mirror of
https://github.com/usestrix/strix.git
synced 2026-10-13 03:57:59 +00:00
feat(web_search): default Exa to per-result summaries and add web_get_contents drill-down
This commit is contained in:
Ahmed Allam
parent
3de3c6f30d
commit
a4fa849f59
5 changed files with 396 additions and 69 deletions
|
|
@ -81,7 +81,7 @@ affecting the agents that do the actual testing.
|
|||
</ParamField>
|
||||
|
||||
<ParamField path="EXA_API_KEY" type="string">
|
||||
API key for Exa. Enables real-time web search through the Exa `/search` endpoint. This is the preferred web search provider.
|
||||
API key for Exa. Enables real-time web search through the Exa `/search` endpoint. Exa also powers the `web_get_contents` tool, which fetches the full text of a page through the Exa `/contents` endpoint. This is the preferred web search provider.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_WEB_SEARCH_PROVIDER" default="auto" type="string">
|
||||
|
|
@ -93,7 +93,11 @@ affecting the agents that do the actual testing.
|
|||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_EXA_NUM_RESULTS" default="5" type="integer">
|
||||
Number of Exa results to return, from `1` to `100`. Each result includes short query-relevant highlights. This setting applies only to the Exa provider.
|
||||
Number of Exa results to return, from `1` to `100`. This setting applies only to the Exa provider.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_EXA_CONTENT_MODE" default="summary" type="string">
|
||||
Content that each Exa result includes: `summary` or `highlights`. With `summary`, each result includes a short security-focused summary of the page. With `highlights`, each result includes verbatim query-relevant excerpts. To read a full page, the agent calls `web_get_contents` with the result URL. This setting applies only to the Exa provider.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="POSTMAN_API_KEY" type="string">
|
||||
|
|
|
|||
|
|
@ -69,7 +69,7 @@ from strix.tools.todo.tools import (
|
|||
mark_todo_pending,
|
||||
update_todo,
|
||||
)
|
||||
from strix.tools.web_search.tool import web_search
|
||||
from strix.tools.web_search.tool import web_get_contents, web_search
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
|
|
@ -579,6 +579,7 @@ _BASE_TOOLS: tuple[Tool, ...] = (
|
|||
save_threat_model,
|
||||
amend_threat_model,
|
||||
web_search,
|
||||
web_get_contents,
|
||||
create_vulnerability_report,
|
||||
create_dependency_report,
|
||||
update_vulnerability_report,
|
||||
|
|
|
|||
|
|
@ -122,6 +122,7 @@ class TelemetrySettings(BaseSettings):
|
|||
|
||||
WebSearchProvider = Literal["auto", "perplexity", "exa"]
|
||||
ExaSearchType = Literal["auto", "fast", "instant", "deep-lite", "deep", "deep-reasoning"]
|
||||
ExaContentMode = Literal["summary", "highlights"]
|
||||
|
||||
|
||||
class IntegrationSettings(BaseSettings):
|
||||
|
|
@ -151,6 +152,10 @@ class IntegrationSettings(BaseSettings):
|
|||
le=100,
|
||||
alias="STRIX_EXA_NUM_RESULTS",
|
||||
)
|
||||
exa_content_mode: ExaContentMode = Field(
|
||||
default="summary",
|
||||
alias="STRIX_EXA_CONTENT_MODE",
|
||||
)
|
||||
postman_api_key: str | None = Field(
|
||||
default=None,
|
||||
alias="POSTMAN_API_KEY",
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
"""``web_search`` — security-focused web search (Exa or Perplexity)."""
|
||||
"""Security-focused web research tools (Exa or Perplexity)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
from typing import Any, cast
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
|
||||
import requests
|
||||
from agents import RunContextWrapper, function_tool
|
||||
|
|
@ -13,6 +13,10 @@ from agents import RunContextWrapper, function_tool
|
|||
from strix.config import load_settings
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
|
|
@ -57,6 +61,20 @@ def _perplexity_content(api_key: str, query: str) -> str:
|
|||
|
||||
|
||||
_EXA_HIGHLIGHT_MAX_CHARS = 750
|
||||
_EXA_PAGE_MAX_CHARS = 20000
|
||||
_EXA_MAX_CONTENT_URLS = 10
|
||||
_EXA_SUMMARY_PROMPT = (
|
||||
"Summarize this page for a penetration tester. Keep concrete technical detail: "
|
||||
"affected products and exact versions, CVE and CWE identifiers, CVSS scores, "
|
||||
"exploitation preconditions, payloads or commands, and mitigations. "
|
||||
"Leave out marketing copy and navigation text."
|
||||
)
|
||||
|
||||
|
||||
def _exa_search_contents(content_mode: str) -> dict[str, Any]:
|
||||
if content_mode == "highlights":
|
||||
return {"highlights": {"maxCharacters": _EXA_HIGHLIGHT_MAX_CHARS}}
|
||||
return {"summary": {"query": _EXA_SUMMARY_PROMPT}}
|
||||
|
||||
|
||||
def _exa_result_block(result: dict[str, Any]) -> str | None:
|
||||
|
|
@ -65,6 +83,9 @@ def _exa_result_block(result: dict[str, Any]) -> str | None:
|
|||
return None
|
||||
title = str(result.get("title") or result_url)
|
||||
parts = [f"### {title}\n{result_url}"]
|
||||
summary = str(result.get("summary") or "").strip()
|
||||
if summary:
|
||||
parts.append(summary)
|
||||
highlights = result.get("highlights") or []
|
||||
if isinstance(highlights, list):
|
||||
excerpts = [str(item).strip() for item in highlights if str(item).strip()]
|
||||
|
|
@ -73,31 +94,70 @@ def _exa_result_block(result: dict[str, Any]) -> str | None:
|
|||
return "\n".join(parts)
|
||||
|
||||
|
||||
def _exa_content(api_key: str, query: str, search_type: str, num_results: int) -> str:
|
||||
url = "https://api.exa.ai/search"
|
||||
headers = {"x-api-key": api_key, "Content-Type": "application/json"}
|
||||
payload = {
|
||||
"query": f"{_SYSTEM_PROMPT}\n\n{query}",
|
||||
"type": search_type,
|
||||
"numResults": num_results,
|
||||
"contents": {"highlights": {"maxCharacters": _EXA_HIGHLIGHT_MAX_CHARS}},
|
||||
}
|
||||
with requests.post(url, headers=headers, json=payload, timeout=300) as response:
|
||||
response.raise_for_status()
|
||||
body: dict[str, Any] = response.json()
|
||||
results: list[Any] = body.get("results") or []
|
||||
def _exa_page_block(result: dict[str, Any]) -> str | None:
|
||||
result_url = str(result.get("url") or result.get("id") or "")
|
||||
text = str(result.get("text") or "").strip()
|
||||
if not result_url or not text:
|
||||
return None
|
||||
if len(text) > _EXA_PAGE_MAX_CHARS:
|
||||
text = f"{text[:_EXA_PAGE_MAX_CHARS]}\n[truncated at {_EXA_PAGE_MAX_CHARS} characters]"
|
||||
title = str(result.get("title") or result_url)
|
||||
return f"### {title}\n{result_url}\n\n{text}"
|
||||
|
||||
|
||||
def _exa_blocks(
|
||||
results: list[Any],
|
||||
render: Callable[[dict[str, Any]], str | None],
|
||||
) -> list[str]:
|
||||
blocks: list[str] = []
|
||||
for result in results:
|
||||
if not isinstance(result, dict):
|
||||
continue
|
||||
block = _exa_result_block(cast("dict[str, Any]", result))
|
||||
block = render(cast("dict[str, Any]", result))
|
||||
if block:
|
||||
blocks.append(block)
|
||||
return blocks
|
||||
|
||||
|
||||
def _exa_post(api_key: str, endpoint: str, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
headers = {"x-api-key": api_key, "Content-Type": "application/json"}
|
||||
with requests.post(endpoint, headers=headers, json=payload, timeout=300) as response:
|
||||
response.raise_for_status()
|
||||
body: dict[str, Any] = response.json()
|
||||
return body
|
||||
|
||||
|
||||
def _exa_content(
|
||||
api_key: str,
|
||||
query: str,
|
||||
search_type: str,
|
||||
num_results: int,
|
||||
content_mode: str,
|
||||
) -> str:
|
||||
body = _exa_post(
|
||||
api_key,
|
||||
"https://api.exa.ai/search",
|
||||
{
|
||||
"query": f"{_SYSTEM_PROMPT}\n\n{query}",
|
||||
"type": search_type,
|
||||
"numResults": num_results,
|
||||
"contents": _exa_search_contents(content_mode),
|
||||
},
|
||||
)
|
||||
blocks = _exa_blocks(body.get("results") or [], _exa_result_block)
|
||||
if not blocks:
|
||||
raise ValueError("Exa response has no results")
|
||||
return "\n\n".join(blocks)
|
||||
|
||||
|
||||
def _exa_page_text(api_key: str, urls: list[str]) -> str:
|
||||
body = _exa_post(api_key, "https://api.exa.ai/contents", {"urls": urls, "text": True})
|
||||
blocks = _exa_blocks(body.get("results") or [], _exa_page_block)
|
||||
if not blocks:
|
||||
raise ValueError("Exa returned no page contents")
|
||||
return "\n\n".join(blocks)
|
||||
|
||||
|
||||
def _resolve_provider( # noqa: PLR0911 - each provider/missing-key case needs its own return
|
||||
integrations: Any,
|
||||
) -> tuple[str, str] | dict[str, Any]:
|
||||
|
|
@ -133,7 +193,35 @@ def _not_configured_error(missing: str) -> dict[str, Any]:
|
|||
}
|
||||
|
||||
|
||||
def _do_search(query: str) -> dict[str, Any]: # noqa: PLR0911 - each error class needs its own sanitized return
|
||||
def _guarded_call( # noqa: PLR0911 - each error class needs its own sanitized return
|
||||
tool: str,
|
||||
rejected_hint: str,
|
||||
fetch: Callable[[], str],
|
||||
) -> str | dict[str, Any]:
|
||||
"""Run a provider call and translate any failure into a sanitized error dict."""
|
||||
try:
|
||||
return fetch()
|
||||
except requests.exceptions.Timeout:
|
||||
logger.warning("%s timed out", tool)
|
||||
return {"success": False, "error": f"{tool} timed out. Try again or narrow the request"}
|
||||
except requests.exceptions.HTTPError as exc:
|
||||
status = exc.response.status_code if exc.response is not None else None
|
||||
logger.exception("%s HTTP error status=%s", tool, status)
|
||||
if status is not None and 400 <= status < 500:
|
||||
return {"success": False, "error": rejected_hint}
|
||||
return {"success": False, "error": f"{tool} service is unavailable. Try again later"}
|
||||
except requests.exceptions.RequestException:
|
||||
logger.exception("%s network error", tool)
|
||||
return {"success": False, "error": f"{tool} network error. Try again later"}
|
||||
except (KeyError, IndexError, ValueError):
|
||||
logger.exception("%s response shape unexpected", tool)
|
||||
return {"success": False, "error": f"{tool} returned an unexpected response. Try again"}
|
||||
except Exception:
|
||||
logger.exception("%s failed", tool)
|
||||
return {"success": False, "error": f"{tool} failed unexpectedly"}
|
||||
|
||||
|
||||
def _do_search(query: str) -> dict[str, Any]:
|
||||
if not query or not query.strip():
|
||||
return {"success": False, "error": "Query cannot be empty"}
|
||||
|
||||
|
|
@ -144,63 +232,75 @@ def _do_search(query: str) -> dict[str, Any]: # noqa: PLR0911 - each error clas
|
|||
provider, api_key = resolved
|
||||
logger.info("web_search provider=%s query (len=%d): %s", provider, len(query), query[:120])
|
||||
|
||||
try:
|
||||
def fetch() -> str:
|
||||
if provider == "exa":
|
||||
content = _exa_content(
|
||||
return _exa_content(
|
||||
api_key,
|
||||
query,
|
||||
integrations.exa_search_type,
|
||||
integrations.exa_num_results,
|
||||
integrations.exa_content_mode,
|
||||
)
|
||||
else:
|
||||
content = _perplexity_content(api_key, query)
|
||||
except requests.exceptions.Timeout:
|
||||
logger.warning("web_search timed out")
|
||||
return _perplexity_content(api_key, query)
|
||||
|
||||
outcome = _guarded_call(
|
||||
"Web search",
|
||||
(
|
||||
"Web search rejected the query. Refine it "
|
||||
"(more specific, shorter, no unusual characters) and retry"
|
||||
),
|
||||
fetch,
|
||||
)
|
||||
if isinstance(outcome, dict):
|
||||
return outcome
|
||||
return {
|
||||
"success": True,
|
||||
"query": query,
|
||||
"provider": provider,
|
||||
"content": outcome,
|
||||
}
|
||||
|
||||
|
||||
def _do_get_contents(urls: list[str]) -> dict[str, Any]:
|
||||
cleaned = [url.strip() for url in urls if url and url.strip()]
|
||||
if not cleaned:
|
||||
return {"success": False, "error": "Provide at least one URL"}
|
||||
if len(cleaned) > _EXA_MAX_CONTENT_URLS:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Web search timed out. Try again or shorten the query",
|
||||
"error": f"Too many URLs. Pass at most {_EXA_MAX_CONTENT_URLS} per call",
|
||||
}
|
||||
except requests.exceptions.HTTPError as exc:
|
||||
status = exc.response.status_code if exc.response is not None else None
|
||||
logger.exception("web_search HTTP error status=%s", status)
|
||||
if status is not None and 400 <= status < 500:
|
||||
return {
|
||||
"success": False,
|
||||
"error": (
|
||||
"Web search rejected the query. Refine it "
|
||||
"(more specific, shorter, no unusual characters) and retry"
|
||||
),
|
||||
}
|
||||
|
||||
integrations = load_settings().integrations
|
||||
api_key = integrations.exa_api_key
|
||||
if not api_key:
|
||||
return _not_configured_error("EXA_API_KEY")
|
||||
if integrations.web_search_provider == "perplexity":
|
||||
logger.warning("web_get_contents invoked while the provider is pinned to Perplexity")
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Web search service is unavailable. Try again later",
|
||||
}
|
||||
except requests.exceptions.RequestException:
|
||||
logger.exception("web_search network error")
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Web search network error. Try again later",
|
||||
}
|
||||
except (KeyError, IndexError, ValueError):
|
||||
logger.exception("web_search response shape unexpected")
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Web search returned an unexpected response. Try again",
|
||||
}
|
||||
except Exception:
|
||||
logger.exception("web_search failed")
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Web search failed unexpectedly",
|
||||
}
|
||||
else:
|
||||
return {
|
||||
"success": True,
|
||||
"query": query,
|
||||
"provider": provider,
|
||||
"content": content,
|
||||
"error": (
|
||||
"Page fetching needs the Exa provider "
|
||||
"(operator pinned STRIX_WEB_SEARCH_PROVIDER to perplexity). "
|
||||
"Use web_search instead"
|
||||
),
|
||||
}
|
||||
|
||||
logger.info("web_get_contents urls=%d", len(cleaned))
|
||||
outcome = _guarded_call(
|
||||
"Page fetch",
|
||||
"Page fetch was rejected. Check the URLs are complete, public, and correctly formed",
|
||||
lambda: _exa_page_text(api_key, cleaned),
|
||||
)
|
||||
if isinstance(outcome, dict):
|
||||
return outcome
|
||||
return {
|
||||
"success": True,
|
||||
"urls": cleaned,
|
||||
"provider": "exa",
|
||||
"content": outcome,
|
||||
}
|
||||
|
||||
|
||||
@function_tool(timeout=330)
|
||||
async def web_search(ctx: RunContextWrapper, query: str) -> str:
|
||||
|
|
@ -234,6 +334,13 @@ async def web_search(ctx: RunContextWrapper, query: str) -> str:
|
|||
exploits, Kali-compatible tooling, and concrete code/command
|
||||
examples.
|
||||
|
||||
With the Exa provider you get a ranked list of results, each with a
|
||||
title, URL, and a short security-focused summary (or verbatim
|
||||
highlights when ``STRIX_EXA_CONTENT_MODE=highlights``). Read the
|
||||
result you need, then call ``web_get_contents`` with its URL to pull
|
||||
the full page text when a summary is not enough. With Perplexity you
|
||||
get a single synthesized cited answer.
|
||||
|
||||
**Good example queries** (each is a full sentence, names a
|
||||
version/product, and asks one concrete thing):
|
||||
|
||||
|
|
@ -261,3 +368,28 @@ async def web_search(ctx: RunContextWrapper, query: str) -> str:
|
|||
"""
|
||||
result = await asyncio.to_thread(_do_search, query)
|
||||
return json.dumps(result, ensure_ascii=False, default=str)
|
||||
|
||||
|
||||
@function_tool(timeout=330)
|
||||
async def web_get_contents(ctx: RunContextWrapper, urls: list[str]) -> str:
|
||||
"""Fetch the full, cleaned text of specific web pages (Exa only).
|
||||
|
||||
Use this as the drill-down step after ``web_search``: when a result's
|
||||
summary or highlights are not enough, pass that result's URL here to
|
||||
read the whole page. Good for reading a full advisory, a CVE writeup,
|
||||
an exploit proof-of-concept, or vendor documentation end to end.
|
||||
|
||||
Prefer ``web_search`` first to find the right pages, then fetch only
|
||||
the few URLs worth reading in full — each page can be large, so avoid
|
||||
fetching many pages you do not need.
|
||||
|
||||
This tool needs the Exa provider (``EXA_API_KEY``). When the operator
|
||||
pins the provider to Perplexity, it returns an error and you should
|
||||
use ``web_search`` instead.
|
||||
|
||||
Args:
|
||||
urls: The page URLs to fetch, at most 10 per call. Use complete,
|
||||
public URLs (for example the ones returned by ``web_search``).
|
||||
"""
|
||||
result = await asyncio.to_thread(_do_get_contents, urls)
|
||||
return json.dumps(result, ensure_ascii=False, default=str)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
"""Tests for web_search provider selection and the Exa backend."""
|
||||
"""Tests for web_search/web_get_contents provider selection and the Exa backend."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
|
|
@ -104,7 +104,7 @@ def test_exa_content_renders_results_with_highlights(monkeypatch: pytest.MonkeyP
|
|||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
|
||||
content = tool._exa_content("ek", "OpenSSH 7.4 RCE?", "auto", 5)
|
||||
content = tool._exa_content("ek", "OpenSSH 7.4 RCE?", "auto", 5, "highlights")
|
||||
|
||||
assert captured["url"] == "https://api.exa.ai/search"
|
||||
assert captured["headers"]["x-api-key"] == "ek"
|
||||
|
|
@ -112,13 +112,42 @@ def test_exa_content_renders_results_with_highlights(monkeypatch: pytest.MonkeyP
|
|||
assert captured["json"]["type"] == "auto"
|
||||
assert captured["json"]["numResults"] == 5
|
||||
assert captured["json"]["contents"]["highlights"]["maxCharacters"] > 0
|
||||
assert "summary" not in captured["json"]["contents"]
|
||||
assert content == (
|
||||
"### NVD entry\nhttps://nvd.example/cve\n> CVE-2024-0001 affects it.\n\n"
|
||||
"### https://blog.example/post\nhttps://blog.example/post"
|
||||
)
|
||||
|
||||
|
||||
def test_exa_content_renders_a_result_without_highlights(
|
||||
def test_exa_content_defaults_to_summary_and_renders_it(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
captured: dict[str, Any] = {}
|
||||
|
||||
def fake_post(_url: str, **kwargs: Any) -> _FakeResponse:
|
||||
captured["json"] = kwargs["json"]
|
||||
return _FakeResponse(
|
||||
{
|
||||
"results": [
|
||||
{
|
||||
"url": "https://nvd.example/cve",
|
||||
"title": "NVD entry",
|
||||
"summary": " CVE-2024-0001 is a heap overflow. ",
|
||||
},
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
|
||||
content = tool._exa_content("ek", "q", "auto", 5, "summary")
|
||||
|
||||
assert captured["json"]["contents"]["summary"]["query"]
|
||||
assert "highlights" not in captured["json"]["contents"]
|
||||
assert content == "### NVD entry\nhttps://nvd.example/cve\nCVE-2024-0001 is a heap overflow."
|
||||
|
||||
|
||||
def test_exa_content_renders_a_result_without_contents(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(
|
||||
|
|
@ -128,7 +157,7 @@ def test_exa_content_renders_a_result_without_highlights(
|
|||
{"results": [{"url": "https://ex.example", "title": "Ex"}]}
|
||||
),
|
||||
)
|
||||
assert tool._exa_content("ek", "q", "auto", 5) == "### Ex\nhttps://ex.example"
|
||||
assert tool._exa_content("ek", "q", "auto", 5, "summary") == "### Ex\nhttps://ex.example"
|
||||
|
||||
|
||||
@pytest.mark.parametrize("body", [{}, {"results": None}, {"results": []}, {"results": ["x"]}])
|
||||
|
|
@ -137,7 +166,28 @@ def test_exa_content_rejects_empty_results(
|
|||
) -> None:
|
||||
monkeypatch.setattr(requests, "post", lambda *_a, **_kw: _FakeResponse(body))
|
||||
with pytest.raises(ValueError, match="no results"):
|
||||
tool._exa_content("ek", "q", "auto", 5)
|
||||
tool._exa_content("ek", "q", "auto", 5, "summary")
|
||||
|
||||
|
||||
def test_exa_content_mode_is_configurable(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
captured: dict[str, Any] = {}
|
||||
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(
|
||||
EXA_API_KEY="ek",
|
||||
STRIX_EXA_CONTENT_MODE="highlights",
|
||||
)
|
||||
|
||||
def fake_post(_url: str, **kwargs: Any) -> _FakeResponse:
|
||||
captured["json"] = kwargs["json"]
|
||||
return _FakeResponse({"results": [{"url": "https://ex.example", "title": "Ex"}]})
|
||||
|
||||
monkeypatch.setattr(tool, "load_settings", _Settings)
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
|
||||
assert tool._do_search("q")["success"] is True
|
||||
assert "highlights" in captured["json"]["contents"]
|
||||
assert "summary" not in captured["json"]["contents"]
|
||||
|
||||
|
||||
def test_do_search_reports_empty_exa_results_as_unexpected(
|
||||
|
|
@ -198,6 +248,141 @@ def test_exa_search_type_and_num_results_are_configurable(
|
|||
assert captured["json"]["numResults"] == 3
|
||||
|
||||
|
||||
def test_exa_page_text_requests_full_text_and_renders_pages(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
captured: dict[str, Any] = {}
|
||||
|
||||
def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
|
||||
captured["url"] = url
|
||||
captured["headers"] = kwargs["headers"]
|
||||
captured["json"] = kwargs["json"]
|
||||
return _FakeResponse(
|
||||
{
|
||||
"results": [
|
||||
{
|
||||
"url": "https://nvd.example/cve",
|
||||
"title": "NVD entry",
|
||||
"text": " Full advisory body. ",
|
||||
},
|
||||
{"url": "https://empty.example", "text": " "},
|
||||
"not-a-dict",
|
||||
{"text": "no url"},
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
|
||||
content = tool._exa_page_text("ek", ["https://nvd.example/cve"])
|
||||
|
||||
assert captured["url"] == "https://api.exa.ai/contents"
|
||||
assert captured["headers"]["x-api-key"] == "ek"
|
||||
assert captured["json"] == {"urls": ["https://nvd.example/cve"], "text": True}
|
||||
assert content == "### NVD entry\nhttps://nvd.example/cve\n\nFull advisory body."
|
||||
|
||||
|
||||
def test_exa_page_text_truncates_a_long_page(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
body = "A" * (tool._EXA_PAGE_MAX_CHARS + 500)
|
||||
monkeypatch.setattr(
|
||||
requests,
|
||||
"post",
|
||||
lambda *_a, **_kw: _FakeResponse(
|
||||
{"results": [{"url": "https://ex.example", "text": body}]}
|
||||
),
|
||||
)
|
||||
content = tool._exa_page_text("ek", ["https://ex.example"])
|
||||
assert "truncated at" in content
|
||||
assert content.count("A") == tool._EXA_PAGE_MAX_CHARS
|
||||
|
||||
|
||||
@pytest.mark.parametrize("body", [{}, {"results": []}, {"results": [{"url": "u"}]}])
|
||||
def test_exa_page_text_rejects_pages_without_text(
|
||||
monkeypatch: pytest.MonkeyPatch, body: dict[str, Any]
|
||||
) -> None:
|
||||
monkeypatch.setattr(requests, "post", lambda *_a, **_kw: _FakeResponse(body))
|
||||
with pytest.raises(ValueError, match="no page contents"):
|
||||
tool._exa_page_text("ek", ["https://ex.example"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize("urls", [[], ["", " "]])
|
||||
def test_do_get_contents_requires_a_url(urls: list[str]) -> None:
|
||||
result = tool._do_get_contents(urls)
|
||||
assert result["success"] is False
|
||||
assert "at least one URL" in result["error"]
|
||||
|
||||
|
||||
def test_do_get_contents_caps_the_url_count() -> None:
|
||||
urls = [f"https://ex{index}.example" for index in range(tool._EXA_MAX_CONTENT_URLS + 1)]
|
||||
result = tool._do_get_contents(urls)
|
||||
assert result["success"] is False
|
||||
assert "Too many URLs" in result["error"]
|
||||
|
||||
|
||||
def test_do_get_contents_needs_an_exa_key(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(PERPLEXITY_API_KEY="pk")
|
||||
|
||||
monkeypatch.setattr(tool, "load_settings", _Settings)
|
||||
|
||||
result = tool._do_get_contents(["https://ex.example"])
|
||||
|
||||
assert result["success"] is False
|
||||
assert "EXA_API_KEY" in result["error"]
|
||||
|
||||
|
||||
def test_do_get_contents_refuses_a_perplexity_pinned_provider(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(
|
||||
EXA_API_KEY="ek",
|
||||
PERPLEXITY_API_KEY="pk",
|
||||
STRIX_WEB_SEARCH_PROVIDER="perplexity",
|
||||
)
|
||||
|
||||
monkeypatch.setattr(tool, "load_settings", _Settings)
|
||||
|
||||
result = tool._do_get_contents(["https://ex.example"])
|
||||
|
||||
assert result["success"] is False
|
||||
assert "web_search" in result["error"]
|
||||
|
||||
|
||||
def test_do_get_contents_returns_page_text(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(EXA_API_KEY="ek")
|
||||
|
||||
monkeypatch.setattr(tool, "load_settings", _Settings)
|
||||
monkeypatch.setattr(tool, "_exa_page_text", lambda *_a: "page")
|
||||
|
||||
result = tool._do_get_contents([" https://ex.example "])
|
||||
|
||||
assert result == {
|
||||
"success": True,
|
||||
"urls": ["https://ex.example"],
|
||||
"provider": "exa",
|
||||
"content": "page",
|
||||
}
|
||||
|
||||
|
||||
def test_do_get_contents_sanitizes_a_network_error(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(EXA_API_KEY="ek")
|
||||
|
||||
def boom(*_args: Any, **_kwargs: Any) -> None:
|
||||
raise requests.exceptions.ConnectionError
|
||||
|
||||
monkeypatch.setattr(tool, "load_settings", _Settings)
|
||||
monkeypatch.setattr(requests, "post", boom)
|
||||
|
||||
result = tool._do_get_contents(["https://ex.example"])
|
||||
|
||||
assert result["success"] is False
|
||||
assert "network error" in result["error"]
|
||||
assert "ek" not in result["error"]
|
||||
|
||||
|
||||
def test_do_search_reports_the_provider_it_used(monkeypatch: pytest.MonkeyPatch) -> None:
|
||||
class _Settings:
|
||||
integrations = IntegrationSettings(EXA_API_KEY="ek")
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue