mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 17:23:15 +00:00
ccea80b887
* feat(reviewer): inline AGENTS.md into reviewer system prompt Fetches AGENTS.md from the PR's head_sha via the GitHub contents API during reviewer setup and inlines it as a "Repository conventions" block in the system prompt. Mirrors how the per-repo review style prompt is already wired. The main agent has long had a mandatory step to read AGENTS.md after cloning, but the reviewer often skips cloning entirely (it can `gh pr diff` directly), so it never saw the file. Loading it deterministically means the reviewer judges findings against the project's own conventions instead of relying on the model to fetch the file itself. * fix(reviewer): fetch AGENTS.md from base_sha, not head_sha The reviewer inlines AGENTS.md into its system prompt. Reading from head_sha means a PR author can edit AGENTS.md in the same PR being reviewed and smuggle instructions like "ignore all bugs" / "publish no findings" into the reviewer's prompt. Switch to base_sha (the target branch's pre-PR state, which is trusted) and update the prompt text to reflect that the contents come from the base, not the head. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
73 lines
2.1 KiB
Python
73 lines
2.1 KiB
Python
"""Fetch ``AGENTS.md`` from a GitHub repo so it can be inlined into prompts.
|
|
|
|
Used by the reviewer to deterministically load repo conventions into context
|
|
without the model having to clone the repo and read the file itself.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
|
|
import httpx
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# Cap the inlined content. AGENTS.md is meant to be a short conventions doc;
|
|
# anything larger is probably accidental and would bloat every reviewer prompt.
|
|
_MAX_AGENTS_MD_BYTES = 64 * 1024
|
|
|
|
|
|
async def fetch_agents_md(
|
|
owner: str,
|
|
repo: str,
|
|
ref: str,
|
|
*,
|
|
token: str | None,
|
|
timeout: float = 10.0,
|
|
) -> str | None:
|
|
"""Fetch ``AGENTS.md`` at ``ref`` from ``owner/repo``.
|
|
|
|
Returns the raw file contents, or ``None`` if the file is missing, the
|
|
request fails, or the file exceeds the size cap.
|
|
"""
|
|
if not owner or not repo or not ref:
|
|
return None
|
|
|
|
url = f"https://api.github.com/repos/{owner}/{repo}/contents/AGENTS.md"
|
|
headers = {
|
|
"Accept": "application/vnd.github.raw",
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
}
|
|
if token:
|
|
headers["Authorization"] = f"Bearer {token}"
|
|
|
|
try:
|
|
async with httpx.AsyncClient(timeout=timeout) as client:
|
|
response = await client.get(url, headers=headers, params={"ref": ref})
|
|
except httpx.HTTPError:
|
|
logger.exception("Failed to fetch AGENTS.md from %s/%s@%s", owner, repo, ref)
|
|
return None
|
|
|
|
if response.status_code == 404:
|
|
return None
|
|
if response.status_code != 200:
|
|
logger.warning(
|
|
"Unexpected status %s fetching AGENTS.md from %s/%s@%s",
|
|
response.status_code,
|
|
owner,
|
|
repo,
|
|
ref,
|
|
)
|
|
return None
|
|
|
|
content = response.text
|
|
if len(content.encode("utf-8")) > _MAX_AGENTS_MD_BYTES:
|
|
logger.info(
|
|
"AGENTS.md in %s/%s@%s exceeds %d bytes; skipping inline",
|
|
owner,
|
|
repo,
|
|
ref,
|
|
_MAX_AGENTS_MD_BYTES,
|
|
)
|
|
return None
|
|
return content
|