open-swe/agent/tools/http_request.py
Adam Moussa b3b0274403
feat: Re-land deferred upstream features on modular webhooks (#80) (#128)
* fix(webhooks): fall back to vision model for Slack/Linear image threads

Re-land upstream #1626 onto the modular webhook structure. When a
Slack mention or Linear issue carries images but the resolved model is
text-only, fall back to a vision-capable model instead of dropping the
images. Re-points default_vision_model_pair at the fork's image-capable
models (Opus 4.8 default, else any supports_images model) rather than
upstream's openai:/anthropic: provider filter.

Refs #80, upstream #1626

* fix(slack): persist trace_message_ts so web-handoff updates the trace reply

Re-land upstream #1630 onto the modular structure. The first-mention
store_slack_run_mapping call did not pass trace_message_ts, so it was
never persisted (nothing to preserve from on first mention) and
_notify_slack_web_handoff always skipped the trace-reply update on web
handoff. Pass it through and cover it with a test.

Refs #80, upstream #1630

* feat(slack): include channel context in Slack prompts

Re-land upstream #1633 onto the modular structure. Fetch cached Slack
channel metadata once per event (_get_slack_channel_context) and thread
it through the docs-plz gate, repo resolution, and process_slack_mention
so prompts carry the channel name and a clearly-marked untrusted
channel description. Avoids duplicate conversations.info calls.

Refs #80, upstream #1633

* feat(tools): add slack_start_new_thread breakout tool

Re-land upstream #1638 onto the modular structure. Adds the
slack_start_new_thread tool (posts a top-level Slack message and
dispatches a fresh agent run for a broken-out task via the durable
dispatch_agent_run contract), wires it into the agent tool list and
tools/__init__, adds prompt guidance, and excludes it from plan mode so
it can't bypass the approval flow. Tool imports only live modules.

Refs #80, upstream #1638

* feat(plan): notify Slack on plan approval

Re-land upstream #1632 onto the modular structure. When a plan is
approved via the dashboard approve endpoint, post a thread reply to the
originating Slack thread noting the comment count and approver, after
the follow-up run is dispatched. Slack post failures never break
approval. Adapted to the fork's approve_plan (no plan_markdown read).

Refs #80, upstream #1632

* feat(plan): publish plans from sandbox files

Re-land upstream #1635 onto the modular structure, completing the
partially-ported change so dev is internally consistent. save_plan now
takes a plan_file_path, reads the agent-authored Markdown file from
/workspace/plans/ (validating extension/location/UTF-8/size) and
publishes it, instead of taking a plan_markdown string. Removes
write_file/edit_file from PLAN_MODE_EXCLUDED_TOOLS so the agent can
author the plan file, updates enter_plan_mode/reject_plan guidance and
the e2e fake LLM. Skips the #1610-only update_plan hunk (not on dev).

Refs #80, upstream #1635

* fix(security): SSRF-harden server-side image fetch + stop logging raw image URLs

INJ-01 (high): fetch_image_block used follow_redirects=True with no per-hop
revalidation and discarded the resolved-IP pin, so an attacker-authored Slack/
Linear image URL could 302-redirect the fetch to an internal host / cloud
metadata endpoint (blind SSRF), and DNS-rebinding could bypass the one-shot
is_url_safe check. Route image fetches through the same per-hop resolve+pin+
revalidate loop the http_request tool uses, lifted into url_safety as the shared
request_with_safe_redirects. Also strip the per-host Slack/Linear bearer token
on redirect so it can't be replayed to a redirect target.

SC-1 (low): linear.py logged full image URLs (which can carry signed tokens) at
DEBUG; multimodal logged them at INFO on every fetch. Log host-only.

Sink lived in multimodal.py (unchanged by the feature work) but PR #128 widened
its reach by no longer dropping images for text-only models. Fixing on the base
branch so #130/#129 inherit it on rebase. Adds fetch_image_block SSRF regression
tests (redirect-to-internal blocked; auth stripped on redirect).
2026-07-08 18:32:43 -04:00

110 lines
3.2 KiB
Python

from typing import Any
import httpx
from ..utils.url_safety import pinned_url as _pinned_url # noqa: F401 (kept for tests)
from ..utils.url_safety import request_with_safe_redirects
from ..utils.url_safety import resolve_and_validate as _resolve_and_validate # noqa: F401
def _blocked_response(url: str, reason: str) -> dict[str, Any]:
return {
"success": False,
"status_code": 0,
"headers": {},
"content": f"Request blocked: {reason}",
"url": url,
}
async def _request_with_safe_redirects(
client: httpx.AsyncClient,
method: str,
url: str,
**kwargs: Any,
) -> tuple[httpx.Response | None, dict[str, Any] | None]:
"""Thin wrapper over the shared SSRF-safe redirect loop that shapes a blocked
hop into the tool's error-response dict."""
response, blocked = await request_with_safe_redirects(client, method, url, **kwargs)
if blocked is not None:
blocked_url, reason = blocked
return None, _blocked_response(blocked_url, reason)
return response, None
async def http_request(
url: str,
method: str = "GET",
headers: dict[str, str] | None = None,
data: str | dict | None = None,
params: dict[str, str] | None = None,
timeout: int = 30,
) -> dict[str, Any]:
"""Make HTTP requests to APIs and web services.
Do not use this tool for GitHub API calls. Use `GH_TOKEN=dummy gh` in the
sandbox so GitHub authentication is handled by the sandbox proxy.
Args:
url: Target URL
method: HTTP method (GET, POST, PUT, DELETE, etc.)
headers: HTTP headers to include
data: Request body data (string or dict)
params: URL query parameters
timeout: Request timeout in seconds
Returns:
Dictionary with response data including status, headers, and content
"""
try:
kwargs: dict[str, Any] = {}
if headers:
kwargs["headers"] = headers
if params:
kwargs["params"] = params
if data:
if isinstance(data, dict):
kwargs["json"] = data
else:
kwargs["content"] = data
async with httpx.AsyncClient(timeout=timeout) as client:
response, blocked = await _request_with_safe_redirects(
client,
method,
url,
**kwargs,
)
if blocked:
return blocked
try:
content = response.json()
except ValueError:
content = response.text
return {
"success": response.status_code < 400,
"status_code": response.status_code,
"headers": dict(response.headers),
"content": content,
"url": str(response.url),
}
except httpx.TimeoutException:
return {
"success": False,
"status_code": 0,
"headers": {},
"content": f"Request timed out after {timeout} seconds",
"url": url,
}
except httpx.HTTPError as e:
return {
"success": False,
"status_code": 0,
"headers": {},
"content": f"Request error: {e!s}",
"url": url,
}