallel/provider.py Both plugins register through
|
|
# agent.web_search_registry and the dispatchers in this file resolve them via get_active_*_provider().
|
|
def _ensure_web_plugins_loaded() -> None:
|
|
"""Idempotently run plugin discovery so the web registry is populated. Dispatch is reachable from contexts
|
|
that never triggered discovery (subprocess agent runs, delegate children, scripts); without it a
|
|
configured backend yields a misleading "No web ... provider" error.
|
|
|
|
Every bundled web provider (brave-free, ddgs, searxng, exa, parallel, tavily, firecrawl, keenable)
|
|
registers itself via ``plugins/web/<vendor>/__init__.py`` during plugin discovery. Tool dispatch can be
|
|
reached from contexts that haven't already triggered discovery — subprocess agent runs, delegate
|
|
children, standalone scripts, certain test paths — and without it the registry is empty and
|
|
``get_provider('firecrawl')`` returns ``None`` even when the user has ``web.extract_backend: firecrawl``
|
|
configured and ``FIRECRAWL_API_KEY`` set. See #27580.
|
|
"""
|
|
try:
|
|
from hermes_cli.plugins import _ensure_plugins_discovered
|
|
_ensure_plugins_discovered()
|
|
except Exception as exc: # noqa: BLE001
|
|
# Warning, not debug: a broken plugin import is otherwise invisible.
|
|
logger.warning("Web plugin discovery failed (non-fatal): %s", exc)
|
|
|
|
|
|
def _finish_debug(call_name: str, debug_call_data: dict, error_msg: Optional[str] = None) -> Optional[str]:
|
|
"""Log the call into the debug session; with *error_msg*, record it and return its ``tool_error`` envelope."""
|
|
if error_msg is not None:
|
|
logger.debug("%s", error_msg)
|
|
debug_call_data["error"] = error_msg
|
|
_debug.log_call(call_name, debug_call_data)
|
|
_debug.save()
|
|
return None if error_msg is None else tool_error(error_msg)
|
|
|
|
|
|
def web_search_tool(query: str, limit: int = 5) -> str:
|
|
"""Search the web via the configured backend.
|
|
|
|
Returns a JSON string ``{"success": bool, "data": {"web": [{"title", "url", "description", "position"},
|
|
...]}}`` (metadata only — use web_extract_tool for page content) or ``{"success": false, "error": ...}``.
|
|
"""
|
|
try:
|
|
limit = min(max(int(limit), 1), 100)
|
|
except (TypeError, ValueError):
|
|
limit = 5
|
|
debug_call_data = {
|
|
"parameters": {"query": query, "limit": limit}, "error": None, "results_count": 0,
|
|
"original_response_size": 0, "final_response_size": 0,
|
|
}
|
|
|
|
try:
|
|
from tools.interrupt import is_interrupted
|
|
if is_interrupted():
|
|
return tool_error("Interrupted", success=False)
|
|
# Sync only — every provider's search() is sync.
|
|
_ensure_web_plugins_loaded()
|
|
from agent.web_search_registry import get_active_search_provider, get_provider as _wsp_get_provider
|
|
backend = _get_search_backend()
|
|
provider = _wsp_get_provider(backend) if backend else None
|
|
if provider is None or not provider.supports_search():
|
|
if provider is None and backend and selection_exists("web"):
|
|
error_text = debug_call_data["error"] = _strict_selection_error("search", backend)
|
|
_finish_debug("web_search_tool", debug_call_data)
|
|
return json.dumps({"success": False, "error": error_text}, indent=2, ensure_ascii=False)
|
|
# Never-configured install: legacy availability-walked autodetect.
|
|
provider = get_active_search_provider()
|
|
|
|
if provider is None:
|
|
fallback = "No web search provider configured. Run `hermes tools` to set one up."
|
|
response_data = {"success": False, "error": _no_provider_error("search", fallback)}
|
|
else:
|
|
logger.info("Web search via %s: '%s' (limit: %d)", provider.name, query, limit)
|
|
response_data = _memoized_search(provider, query, limit)
|
|
|
|
debug_call_data["results_count"] = len(response_data.get("data", {}).get("web", []))
|
|
result_json = json.dumps(response_data, indent=2, ensure_ascii=False)
|
|
debug_call_data["final_response_size"] = len(result_json)
|
|
_finish_debug("web_search_tool", debug_call_data)
|
|
return result_json
|
|
except Exception as e:
|
|
return _finish_debug("web_search_tool", debug_call_data, f"Error searching web: {str(e)}")
|
|
|
|
|
|
def _memoized_search(provider, query: str, limit: int) -> dict:
|
|
"""TTL memo + single-flight around the paid vendor call (tools/web_result_cache.py); sits after every
|
|
safety/config check. The provider is asked for the BUCKETED count so near-identical limits share an entry;
|
|
the caller's count is sliced out. Only successful, non-rescued responses are cached — caching a rescue
|
|
would make the one-shot ring fallback sticky for a whole TTL."""
|
|
from tools.web_result_cache import bucket_limit, search_memo, slice_search_response
|
|
|
|
def _paid_search() -> tuple[dict, bool]:
|
|
fetch_limit = bucket_limit(limit)
|
|
try:
|
|
resp = provider.search(query, fetch_limit)
|
|
except Exception as exc: # noqa: BLE001 — candidate for fallback / rescue
|
|
served = _served_after_failure(str(exc), fetch_limit)
|
|
if served is None:
|
|
raise
|
|
return served, True
|
|
if not resp.get("success"):
|
|
served = _served_after_failure(str(resp.get("error", "")), fetch_limit)
|
|
if served is not None:
|
|
return served, True
|
|
return resp, False
|
|
|
|
def _served_after_failure(error: str, fetch_limit: int) -> Optional[dict]:
|
|
"""Managed Firecrawl for a failed managed Perplexity call, else the one-shot keyless rescue when
|
|
eligible; None means the vendor's own failure stands."""
|
|
fallback = _managed_search_fallback(provider, error, query, fetch_limit)
|
|
if fallback is not None:
|
|
return fallback
|
|
return _rescue_search(provider.name, error, query, fetch_limit) if _rescue_eligible(provider) else None
|
|
|
|
response_data = search_memo.lookup(provider.name, query, limit)
|
|
if response_data is None:
|
|
with search_memo.flight_lock(provider.name, query, limit):
|
|
# Re-check inside the lock: a concurrent identical call may have stored.
|
|
response_data = search_memo.lookup(provider.name, query, limit)
|
|
if response_data is None:
|
|
response_data, was_rescued = _paid_search()
|
|
if not was_rescued:
|
|
search_memo.store(provider.name, query, limit, response_data)
|
|
return slice_search_response(response_data, limit)
|
|
|
|
|
|
async def web_extract_tool(urls: List[Any], format: str = None, char_limit: Optional[int] = None) -> str:
|
|
"""Extract clean page content (no LLM) from URLs via the configured backend.
|
|
|
|
Pages over ``char_limit`` (default web.extract_char_limit or 15000) are head+tail truncated with a footer
|
|
pointing at the stored full text; inline base64 images become ``[IMAGE: alt]``. URLs carrying secrets are
|
|
refused before any fetch; private-network URLs are blocked per entry. Returns JSON ``{"results": [...]}``.
|
|
"""
|
|
normalized_urls, normalized_indices, invalid_urls, blocked = _validate_extract_urls(urls)
|
|
if blocked is not None:
|
|
return blocked
|
|
debug_call_data = {
|
|
"parameters": {"urls": normalized_urls, "format": format, "char_limit": char_limit}, "error": None,
|
|
"pages_extracted": 0, "pages_truncated": 0, "original_response_size": 0, "final_response_size": 0,
|
|
"truncation_metrics": [], "processing_applied": [],
|
|
}
|
|
|
|
try:
|
|
logger.info("Extracting content from %d URL(s)", len(normalized_urls))
|
|
# SSRF protection — filter private/internal URLs before any backend.
|
|
safe_urls, safe_indices, ssrf_blocked = [], [], {}
|
|
for index, url in zip(normalized_indices, normalized_urls):
|
|
if await async_is_safe_url(url):
|
|
safe_urls.append(url)
|
|
safe_indices.append(index)
|
|
else:
|
|
ssrf_blocked[index] = _result_entry(
|
|
url, "Blocked: URL targets a private or internal network address"
|
|
)
|
|
|
|
results = []
|
|
if safe_urls:
|
|
backend = _get_extract_backend()
|
|
_ensure_web_plugins_loaded()
|
|
provider, error_json = _resolve_extract_provider(backend)
|
|
if error_json is not None:
|
|
return error_json
|
|
results = await _extract_safe_urls(provider, safe_urls, format)
|
|
# Reconstruct input order across invalid, blocked, and provider entries (providers preserve
|
|
# the order of the safe URL list they receive).
|
|
if invalid_urls or ssrf_blocked:
|
|
fixed = {**ssrf_blocked, **invalid_urls}
|
|
results = _merge_in_order(len(urls), fixed, safe_indices, safe_urls, results)
|
|
|
|
logger.info("Extracted content from %d pages", len(results))
|
|
debug_call_data["pages_extracted"] = len(results)
|
|
debug_call_data["original_response_size"] = len(json.dumps({"results": results}))
|
|
debug_call_data["processing_applied"].append("truncate_and_store")
|
|
_truncate_results(results, _effective_char_limit(char_limit), debug_call_data)
|
|
trimmed = _trim_results(results)
|
|
result_json = (
|
|
json.dumps({"results": trimmed}, indent=2, ensure_ascii=False) if trimmed
|
|
else tool_error("Content was inaccessible or not found")
|
|
)
|
|
# Belt-and-suspenders sweep of the serialized JSON: a provider may tuck a base64 blob in metadata.
|
|
cleaned_result = convert_base64_images_to_links(result_json)
|
|
debug_call_data["final_response_size"] = len(cleaned_result)
|
|
debug_call_data["processing_applied"].append("base64_image_conversion")
|
|
_finish_debug("web_extract_tool", debug_call_data)
|
|
return cleaned_result
|
|
except Exception as e:
|
|
return _finish_debug("web_extract_tool", debug_call_data, f"Error extracting content: {str(e)}")
|
|
|
|
|
|
def _provider_is_ready(provider) -> bool:
|
|
"""True when *provider* is keyed-available OR keyless-capable, without raising.
|
|
|
|
``get_active_*_provider()`` returns an explicitly configured backend even when ``is_available()`` is
|
|
False (so dispatch can emit a precise error), so readiness gates (tool check_fn, ``hermes doctor``)
|
|
must probe for real. Keyless mode (Exa/Parallel free tier) is a working state, not a misconfig.
|
|
|
|
See #78412.
|
|
"""
|
|
if provider is None:
|
|
return False
|
|
ready = _probe(provider, "is_available", " during readiness check")
|
|
if ready is None: # broken provider == not ready; don't try the keyless probe
|
|
return False
|
|
return bool(ready or _probe(provider, "is_keyless_available", " during readiness check"))
|
|
|
|
|
|
# Credential probes that back other tools but serve no registered web backend: ``xai`` is
|
|
# probed via has_xai_credentials() for TTS/media only, so it must not light this gate. A
|
|
# stored ``web.backend: xai`` still counts since _get_backend returns a configured
|
|
# selection as-is and dispatch surfaces the honest "unknown provider" error.
|
|
_WEB_CHECK_SKIP = frozenset({"xai"})
|
|
|
|
|
|
def check_web_api_key() -> bool:
|
|
"""``check_fn`` gate for web_search / web_extract: is any web backend available?
|
|
|
|
A plugin-registered provider reporting ``is_available()`` must light the tools up even with no
|
|
built-in credentials; resolution funnels through :func:`_is_backend_available`.
|
|
|
|
See #28651, #31873.
|
|
"""
|
|
# Boolean OR over configured + built-ins — probe order is irrelevant here.
|
|
candidates = ([c for c in (_configured_backend(),) if c]
|
|
+ [b for b in _LEGACY_WEB_BACKENDS if b not in _WEB_CHECK_SKIP])
|
|
if any(_is_backend_available(backend) for backend in candidates):
|
|
return True
|
|
# Plugin path. Discovery must run first: check_fn fires at tool-registration time, before any dispatch.
|
|
try:
|
|
_ensure_web_plugins_loaded()
|
|
from agent.web_search_registry import get_active_search_provider, get_active_extract_provider
|
|
for provider in (get_active_search_provider(), get_active_extract_provider()):
|
|
if provider is not None and getattr(provider, "name", None) in _WEB_CHECK_SKIP:
|
|
# The registry's single-eligible / legacy walk picked a built-in that _get_backend
|
|
# never autodetects (the explicit-config case was handled above): the dispatcher
|
|
# would route to the keyless tier instead, so gate on exactly that.
|
|
if _keyless_backend() is not None:
|
|
return True
|
|
continue
|
|
if _provider_is_ready(provider):
|
|
return True
|
|
return False
|
|
except Exception as exc: # noqa: BLE001 — registry optional; never fatal
|
|
logger.debug("web provider registry availability check failed: %s", exc)
|
|
return False
|
|
|
|
|
|
# ─── Registry ─────────────────────────────────────────────────────────────────
|
|
from tools.registry import registry, tool_error
|
|
|
|
WEB_SEARCH_SCHEMA = {
|
|
"name": "web_search",
|
|
"description": "Search the web for information. Returns up to 5 results by default with titles, URLs, and descriptions. The query is passed through to the configured backend, so operators such as site:domain, filetype:pdf, intitle:word, -term, and \"exact phrase\" may work when the backend supports them.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "The search query to look up on the web. You may include backend-supported operators such as site:example.com, filetype:pdf, intitle:word, -term, or \"exact phrase\"."
|
|
},
|
|
"limit": {
|
|
"type": "integer",
|
|
"description": "Maximum number of results to return. Defaults to 5.",
|
|
"minimum": 1,
|
|
"maximum": 100,
|
|
"default": 5
|
|
}
|
|
},
|
|
"required": ["query"]
|
|
}
|
|
}
|
|
|
|
WEB_EXTRACT_SCHEMA = {
|
|
"name": "web_extract",
|
|
"description": "Extract content from web page URLs. Returns clean page content in markdown/text (no LLM summarization — fast). Also works with PDF URLs (arxiv papers, documents) — pass the PDF link directly. Pages within the char budget (default 15000) return whole; larger pages return a head+tail window with a footer telling you the full text's saved file path and the read_file call to page through the omitted middle. Inline images appear as [IMAGE: alt] placeholders; real image URLs are kept as links. If a URL fails or times out, use the browser tool instead.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"urls": {
|
|
"type": "array",
|
|
"items": {"type": "string"},
|
|
"description": "List of URLs to extract content from (max 5 URLs per call)",
|
|
"maxItems": 5
|
|
},
|
|
"char_limit": {
|
|
"type": "integer",
|
|
"description": "Optional per-page character budget sent back (default 15000). Pages larger than this are head+tail truncated with the full text stored to disk. Raise it when you need more of a long page inline.",
|
|
"minimum": 2000
|
|
}
|
|
},
|
|
"required": ["urls"]
|
|
}
|
|
}
|
|
|
|
registry.register(
|
|
name="web_search", toolset="web", schema=WEB_SEARCH_SCHEMA,
|
|
handler=lambda args, **kw: web_search_tool(args.get("query", ""), limit=args.get("limit", 5)),
|
|
check_fn=check_web_api_key, requires_env=_web_requires_env(), emoji="🔍",
|
|
max_result_size_chars=100_000,
|
|
)
|
|
registry.register(
|
|
name="web_extract", toolset="web", schema=WEB_EXTRACT_SCHEMA,
|
|
handler=lambda args, **kw: web_extract_tool(
|
|
args.get("urls", [])[:5] if isinstance(args.get("urls"), list) else [], "markdown",
|
|
char_limit=args.get("char_limit"),
|
|
),
|
|
check_fn=check_web_api_key, requires_env=_web_requires_env(), is_async=True, emoji="📄",
|
|
max_result_size_chars=100_000,
|
|
)
|