2026-06-11 16:11:10 -07:00
|
|
|
"""Read API for the PR review UI.
|
|
|
|
|
|
|
|
|
|
Reviewer threads (``metadata.kind == "reviewer"``) hold the durable review
|
|
|
|
|
state for a PR: identity (``pr``), findings, watch flag, and head SHA. These
|
|
|
|
|
endpoints surface that state plus live PR details/diff fetched from GitHub
|
|
|
|
|
with the App installation token.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
2026-06-22 14:01:06 -07:00
|
|
|
import ipaddress
|
2026-06-11 16:11:10 -07:00
|
|
|
import logging
|
feat: inline PR comments in the reviews UI (#1600)
* feat: inline PR comments in the reviews UI
Click the diff gutter "+" on a line to open an inline comment composer
(rendered like the finding card via a Pierre annotation); submitting
posts a real inline PR review comment as the signed-in user through a
new POST /reviews/{owner}/{repo}/{number}/comments. The "+" press-drag →
"Add to Chat" selection path is unchanged.
* feat: GitHub-parity comment box, PR comments dropdown, collapse nav
- Comment composer now mirrors GitHub's box: Write/Preview tabs (markdown
rendered via the existing Markdown component) and a markdown toolbar
(heading, bold, italic, quote, code, link, bulleted/numbered/task list).
- Surface other people's inline PR comments in a Devin-style dropdown in the
review header (search + link to the thread on GitHub). New
GET /reviews/{owner}/{repo}/{number}/comments lists them and flags the
reviewer's own (marker-bearing) comments so they're filtered out.
- Collapse the global nav by default on a review detail page, restoring the
prior preference on leave.
* feat: bigger comment-toolbar icons; open dropdown comments inline
- Enlarge the markdown toolbar glyphs (Phosphor) in the comment composer —
they were rendering at 10px.
- Clicking a comment in the PR comments dropdown now opens it inline in the
diff as a read-only finding-style card (InlineComment), scrolling its line
into view, instead of navigating to GitHub. Falls back to GitHub when the
comment's file/line isn't in the current diff.
* fix: drive "Add to Chat" from native text selection
The gutter "+" is now comment-only; wiring its click to the composer
conflicted with its old double-duty as the drag-to-select handle, which
broke selection → "Add to Chat". Switch to Devin's model: disable Pierre's
interactive line selection and instead map a native text highlight in the
diff to a line range (via the data-line / data-line-type attributes Pierre
stamps on each line, read from the diff's open shadow root) to show the
"Add to Chat" popup. ⌘L and the existing attachment/popup path are unchanged.
* feat: gutter "+" drag selects a range for multi-line comments
Re-enable Pierre's gutter line selection so dragging the "+" down the
gutter comments across a range (click still comments on a single line);
onLineSelectionEnd routes the range to the composer. Native code-text
selection still drives "Add to Chat" — Pierre only line-selects from the
gutter, and onLineSelectionEnd bails when a native text selection is
present, so a code highlight never opens the composer.
* fix: keep the range highlighted while its comment composer is open
Previously opening the composer cleared the selection, so the lines being
commented on lost their highlight. Drive the controlled selection from the
open comment draft's range so the rows stay highlighted until the composer
is closed.
* fix: address PR review — paginate comments, fall back for outdated ones
- list_review_comments now pages through all PR review comments (bounded by
_MAX_REVIEW_COMMENT_PAGES) instead of returning only the first 100, so older
comments still show in the dropdown.
- Surface GitHub's outdated flag (position == null) as is_outdated; opening such
a comment (or one whose line isn't in the diff) now opens it on GitHub instead
of silently rendering nothing, plus a timeout fallback if the annotation never
mounts (e.g. collapsed context).
2026-06-23 16:01:46 -07:00
|
|
|
import re
|
2026-06-22 14:01:06 -07:00
|
|
|
import socket
|
2026-06-11 16:11:10 -07:00
|
|
|
from collections.abc import Awaitable, Callable
|
|
|
|
|
from typing import Any, Literal
|
2026-06-22 14:01:06 -07:00
|
|
|
from urllib.parse import urljoin, urlparse
|
2026-06-11 16:11:10 -07:00
|
|
|
|
|
|
|
|
import httpx
|
2026-06-22 14:01:06 -07:00
|
|
|
from fastapi import HTTPException, Response
|
2026-06-11 16:11:10 -07:00
|
|
|
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
from ..review.findings import REVIEWER_THREAD_KIND
|
2026-06-11 16:11:10 -07:00
|
|
|
from ..utils.github_app import get_github_app_installation_token
|
|
|
|
|
from ..utils.github_checks import github_headers
|
|
|
|
|
from ..utils.thread_ops import langgraph_client
|
2026-06-12 11:03:51 -07:00
|
|
|
from .pr_diff import build_pr_diff_files
|
2026-06-11 16:11:10 -07:00
|
|
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
|
|
_GITHUB_API = "https://api.github.com"
|
|
|
|
|
_GITHUB_TIMEOUT = httpx.Timeout(15.0, connect=5.0)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _require_app_token() -> str:
|
|
|
|
|
token = await get_github_app_installation_token()
|
|
|
|
|
if not token:
|
|
|
|
|
raise HTTPException(503, "GitHub App token unavailable")
|
|
|
|
|
return token
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _github_get(
|
|
|
|
|
path: str, token: str, *, accept: str | None = None, params: dict[str, Any] | None = None
|
|
|
|
|
) -> Any:
|
|
|
|
|
headers = github_headers(token)
|
|
|
|
|
if accept:
|
|
|
|
|
headers["Accept"] = accept
|
|
|
|
|
async with httpx.AsyncClient(timeout=_GITHUB_TIMEOUT) as client:
|
|
|
|
|
response = await client.get(f"{_GITHUB_API}{path}", headers=headers, params=params)
|
|
|
|
|
if response.status_code == 404:
|
|
|
|
|
raise HTTPException(404, "not found on GitHub")
|
|
|
|
|
if response.status_code >= 400:
|
|
|
|
|
logger.warning("GitHub GET %s failed: %s", path, response.status_code)
|
|
|
|
|
raise HTTPException(502, f"GitHub request failed ({response.status_code})")
|
|
|
|
|
if accept and "json" not in accept:
|
|
|
|
|
return response.text
|
|
|
|
|
return response.json()
|
|
|
|
|
|
|
|
|
|
|
feat: inline PR comments in the reviews UI (#1600)
* feat: inline PR comments in the reviews UI
Click the diff gutter "+" on a line to open an inline comment composer
(rendered like the finding card via a Pierre annotation); submitting
posts a real inline PR review comment as the signed-in user through a
new POST /reviews/{owner}/{repo}/{number}/comments. The "+" press-drag →
"Add to Chat" selection path is unchanged.
* feat: GitHub-parity comment box, PR comments dropdown, collapse nav
- Comment composer now mirrors GitHub's box: Write/Preview tabs (markdown
rendered via the existing Markdown component) and a markdown toolbar
(heading, bold, italic, quote, code, link, bulleted/numbered/task list).
- Surface other people's inline PR comments in a Devin-style dropdown in the
review header (search + link to the thread on GitHub). New
GET /reviews/{owner}/{repo}/{number}/comments lists them and flags the
reviewer's own (marker-bearing) comments so they're filtered out.
- Collapse the global nav by default on a review detail page, restoring the
prior preference on leave.
* feat: bigger comment-toolbar icons; open dropdown comments inline
- Enlarge the markdown toolbar glyphs (Phosphor) in the comment composer —
they were rendering at 10px.
- Clicking a comment in the PR comments dropdown now opens it inline in the
diff as a read-only finding-style card (InlineComment), scrolling its line
into view, instead of navigating to GitHub. Falls back to GitHub when the
comment's file/line isn't in the current diff.
* fix: drive "Add to Chat" from native text selection
The gutter "+" is now comment-only; wiring its click to the composer
conflicted with its old double-duty as the drag-to-select handle, which
broke selection → "Add to Chat". Switch to Devin's model: disable Pierre's
interactive line selection and instead map a native text highlight in the
diff to a line range (via the data-line / data-line-type attributes Pierre
stamps on each line, read from the diff's open shadow root) to show the
"Add to Chat" popup. ⌘L and the existing attachment/popup path are unchanged.
* feat: gutter "+" drag selects a range for multi-line comments
Re-enable Pierre's gutter line selection so dragging the "+" down the
gutter comments across a range (click still comments on a single line);
onLineSelectionEnd routes the range to the composer. Native code-text
selection still drives "Add to Chat" — Pierre only line-selects from the
gutter, and onLineSelectionEnd bails when a native text selection is
present, so a code highlight never opens the composer.
* fix: keep the range highlighted while its comment composer is open
Previously opening the composer cleared the selection, so the lines being
commented on lost their highlight. Drive the controlled selection from the
open comment draft's range so the rows stay highlighted until the composer
is closed.
* fix: address PR review — paginate comments, fall back for outdated ones
- list_review_comments now pages through all PR review comments (bounded by
_MAX_REVIEW_COMMENT_PAGES) instead of returning only the first 100, so older
comments still show in the dropdown.
- Surface GitHub's outdated flag (position == null) as is_outdated; opening such
a comment (or one whose line isn't in the diff) now opens it on GitHub instead
of silently rendering nothing, plus a timeout fallback if the annotation never
mounts (e.g. collapsed context).
2026-06-23 16:01:46 -07:00
|
|
|
def _github_error_message(response: httpx.Response) -> str:
|
|
|
|
|
"""Best-effort extraction of GitHub's error message for surfacing to the UI."""
|
|
|
|
|
fallback = f"GitHub request failed ({response.status_code})"
|
|
|
|
|
try:
|
|
|
|
|
data = response.json()
|
|
|
|
|
except ValueError:
|
|
|
|
|
return fallback
|
|
|
|
|
if not isinstance(data, dict):
|
|
|
|
|
return fallback
|
|
|
|
|
message = data.get("message")
|
|
|
|
|
message_str = message if isinstance(message, str) else ""
|
|
|
|
|
errors = data.get("errors")
|
|
|
|
|
detail_parts: list[str] = []
|
|
|
|
|
if isinstance(errors, list):
|
|
|
|
|
for err in errors:
|
|
|
|
|
if isinstance(err, dict) and isinstance(err.get("message"), str):
|
|
|
|
|
detail_parts.append(err["message"])
|
|
|
|
|
detail = "; ".join(detail_parts)
|
|
|
|
|
if message_str and detail:
|
|
|
|
|
return f"{message_str}: {detail}"
|
|
|
|
|
return message_str or detail or fallback
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _github_post(path: str, token: str, *, json: dict[str, Any]) -> Any:
|
|
|
|
|
async with httpx.AsyncClient(timeout=_GITHUB_TIMEOUT) as client:
|
|
|
|
|
response = await client.post(
|
|
|
|
|
f"{_GITHUB_API}{path}", headers=github_headers(token), json=json
|
|
|
|
|
)
|
|
|
|
|
if response.status_code >= 400:
|
|
|
|
|
message = _github_error_message(response)
|
|
|
|
|
logger.warning("GitHub POST %s failed: %s %s", path, response.status_code, message)
|
|
|
|
|
# Pass 4xx through verbatim (422 = line not in diff, 403 = perms); collapse
|
|
|
|
|
# 5xx to a 502 so a GitHub outage doesn't masquerade as a client error.
|
|
|
|
|
raise HTTPException(response.status_code if response.status_code < 500 else 502, message)
|
|
|
|
|
return response.json()
|
|
|
|
|
|
|
|
|
|
|
2026-06-11 16:11:10 -07:00
|
|
|
def reviewer_thread_id(owner: str, repo: str, pr_number: int) -> str:
|
|
|
|
|
import uuid
|
|
|
|
|
|
|
|
|
|
stable_key = f"{owner}/{repo}/pr/{pr_number}/reviewer"
|
|
|
|
|
return str(uuid.uuid5(uuid.NAMESPACE_URL, stable_key))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _findings_list(metadata: dict[str, Any]) -> list[dict[str, Any]]:
|
|
|
|
|
findings = metadata.get("findings")
|
|
|
|
|
if not isinstance(findings, list):
|
|
|
|
|
return []
|
|
|
|
|
return [f for f in findings if isinstance(f, dict) and isinstance(f.get("id"), str)]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _serialize_finding(finding: dict[str, Any], head_sha: str | None) -> dict[str, Any]:
|
|
|
|
|
last_confirmed = finding.get("last_confirmed_sha")
|
|
|
|
|
outdated = bool(
|
|
|
|
|
head_sha
|
|
|
|
|
and isinstance(last_confirmed, str)
|
|
|
|
|
and last_confirmed
|
|
|
|
|
and last_confirmed != head_sha
|
|
|
|
|
)
|
|
|
|
|
interactions = finding.get("interactions")
|
|
|
|
|
return {
|
|
|
|
|
"id": finding.get("id"),
|
|
|
|
|
"severity": finding.get("severity", "low"),
|
|
|
|
|
"confidence": finding.get("confidence", "medium"),
|
|
|
|
|
"category": finding.get("category", ""),
|
|
|
|
|
"title": finding.get("title") or "",
|
|
|
|
|
"description": finding.get("description", ""),
|
|
|
|
|
"suggestion": finding.get("suggestion"),
|
|
|
|
|
"file": finding.get("file", ""),
|
|
|
|
|
"start_line": finding.get("start_line"),
|
|
|
|
|
"end_line": finding.get("end_line"),
|
|
|
|
|
"side": finding.get("side", "RIGHT"),
|
|
|
|
|
"in_diff": bool(finding.get("in_diff", True)),
|
|
|
|
|
"status": finding.get("status", "open"),
|
|
|
|
|
"outdated": outdated,
|
|
|
|
|
"resolution_note": finding.get("resolution_note"),
|
|
|
|
|
"diff_hunk": finding.get("diff_hunk"),
|
|
|
|
|
"github_thread_resolved": bool(finding.get("github_thread_resolved")),
|
|
|
|
|
"github_review_comment_id": (
|
|
|
|
|
finding["github_review_comment_id"]
|
|
|
|
|
if isinstance(finding.get("github_review_comment_id"), int)
|
|
|
|
|
else None
|
|
|
|
|
),
|
|
|
|
|
"interactions": interactions if isinstance(interactions, list) else [],
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_BUG_SEVERITIES = frozenset({"high", "critical"})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def classify_finding(finding: dict[str, Any]) -> Literal["bug", "investigate", "informational"]:
|
|
|
|
|
"""Map our severity/confidence model onto the UI's Bugs/Flags split."""
|
|
|
|
|
severity = finding.get("severity", "low")
|
|
|
|
|
confidence = finding.get("confidence", "medium")
|
|
|
|
|
if severity in _BUG_SEVERITIES and confidence == "high":
|
|
|
|
|
return "bug"
|
|
|
|
|
if severity != "low":
|
|
|
|
|
return "investigate"
|
|
|
|
|
return "informational"
|
|
|
|
|
|
|
|
|
|
|
feat: AI-sorted PR review view with diff grouping (#1544)
* feat: AI-sorted PR review view with diff grouping
Group a PR's changed files into a logical top-to-bottom walkthrough via a best-effort structured-output LLM pass, kicked off concurrently with the reviewer run (~0 added latency) and persisted on reviewer thread metadata. Results render in the review UI behind an AI sorted / file tree toggle that persists across PRs; the view falls back to the file tree when groups are absent or stale.
Adds a grouping-model team default (inherits the Reviewer subagent model when unset) and the admin RolePicker for it.
* feat(reviews): richer AI-sorted explanations + sidebar polish
Sidebar group rows get Devin-style spacing (dividers, padding), a per-group file list (click a file to jump to its diff), inline-code chips in titles, and an accent Read explanation link.
Group explanations are now rich markdown: the grouping prompt feeds per-hunk line ranges and asks for inline code, a short code block, and [path:line](#loc=...) references. The Markdown renderer turns those #loc= links into in-page buttons that scroll the diff to the hunk and highlight the range, reusing the existing selectedLines path.
* fix(reviews): drop stale diff groups from the AI-sorted view
When groups were generated for a previous head, a persisted "ai" view in localStorage still rendered the outdated walkthrough. groupedView now returns null on diff_groups_stale, so the file-tree fallback is used and the view toggle hides until fresh groups arrive.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-16 13:59:37 -07:00
|
|
|
def _serialize_diff_groups(
|
|
|
|
|
metadata: dict[str, Any], head_sha: str
|
|
|
|
|
) -> tuple[list[dict[str, Any]], bool]:
|
|
|
|
|
"""Serialize the persisted ``diff_groups`` for the AI sorted view.
|
|
|
|
|
|
|
|
|
|
Returns ``(groups, stale)`` where each group carries a 1-based ``index``
|
|
|
|
|
and validated fields, and ``stale`` is True when the groups were generated
|
|
|
|
|
for a different head SHA than the one currently being rendered.
|
|
|
|
|
"""
|
|
|
|
|
raw = metadata.get("diff_groups")
|
|
|
|
|
if not isinstance(raw, dict):
|
|
|
|
|
return [], False
|
|
|
|
|
raw_groups = raw.get("groups")
|
|
|
|
|
if not isinstance(raw_groups, list):
|
|
|
|
|
return [], False
|
|
|
|
|
groups: list[dict[str, Any]] = []
|
|
|
|
|
for group in raw_groups:
|
|
|
|
|
if not isinstance(group, dict):
|
|
|
|
|
continue
|
|
|
|
|
title = group.get("title")
|
|
|
|
|
if not isinstance(title, str) or not title.strip():
|
|
|
|
|
continue
|
|
|
|
|
files = [f for f in (group.get("files") or []) if isinstance(f, str) and f]
|
|
|
|
|
if not files:
|
|
|
|
|
continue
|
|
|
|
|
summary = group.get("summary")
|
|
|
|
|
groups.append(
|
|
|
|
|
{
|
|
|
|
|
"index": len(groups) + 1,
|
|
|
|
|
"title": title.strip(),
|
|
|
|
|
"summary": summary.strip() if isinstance(summary, str) else "",
|
|
|
|
|
"files": files,
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
groups_head = raw.get("head_sha")
|
|
|
|
|
stale = bool(
|
|
|
|
|
head_sha and isinstance(groups_head, str) and groups_head and groups_head != head_sha
|
|
|
|
|
)
|
|
|
|
|
return groups, stale
|
|
|
|
|
|
|
|
|
|
|
2026-06-11 16:11:10 -07:00
|
|
|
def _finding_counts(findings: list[dict[str, Any]]) -> dict[str, int]:
|
|
|
|
|
counts = {"open": 0, "resolved": 0, "dismissed": 0, "bugs": 0, "flags": 0}
|
|
|
|
|
for finding in findings:
|
|
|
|
|
status = finding.get("status", "open")
|
|
|
|
|
if status in counts:
|
|
|
|
|
counts[status] += 1
|
|
|
|
|
if status == "open":
|
|
|
|
|
if classify_finding(finding) == "bug":
|
|
|
|
|
counts["bugs"] += 1
|
|
|
|
|
else:
|
|
|
|
|
counts["flags"] += 1
|
|
|
|
|
return counts
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _run_status(thread: dict[str, Any], metadata: dict[str, Any]) -> str:
|
|
|
|
|
if thread.get("status") == "busy":
|
|
|
|
|
return "running"
|
|
|
|
|
latest = metadata.get("latest_run_status")
|
|
|
|
|
if latest in {"pending", "running"}:
|
|
|
|
|
return "running"
|
|
|
|
|
if latest in {"error", "failed", "timeout", "interrupted"}:
|
|
|
|
|
return "error"
|
|
|
|
|
return "idle"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _thread_review_summary(thread: dict[str, Any]) -> dict[str, Any] | None:
|
|
|
|
|
metadata = thread.get("metadata") if isinstance(thread.get("metadata"), dict) else {}
|
|
|
|
|
pr = metadata.get("pr")
|
|
|
|
|
if not isinstance(pr, dict):
|
|
|
|
|
return None
|
|
|
|
|
owner = pr.get("owner")
|
|
|
|
|
name = pr.get("name")
|
|
|
|
|
number = pr.get("number")
|
|
|
|
|
if not (isinstance(owner, str) and isinstance(name, str) and isinstance(number, int)):
|
|
|
|
|
return None
|
|
|
|
|
findings = _findings_list(metadata)
|
|
|
|
|
updated_at = thread.get("updated_at")
|
|
|
|
|
return {
|
|
|
|
|
"thread_id": thread.get("thread_id"),
|
|
|
|
|
"owner": owner,
|
|
|
|
|
"repo": name,
|
|
|
|
|
"full_name": f"{owner}/{name}",
|
|
|
|
|
"number": number,
|
|
|
|
|
"title": pr.get("title") or f"PR #{number}",
|
|
|
|
|
"url": pr.get("url") or f"https://github.com/{owner}/{name}/pull/{number}",
|
|
|
|
|
"head_ref": pr.get("head_ref") or "",
|
|
|
|
|
"base_ref": pr.get("base_ref") or "",
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
"author": pr.get("author") if isinstance(pr.get("author"), str) else "",
|
2026-06-11 16:11:10 -07:00
|
|
|
"head_sha": metadata.get("head_sha") or "",
|
|
|
|
|
"watch": bool(metadata.get("watch")),
|
|
|
|
|
"status": _run_status(thread, metadata),
|
|
|
|
|
"counts": _finding_counts(findings),
|
|
|
|
|
"updated_at": updated_at if isinstance(updated_at, str) else None,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def list_reviews(
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
limit: int = 20,
|
2026-06-11 16:11:10 -07:00
|
|
|
*,
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
offset: int = 0,
|
|
|
|
|
author: str | None = None,
|
2026-06-11 16:11:10 -07:00
|
|
|
is_accessible: Callable[[dict[str, Any]], Awaitable[bool]] | None = None,
|
|
|
|
|
page_size: int = 100,
|
|
|
|
|
max_scan: int = 1000,
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
) -> tuple[list[dict[str, Any]], bool]:
|
2026-06-11 16:11:10 -07:00
|
|
|
"""List review summaries, newest first.
|
|
|
|
|
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
Returns ``(summaries, has_more)`` where the summaries are the page at
|
|
|
|
|
``offset`` (counted in accessible, filter-matching records) and
|
|
|
|
|
``has_more`` says whether at least one more record exists past it.
|
|
|
|
|
|
2026-06-12 14:14:50 -07:00
|
|
|
``author`` is pushed into the ``threads.search`` metadata filter
|
|
|
|
|
(``pr.author`` containment), so the "My PRs" tab only fetches the user's
|
|
|
|
|
own reviewer threads instead of scanning the whole population in Python.
|
|
|
|
|
|
2026-06-11 16:11:10 -07:00
|
|
|
When ``is_accessible`` is given, keeps paging through reviewer threads
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
until enough accessible summaries are collected (or ``max_scan`` threads
|
|
|
|
|
have been examined), so inaccessible records don't crowd accessible ones
|
2026-06-12 14:14:50 -07:00
|
|
|
out of a single fixed-size page.
|
2026-06-11 16:11:10 -07:00
|
|
|
"""
|
|
|
|
|
client = langgraph_client()
|
2026-06-12 14:14:50 -07:00
|
|
|
search_metadata: dict[str, Any] = {"kind": REVIEWER_THREAD_KIND}
|
|
|
|
|
if author is not None:
|
|
|
|
|
search_metadata["pr"] = {"author": author}
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
needed = offset + limit + 1
|
2026-06-11 16:11:10 -07:00
|
|
|
summaries: list[dict[str, Any]] = []
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
scan_offset = 0
|
|
|
|
|
while len(summaries) < needed and scan_offset < max_scan:
|
2026-06-11 16:11:10 -07:00
|
|
|
threads = await client.threads.search(
|
2026-06-12 14:14:50 -07:00
|
|
|
metadata=search_metadata,
|
2026-06-11 16:11:10 -07:00
|
|
|
limit=page_size,
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
offset=scan_offset,
|
2026-06-11 16:11:10 -07:00
|
|
|
sort_by="updated_at",
|
|
|
|
|
sort_order="desc",
|
|
|
|
|
)
|
|
|
|
|
if not threads:
|
|
|
|
|
break
|
|
|
|
|
for thread in threads:
|
|
|
|
|
if not isinstance(thread, dict):
|
|
|
|
|
continue
|
|
|
|
|
summary = _thread_review_summary(thread)
|
|
|
|
|
if not summary:
|
|
|
|
|
continue
|
|
|
|
|
if is_accessible is not None and not await is_accessible(summary):
|
|
|
|
|
continue
|
|
|
|
|
summaries.append(summary)
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
if len(summaries) >= needed:
|
2026-06-11 16:11:10 -07:00
|
|
|
break
|
|
|
|
|
if len(threads) < page_size:
|
|
|
|
|
break
|
fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)
* fix: Reviews tab — anchored finding card, paginated list, file tree truncation
- Finding card now tracks the diff anchor while scrolling instead of staying
frozen in the viewport; auto-hides when its diff card collapses (including
collapse via mark-as-viewed) and on click outside
- Checks section capped with max height + scroll
- /reviews paginated (page size 20) with has_more, filtered to the current
user's PRs by default with an All toggle; PR author login now stored in
reviewer thread metadata
- File tree truncation marker overlapped filenames because the sidebar bg
was transparent; use the opaque sidebar color
* fix: finding card tracks anchor 1:1 while scrolling
Drop the vertical viewport clamp — it pinned the card at the clamp
boundary while the highlighted lines kept scrolling, breaking the
attachment.
* fix: anchor finding card with Base UI popover
Replace manual fixed-position tracking (laggy: setState per scroll
frame) with a Popover anchored to the finding's diff row. Floating UI
tracks the anchor outside React renders, so the card moves 1:1 with
the content and scrolls out of view with it. Unanchored findings keep
the fixed top-right card.
* fix: lock finding card to diff scroll
Replace the Base UI popover (async repositioning, paints a frame behind
native scroll) with a card absolutely positioned inside the scroll
container, so it scrolls with the diff in the same compositor frame.
Scroll moves to the ReviewBody root, side panel becomes sticky.
Position recomputes only on layout shifts via ResizeObserver.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 17:52:20 -07:00
|
|
|
scan_offset += page_size
|
|
|
|
|
page = summaries[offset : offset + limit]
|
|
|
|
|
return page, len(summaries) > offset + limit
|
2026-06-11 16:11:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def _user_ref(value: Any) -> dict[str, Any] | None:
|
|
|
|
|
if not isinstance(value, dict):
|
|
|
|
|
return None
|
|
|
|
|
login = value.get("login")
|
|
|
|
|
if not isinstance(login, str):
|
|
|
|
|
return None
|
|
|
|
|
return {"login": login, "avatar_url": value.get("avatar_url")}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _serialize_pr_details(payload: dict[str, Any]) -> dict[str, Any]:
|
|
|
|
|
labels = payload.get("labels")
|
|
|
|
|
state = payload.get("state")
|
|
|
|
|
if payload.get("merged"):
|
|
|
|
|
state = "merged"
|
|
|
|
|
elif payload.get("draft"):
|
|
|
|
|
state = "draft"
|
|
|
|
|
return {
|
|
|
|
|
"state": state if isinstance(state, str) else "open",
|
|
|
|
|
"title": payload.get("title") or "",
|
|
|
|
|
"body": payload.get("body") or "",
|
|
|
|
|
"additions": payload.get("additions") or 0,
|
|
|
|
|
"deletions": payload.get("deletions") or 0,
|
|
|
|
|
"changed_files": payload.get("changed_files") or 0,
|
|
|
|
|
"commits": payload.get("commits") or 0,
|
|
|
|
|
"head_sha": (payload.get("head") or {}).get("sha") or "",
|
|
|
|
|
"head_ref": (payload.get("head") or {}).get("ref") or "",
|
|
|
|
|
"base_ref": (payload.get("base") or {}).get("ref") or "",
|
|
|
|
|
"author": _user_ref(payload.get("user")),
|
|
|
|
|
"assignees": [
|
|
|
|
|
user
|
|
|
|
|
for user in (_user_ref(value) for value in payload.get("assignees") or [])
|
|
|
|
|
if user is not None
|
|
|
|
|
],
|
|
|
|
|
"requested_reviewers": [
|
|
|
|
|
user
|
|
|
|
|
for user in (_user_ref(value) for value in payload.get("requested_reviewers") or [])
|
|
|
|
|
if user is not None
|
|
|
|
|
],
|
|
|
|
|
"labels": [
|
|
|
|
|
{"name": label.get("name"), "color": label.get("color")}
|
|
|
|
|
for label in (labels if isinstance(labels, list) else [])
|
|
|
|
|
if isinstance(label, dict) and isinstance(label.get("name"), str)
|
|
|
|
|
],
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _fetch_check_runs(owner: str, repo: str, sha: str, token: str) -> list[dict[str, Any]]:
|
|
|
|
|
if not sha:
|
|
|
|
|
return []
|
|
|
|
|
try:
|
|
|
|
|
payload = await _github_get(
|
|
|
|
|
f"/repos/{owner}/{repo}/commits/{sha}/check-runs",
|
|
|
|
|
token,
|
|
|
|
|
params={"per_page": 50},
|
|
|
|
|
)
|
|
|
|
|
except HTTPException:
|
|
|
|
|
return []
|
|
|
|
|
runs = payload.get("check_runs") if isinstance(payload, dict) else None
|
|
|
|
|
out: list[dict[str, Any]] = []
|
|
|
|
|
for run in runs if isinstance(runs, list) else []:
|
|
|
|
|
if not isinstance(run, dict):
|
|
|
|
|
continue
|
|
|
|
|
out.append(
|
|
|
|
|
{
|
|
|
|
|
"name": run.get("name") or "",
|
|
|
|
|
"status": run.get("status") or "",
|
|
|
|
|
"conclusion": run.get("conclusion"),
|
|
|
|
|
"url": run.get("html_url"),
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
return out
|
|
|
|
|
|
|
|
|
|
|
2026-06-23 12:32:10 -07:00
|
|
|
async def get_pr_head_sha(owner: str, repo: str, pr_number: int) -> str:
|
|
|
|
|
"""Return the PR's current head SHA from GitHub, or "" if unavailable.
|
|
|
|
|
|
|
|
|
|
A lightweight alternative to :func:`get_review` for callers that only need to
|
|
|
|
|
detect whether the PR head has moved (e.g. the chat staleness check).
|
|
|
|
|
"""
|
|
|
|
|
try:
|
|
|
|
|
token = await _require_app_token()
|
|
|
|
|
payload = await _github_get(f"/repos/{owner}/{repo}/pulls/{pr_number}", token)
|
|
|
|
|
except HTTPException:
|
|
|
|
|
return ""
|
|
|
|
|
head = payload.get("head") if isinstance(payload, dict) else None
|
|
|
|
|
sha = head.get("sha") if isinstance(head, dict) else None
|
|
|
|
|
return sha if isinstance(sha, str) else ""
|
|
|
|
|
|
|
|
|
|
|
feat: inline PR comments in the reviews UI (#1600)
* feat: inline PR comments in the reviews UI
Click the diff gutter "+" on a line to open an inline comment composer
(rendered like the finding card via a Pierre annotation); submitting
posts a real inline PR review comment as the signed-in user through a
new POST /reviews/{owner}/{repo}/{number}/comments. The "+" press-drag →
"Add to Chat" selection path is unchanged.
* feat: GitHub-parity comment box, PR comments dropdown, collapse nav
- Comment composer now mirrors GitHub's box: Write/Preview tabs (markdown
rendered via the existing Markdown component) and a markdown toolbar
(heading, bold, italic, quote, code, link, bulleted/numbered/task list).
- Surface other people's inline PR comments in a Devin-style dropdown in the
review header (search + link to the thread on GitHub). New
GET /reviews/{owner}/{repo}/{number}/comments lists them and flags the
reviewer's own (marker-bearing) comments so they're filtered out.
- Collapse the global nav by default on a review detail page, restoring the
prior preference on leave.
* feat: bigger comment-toolbar icons; open dropdown comments inline
- Enlarge the markdown toolbar glyphs (Phosphor) in the comment composer —
they were rendering at 10px.
- Clicking a comment in the PR comments dropdown now opens it inline in the
diff as a read-only finding-style card (InlineComment), scrolling its line
into view, instead of navigating to GitHub. Falls back to GitHub when the
comment's file/line isn't in the current diff.
* fix: drive "Add to Chat" from native text selection
The gutter "+" is now comment-only; wiring its click to the composer
conflicted with its old double-duty as the drag-to-select handle, which
broke selection → "Add to Chat". Switch to Devin's model: disable Pierre's
interactive line selection and instead map a native text highlight in the
diff to a line range (via the data-line / data-line-type attributes Pierre
stamps on each line, read from the diff's open shadow root) to show the
"Add to Chat" popup. ⌘L and the existing attachment/popup path are unchanged.
* feat: gutter "+" drag selects a range for multi-line comments
Re-enable Pierre's gutter line selection so dragging the "+" down the
gutter comments across a range (click still comments on a single line);
onLineSelectionEnd routes the range to the composer. Native code-text
selection still drives "Add to Chat" — Pierre only line-selects from the
gutter, and onLineSelectionEnd bails when a native text selection is
present, so a code highlight never opens the composer.
* fix: keep the range highlighted while its comment composer is open
Previously opening the composer cleared the selection, so the lines being
commented on lost their highlight. Drive the controlled selection from the
open comment draft's range so the rows stay highlighted until the composer
is closed.
* fix: address PR review — paginate comments, fall back for outdated ones
- list_review_comments now pages through all PR review comments (bounded by
_MAX_REVIEW_COMMENT_PAGES) instead of returning only the first 100, so older
comments still show in the dropdown.
- Surface GitHub's outdated flag (position == null) as is_outdated; opening such
a comment (or one whose line isn't in the diff) now opens it on GitHub instead
of silently rendering nothing, plus a timeout fallback if the annotation never
mounts (e.g. collapsed context).
2026-06-23 16:01:46 -07:00
|
|
|
async def create_review_comment(
|
|
|
|
|
owner: str,
|
|
|
|
|
repo: str,
|
|
|
|
|
pr_number: int,
|
|
|
|
|
*,
|
|
|
|
|
token: str,
|
|
|
|
|
path: str,
|
|
|
|
|
line: int,
|
|
|
|
|
side: Literal["LEFT", "RIGHT"],
|
|
|
|
|
body: str,
|
|
|
|
|
start_line: int | None = None,
|
|
|
|
|
start_side: Literal["LEFT", "RIGHT"] | None = None,
|
|
|
|
|
) -> dict[str, Any]:
|
|
|
|
|
"""Post a single inline review comment to a PR using the caller's token.
|
|
|
|
|
|
|
|
|
|
Unlike the reviewer agent (which batches comments into one review via the App
|
|
|
|
|
token), this posts a standalone comment immediately, authored by the signed-in
|
|
|
|
|
user. ``commit_id`` is the PR's live head SHA. GitHub errors surface verbatim so
|
|
|
|
|
the UI can explain a 422 (line not part of the diff) or 403 (missing permission).
|
|
|
|
|
"""
|
|
|
|
|
head_sha = await get_pr_head_sha(owner, repo, pr_number)
|
|
|
|
|
if not head_sha:
|
|
|
|
|
raise HTTPException(502, "could not resolve PR head commit")
|
|
|
|
|
payload: dict[str, Any] = {
|
|
|
|
|
"body": body,
|
|
|
|
|
"commit_id": head_sha,
|
|
|
|
|
"path": path,
|
|
|
|
|
"line": line,
|
|
|
|
|
"side": side,
|
|
|
|
|
}
|
|
|
|
|
# GitHub forbids multi-line ranges that span sides; only add the range start
|
|
|
|
|
# when it is a distinct earlier line on the same side.
|
|
|
|
|
if start_line is not None and start_line != line:
|
|
|
|
|
payload["start_line"] = start_line
|
|
|
|
|
payload["start_side"] = start_side or side
|
|
|
|
|
return await _github_post(
|
|
|
|
|
f"/repos/{owner}/{repo}/pulls/{pr_number}/comments", token, json=payload
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_HTML_COMMENT_RE = re.compile(r"<!--.*?-->", re.DOTALL)
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
# Inline comments the reviewer posts carry this hidden marker (see review.publish).
|
feat: inline PR comments in the reviews UI (#1600)
* feat: inline PR comments in the reviews UI
Click the diff gutter "+" on a line to open an inline comment composer
(rendered like the finding card via a Pierre annotation); submitting
posts a real inline PR review comment as the signed-in user through a
new POST /reviews/{owner}/{repo}/{number}/comments. The "+" press-drag →
"Add to Chat" selection path is unchanged.
* feat: GitHub-parity comment box, PR comments dropdown, collapse nav
- Comment composer now mirrors GitHub's box: Write/Preview tabs (markdown
rendered via the existing Markdown component) and a markdown toolbar
(heading, bold, italic, quote, code, link, bulleted/numbered/task list).
- Surface other people's inline PR comments in a Devin-style dropdown in the
review header (search + link to the thread on GitHub). New
GET /reviews/{owner}/{repo}/{number}/comments lists them and flags the
reviewer's own (marker-bearing) comments so they're filtered out.
- Collapse the global nav by default on a review detail page, restoring the
prior preference on leave.
* feat: bigger comment-toolbar icons; open dropdown comments inline
- Enlarge the markdown toolbar glyphs (Phosphor) in the comment composer —
they were rendering at 10px.
- Clicking a comment in the PR comments dropdown now opens it inline in the
diff as a read-only finding-style card (InlineComment), scrolling its line
into view, instead of navigating to GitHub. Falls back to GitHub when the
comment's file/line isn't in the current diff.
* fix: drive "Add to Chat" from native text selection
The gutter "+" is now comment-only; wiring its click to the composer
conflicted with its old double-duty as the drag-to-select handle, which
broke selection → "Add to Chat". Switch to Devin's model: disable Pierre's
interactive line selection and instead map a native text highlight in the
diff to a line range (via the data-line / data-line-type attributes Pierre
stamps on each line, read from the diff's open shadow root) to show the
"Add to Chat" popup. ⌘L and the existing attachment/popup path are unchanged.
* feat: gutter "+" drag selects a range for multi-line comments
Re-enable Pierre's gutter line selection so dragging the "+" down the
gutter comments across a range (click still comments on a single line);
onLineSelectionEnd routes the range to the composer. Native code-text
selection still drives "Add to Chat" — Pierre only line-selects from the
gutter, and onLineSelectionEnd bails when a native text selection is
present, so a code highlight never opens the composer.
* fix: keep the range highlighted while its comment composer is open
Previously opening the composer cleared the selection, so the lines being
commented on lost their highlight. Drive the controlled selection from the
open comment draft's range so the rows stay highlighted until the composer
is closed.
* fix: address PR review — paginate comments, fall back for outdated ones
- list_review_comments now pages through all PR review comments (bounded by
_MAX_REVIEW_COMMENT_PAGES) instead of returning only the first 100, so older
comments still show in the dropdown.
- Surface GitHub's outdated flag (position == null) as is_outdated; opening such
a comment (or one whose line isn't in the diff) now opens it on GitHub instead
of silently rendering nothing, plus a timeout fallback if the annotation never
mounts (e.g. collapsed context).
2026-06-23 16:01:46 -07:00
|
|
|
_OPEN_SWE_COMMENT_RE = re.compile(r"<!--\s*open-swe-review-comment\b")
|
|
|
|
|
_REVIEW_COMMENTS_PER_PAGE = 100
|
|
|
|
|
# Bound the fetch so a pathological PR can't trigger unbounded paging (~2000 comments).
|
|
|
|
|
_MAX_REVIEW_COMMENT_PAGES = 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _clean_comment_body(body: str) -> str:
|
|
|
|
|
return _HTML_COMMENT_RE.sub("", body).strip()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _normalize_review_comment(item: dict[str, Any]) -> dict[str, Any]:
|
|
|
|
|
body = item.get("body") if isinstance(item.get("body"), str) else ""
|
|
|
|
|
user = item.get("user") if isinstance(item.get("user"), dict) else {}
|
|
|
|
|
line = item.get("line")
|
|
|
|
|
if not isinstance(line, int):
|
|
|
|
|
original = item.get("original_line")
|
|
|
|
|
line = original if isinstance(original, int) else None
|
|
|
|
|
return {
|
|
|
|
|
"id": item.get("id"),
|
|
|
|
|
"author": user.get("login") if isinstance(user.get("login"), str) else "",
|
|
|
|
|
"author_avatar_url": (
|
|
|
|
|
user.get("avatar_url") if isinstance(user.get("avatar_url"), str) else ""
|
|
|
|
|
),
|
|
|
|
|
"path": item.get("path") if isinstance(item.get("path"), str) else "",
|
|
|
|
|
"line": line,
|
|
|
|
|
"side": item.get("side") if item.get("side") in ("LEFT", "RIGHT") else "RIGHT",
|
|
|
|
|
"body": _clean_comment_body(body),
|
|
|
|
|
"html_url": item.get("html_url") if isinstance(item.get("html_url"), str) else "",
|
|
|
|
|
"created_at": item.get("created_at") if isinstance(item.get("created_at"), str) else "",
|
|
|
|
|
"is_open_swe": bool(_OPEN_SWE_COMMENT_RE.search(body)),
|
|
|
|
|
# GitHub nulls `position` when the line no longer appears in the current
|
|
|
|
|
# diff — i.e. the comment is outdated and can't be rendered inline.
|
|
|
|
|
"is_outdated": not isinstance(item.get("position"), int),
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def list_review_comments(owner: str, repo: str, pr_number: int) -> dict[str, Any]:
|
|
|
|
|
"""List inline review comments on a PR (newest first), normalized for the UI.
|
|
|
|
|
|
|
|
|
|
Surfaces every inline comment on the PR — including humans' — not just the
|
|
|
|
|
reviewer's findings. ``is_open_swe`` flags the reviewer's own (marker-bearing)
|
|
|
|
|
comments so the UI can separate them from other people's. Pages through the
|
|
|
|
|
full list (bounded by ``_MAX_REVIEW_COMMENT_PAGES``) so older comments aren't
|
|
|
|
|
silently dropped.
|
|
|
|
|
"""
|
|
|
|
|
token = await _require_app_token()
|
|
|
|
|
comments: list[dict[str, Any]] = []
|
|
|
|
|
for page in range(1, _MAX_REVIEW_COMMENT_PAGES + 1):
|
|
|
|
|
raw = await _github_get(
|
|
|
|
|
f"/repos/{owner}/{repo}/pulls/{pr_number}/comments",
|
|
|
|
|
token,
|
|
|
|
|
params={
|
|
|
|
|
"per_page": _REVIEW_COMMENTS_PER_PAGE,
|
|
|
|
|
"page": page,
|
|
|
|
|
"sort": "created",
|
|
|
|
|
"direction": "desc",
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
if not isinstance(raw, list) or not raw:
|
|
|
|
|
break
|
|
|
|
|
comments.extend(_normalize_review_comment(item) for item in raw if isinstance(item, dict))
|
|
|
|
|
if len(raw) < _REVIEW_COMMENTS_PER_PAGE:
|
|
|
|
|
break
|
|
|
|
|
return {"comments": comments}
|
|
|
|
|
|
|
|
|
|
|
2026-06-11 16:11:10 -07:00
|
|
|
async def get_review(owner: str, repo: str, pr_number: int) -> dict[str, Any]:
|
|
|
|
|
thread_id = reviewer_thread_id(owner, repo, pr_number)
|
|
|
|
|
client = langgraph_client()
|
|
|
|
|
try:
|
|
|
|
|
thread = await client.threads.get(thread_id)
|
|
|
|
|
except Exception as exc: # noqa: BLE001
|
|
|
|
|
raise HTTPException(404, "review not found") from exc
|
|
|
|
|
if not isinstance(thread, dict):
|
|
|
|
|
raise HTTPException(404, "review not found")
|
|
|
|
|
metadata = thread.get("metadata") if isinstance(thread.get("metadata"), dict) else {}
|
|
|
|
|
summary = _thread_review_summary(thread)
|
|
|
|
|
if not summary:
|
|
|
|
|
raise HTTPException(404, "review not found")
|
|
|
|
|
|
|
|
|
|
token = await _require_app_token()
|
|
|
|
|
pr_payload = await _github_get(f"/repos/{owner}/{repo}/pulls/{pr_number}", token)
|
|
|
|
|
details = _serialize_pr_details(pr_payload if isinstance(pr_payload, dict) else {})
|
|
|
|
|
head_sha = details["head_sha"] or summary["head_sha"]
|
|
|
|
|
checks = await _fetch_check_runs(owner, repo, head_sha, token)
|
|
|
|
|
|
|
|
|
|
findings = [_serialize_finding(finding, head_sha) for finding in _findings_list(metadata)]
|
|
|
|
|
findings.sort(
|
|
|
|
|
key=lambda f: (
|
|
|
|
|
f["status"] != "open",
|
|
|
|
|
{"bug": 0, "investigate": 1, "informational": 2}[classify_finding(f)],
|
|
|
|
|
f["file"],
|
|
|
|
|
f["start_line"] or 0,
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
for finding in findings:
|
|
|
|
|
finding["group"] = classify_finding(finding)
|
|
|
|
|
|
feat: AI-sorted PR review view with diff grouping (#1544)
* feat: AI-sorted PR review view with diff grouping
Group a PR's changed files into a logical top-to-bottom walkthrough via a best-effort structured-output LLM pass, kicked off concurrently with the reviewer run (~0 added latency) and persisted on reviewer thread metadata. Results render in the review UI behind an AI sorted / file tree toggle that persists across PRs; the view falls back to the file tree when groups are absent or stale.
Adds a grouping-model team default (inherits the Reviewer subagent model when unset) and the admin RolePicker for it.
* feat(reviews): richer AI-sorted explanations + sidebar polish
Sidebar group rows get Devin-style spacing (dividers, padding), a per-group file list (click a file to jump to its diff), inline-code chips in titles, and an accent Read explanation link.
Group explanations are now rich markdown: the grouping prompt feeds per-hunk line ranges and asks for inline code, a short code block, and [path:line](#loc=...) references. The Markdown renderer turns those #loc= links into in-page buttons that scroll the diff to the hunk and highlight the range, reusing the existing selectedLines path.
* fix(reviews): drop stale diff groups from the AI-sorted view
When groups were generated for a previous head, a persisted "ai" view in localStorage still rendered the outdated walkthrough. groupedView now returns null on diff_groups_stale, so the file-tree fallback is used and the view toggle hides until fresh groups arrive.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-16 13:59:37 -07:00
|
|
|
diff_groups, diff_groups_stale = _serialize_diff_groups(metadata, head_sha)
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
**summary,
|
|
|
|
|
"pr": details,
|
|
|
|
|
"checks": checks,
|
|
|
|
|
"findings": findings,
|
|
|
|
|
"diff_groups": diff_groups,
|
|
|
|
|
"diff_groups_stale": diff_groups_stale,
|
|
|
|
|
}
|
2026-06-11 16:11:10 -07:00
|
|
|
|
|
|
|
|
|
2026-06-12 11:03:51 -07:00
|
|
|
async def get_review_diff(owner: str, repo: str, pr_number: int) -> dict[str, Any]:
|
|
|
|
|
"""Return the PR's changed files with full original/modified contents.
|
2026-06-11 16:11:10 -07:00
|
|
|
|
2026-06-12 11:03:51 -07:00
|
|
|
Uses the App installation token so the diff is available regardless of who
|
|
|
|
|
is viewing the review. The client renders these with pierre's MultiFileDiff.
|
2026-06-11 16:11:10 -07:00
|
|
|
"""
|
|
|
|
|
token = await _require_app_token()
|
2026-06-12 11:03:51 -07:00
|
|
|
async with httpx.AsyncClient(headers=github_headers(token), timeout=_GITHUB_TIMEOUT) as client:
|
|
|
|
|
diff = await build_pr_diff_files(client, f"{owner}/{repo}", pr_number)
|
|
|
|
|
files = diff["files"]
|
2026-06-11 16:11:10 -07:00
|
|
|
return {
|
|
|
|
|
"files": files,
|
|
|
|
|
"total_additions": sum(f["additions"] for f in files),
|
|
|
|
|
"total_deletions": sum(f["deletions"] for f in files),
|
2026-06-12 11:03:51 -07:00
|
|
|
"truncated": diff["truncated"],
|
2026-06-11 16:11:10 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
2026-06-22 14:01:06 -07:00
|
|
|
# --- PR description image proxy ----------------------------------------------
|
|
|
|
|
# PR bodies can embed images hosted on GitHub (user-attachment uploads,
|
|
|
|
|
# *.githubusercontent.com). For private repos those URLs require GitHub auth the
|
|
|
|
|
# browser doesn't have, so they render broken. We proxy them through the App
|
|
|
|
|
# installation token. The host allowlist + per-redirect public-IP check guard
|
|
|
|
|
# against SSRF (only GitHub-owned hosts are ever contacted).
|
|
|
|
|
|
|
|
|
|
_ALLOWED_IMAGE_HOST_SUFFIXES = (".githubusercontent.com",)
|
|
|
|
|
_MAX_IMAGE_REDIRECTS = 5
|
|
|
|
|
_MAX_IMAGE_BYTES = 25 * 1024 * 1024
|
|
|
|
|
# Only safe raster formats — SVG (image/svg+xml) can execute script in our
|
|
|
|
|
# origin, so it is never served.
|
|
|
|
|
_ALLOWED_IMAGE_CONTENT_TYPES = frozenset(
|
|
|
|
|
{"image/png", "image/jpeg", "image/gif", "image/webp", "image/avif"}
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _is_allowed_image_url(url: str) -> bool:
|
|
|
|
|
parsed = urlparse(url)
|
|
|
|
|
if parsed.scheme != "https":
|
|
|
|
|
return False
|
|
|
|
|
host = (parsed.hostname or "").lower()
|
|
|
|
|
if not host:
|
|
|
|
|
return False
|
|
|
|
|
if host == "github.com" or host == "www.github.com":
|
|
|
|
|
# On github.com only user-attachment assets are images worth proxying.
|
|
|
|
|
return parsed.path.startswith("/user-attachments/")
|
|
|
|
|
return any(host.endswith(suffix) for suffix in _ALLOWED_IMAGE_HOST_SUFFIXES)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _host_resolves_public(hostname: str) -> bool:
|
|
|
|
|
try:
|
|
|
|
|
addr_infos = socket.getaddrinfo(hostname, None)
|
|
|
|
|
except socket.gaierror:
|
|
|
|
|
return False
|
|
|
|
|
if not addr_infos:
|
|
|
|
|
return False
|
|
|
|
|
for addr_info in addr_infos:
|
|
|
|
|
try:
|
|
|
|
|
ip = ipaddress.ip_address(addr_info[4][0])
|
|
|
|
|
except ValueError:
|
|
|
|
|
return False
|
|
|
|
|
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
|
|
|
|
|
return False
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _validate_image_url(url: str) -> None:
|
|
|
|
|
if not _is_allowed_image_url(url):
|
|
|
|
|
raise HTTPException(400, "image host not allowed")
|
|
|
|
|
hostname = urlparse(url).hostname or ""
|
|
|
|
|
if not _host_resolves_public(hostname):
|
|
|
|
|
raise HTTPException(400, "image host not allowed")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _require_image_in_pr(owner: str, repo: str, pr_number: int, url: str, token: str) -> None:
|
|
|
|
|
"""Bind the requested image to the authorized PR.
|
|
|
|
|
|
|
|
|
|
The proxy fetches with the App installation token, which can read every repo
|
|
|
|
|
the App is installed on. Without this check a caller authorized for one repo
|
|
|
|
|
could proxy an image URL from another private repo (IDOR). Only URLs that
|
|
|
|
|
actually appear in this PR's body are allowed.
|
|
|
|
|
"""
|
|
|
|
|
pr_payload = await _github_get(f"/repos/{owner}/{repo}/pulls/{pr_number}", token)
|
|
|
|
|
body = pr_payload.get("body") or ""
|
|
|
|
|
if url not in body:
|
|
|
|
|
raise HTTPException(403, "image not referenced by this PR")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def proxy_pr_image(owner: str, repo: str, pr_number: int, url: str) -> Response:
|
|
|
|
|
"""Stream a GitHub-hosted PR image through the App token.
|
|
|
|
|
|
|
|
|
|
The URL must appear in the target PR's body (bound to the authorized
|
|
|
|
|
resource), and every URL (including redirect targets) is validated against
|
|
|
|
|
the GitHub host allowlist and a public-IP check before it is contacted.
|
|
|
|
|
"""
|
|
|
|
|
_validate_image_url(url)
|
|
|
|
|
token = await _require_app_token()
|
|
|
|
|
await _require_image_in_pr(owner, repo, pr_number, url, token)
|
|
|
|
|
headers = {"Authorization": f"Bearer {token}", "Accept": "image/*"}
|
|
|
|
|
|
|
|
|
|
current_url = url
|
|
|
|
|
async with httpx.AsyncClient(timeout=_GITHUB_TIMEOUT, follow_redirects=False) as client:
|
|
|
|
|
for _ in range(_MAX_IMAGE_REDIRECTS + 1):
|
|
|
|
|
async with client.stream("GET", current_url, headers=headers) as response:
|
|
|
|
|
if response.is_redirect:
|
|
|
|
|
location = response.headers.get("Location")
|
|
|
|
|
if not location:
|
|
|
|
|
raise HTTPException(502, "image fetch failed (redirect without target)")
|
|
|
|
|
current_url = urljoin(str(response.url), location)
|
|
|
|
|
_validate_image_url(current_url)
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
if response.status_code >= 400:
|
|
|
|
|
raise HTTPException(502, f"image fetch failed ({response.status_code})")
|
|
|
|
|
|
|
|
|
|
content_type = (
|
|
|
|
|
response.headers.get("Content-Type", "").lower().split(";", 1)[0].strip()
|
|
|
|
|
)
|
|
|
|
|
if content_type not in _ALLOWED_IMAGE_CONTENT_TYPES:
|
|
|
|
|
raise HTTPException(415, "unsupported image type")
|
|
|
|
|
|
|
|
|
|
# Stream and abort once over the cap so a large (or lying) upstream
|
|
|
|
|
# can't make the worker buffer the whole file.
|
|
|
|
|
content = bytearray()
|
|
|
|
|
async for chunk in response.aiter_bytes():
|
|
|
|
|
content.extend(chunk)
|
|
|
|
|
if len(content) > _MAX_IMAGE_BYTES:
|
|
|
|
|
raise HTTPException(413, "image too large")
|
|
|
|
|
|
|
|
|
|
return Response(
|
|
|
|
|
content=bytes(content),
|
|
|
|
|
media_type=content_type,
|
|
|
|
|
headers={
|
|
|
|
|
"Cache-Control": "private, max-age=300",
|
|
|
|
|
"X-Content-Type-Options": "nosniff",
|
|
|
|
|
"Content-Security-Policy": "default-src 'none'; sandbox",
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
raise HTTPException(502, "too many redirects fetching image")
|
|
|
|
|
|
|
|
|
|
|
2026-06-11 16:11:10 -07:00
|
|
|
async def trigger_re_review(owner: str, repo: str, pr_number: int, login: str) -> dict[str, Any]:
|
|
|
|
|
from ..utils.slack import GitHubPrRef
|
refactor: split webapp.py into api/ + per-source webhook routes
Plan step C4 (docs/upstream-sync/domain-reorg/reorg-build-plan.md, approved
decisions 1-2): split the 2,590-line agent/webapp.py monolith into
agent/webhooks/common.py (shared verify/dispatch helpers), agent/api/app.py
(composition), agent/api/health.py (/health + /webhooks/run-complete), and
per-source {github,linear,slack,jira,confluence}_routes.py. Atlassian
Connect lifecycle + descriptor routes (/connect/*) fold into
confluence_routes.py; webapp.py becomes the upstream-shaped compatibility
shim (from .api.app import app). langgraph.json http.app stays
agent.webapp:app via the shim.
Fork content, upstream layout: linear/slack route files verified
content-identical to upstream 8356eb34 and taken verbatim; github_routes is
upstream + the fork's CI auto-fix trigger wiring; jira/confluence routes are
fork-only, transformed to the same common.X / service.X module-attribute
style. All signature verification (GitHub HMAC, Slack, Linear
timestamp-freshness, verify_jira_secret + opt-in HMAC/timestamp/IP
allowlist, Connect JWT/qsh), token-attribution gating, TID-COLLIDE-01 repo
binding, _is_repo_auto_review_enabled gates, and public-repo org gate move
unchanged.
Handlers rewired from webapp.X to common.X; test monkeypatch sites across
26 files + conftest.py + e2e/harness.py retargeted to
webhook_common/handler/route modules per upstream's pattern. Residual
agent.webapp importers: only the shim, langgraph.json http.app, Makefile
uvicorn target, and docs (doc-path updates land in C7).
Gates: ruff check + format, pytest --co, full unit (1637 passed), full
Playwright E2E vs real langgraph dev (9/9), residual-importer sweep.
2026-07-17 14:30:05 -04:00
|
|
|
from ..webhooks.github import trigger_pr_review_from_ref
|
2026-06-11 16:11:10 -07:00
|
|
|
|
|
|
|
|
pr_ref = GitHubPrRef(
|
|
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
number=pr_number,
|
|
|
|
|
url=f"https://github.com/{owner}/{repo}/pull/{pr_number}",
|
|
|
|
|
)
|
2026-07-31 12:34:56 -04:00
|
|
|
result = await trigger_pr_review_from_ref(
|
|
|
|
|
pr_ref,
|
|
|
|
|
source="dashboard",
|
|
|
|
|
github_login=login,
|
|
|
|
|
request_verdict=True,
|
|
|
|
|
)
|
2026-06-11 16:11:10 -07:00
|
|
|
if not result.get("success"):
|
|
|
|
|
raise HTTPException(502, str(result.get("error") or "could not trigger review"))
|
|
|
|
|
return result
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
async def dry_run_trace_resolution(owner: str, repo: str, pr_number: int) -> dict[str, Any]:
|
|
|
|
|
"""Resolve a PR to its author coding-agent thread without running a review."""
|
|
|
|
|
from dataclasses import asdict
|
|
|
|
|
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
from ..review.trace_context import resolve_pr_trace
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
from ..utils.github_app import get_github_app_installation_token_with_expiry
|
|
|
|
|
from ..utils.slack import GitHubPrRef
|
refactor: split webapp.py into api/ + per-source webhook routes
Plan step C4 (docs/upstream-sync/domain-reorg/reorg-build-plan.md, approved
decisions 1-2): split the 2,590-line agent/webapp.py monolith into
agent/webhooks/common.py (shared verify/dispatch helpers), agent/api/app.py
(composition), agent/api/health.py (/health + /webhooks/run-complete), and
per-source {github,linear,slack,jira,confluence}_routes.py. Atlassian
Connect lifecycle + descriptor routes (/connect/*) fold into
confluence_routes.py; webapp.py becomes the upstream-shaped compatibility
shim (from .api.app import app). langgraph.json http.app stays
agent.webapp:app via the shim.
Fork content, upstream layout: linear/slack route files verified
content-identical to upstream 8356eb34 and taken verbatim; github_routes is
upstream + the fork's CI auto-fix trigger wiring; jira/confluence routes are
fork-only, transformed to the same common.X / service.X module-attribute
style. All signature verification (GitHub HMAC, Slack, Linear
timestamp-freshness, verify_jira_secret + opt-in HMAC/timestamp/IP
allowlist, Connect JWT/qsh), token-attribution gating, TID-COLLIDE-01 repo
binding, _is_repo_auto_review_enabled gates, and public-repo org gate move
unchanged.
Handlers rewired from webapp.X to common.X; test monkeypatch sites across
26 files + conftest.py + e2e/harness.py retargeted to
webhook_common/handler/route modules per upstream's pattern. Residual
agent.webapp importers: only the shim, langgraph.json http.app, Makefile
uvicorn target, and docs (doc-path updates land in C7).
Gates: ruff check + format, pytest --co, full unit (1637 passed), full
Playwright E2E vs real langgraph dev (9/9), residual-importer sweep.
2026-07-17 14:30:05 -04:00
|
|
|
from ..webhooks.common import fetch_github_pr_metadata
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
|
|
|
|
|
pr_ref = GitHubPrRef(
|
|
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
number=pr_number,
|
|
|
|
|
url=f"https://github.com/{owner}/{repo}/pull/{pr_number}",
|
|
|
|
|
)
|
|
|
|
|
token, _ = await get_github_app_installation_token_with_expiry()
|
|
|
|
|
if not token:
|
|
|
|
|
raise HTTPException(502, "No GitHub App token available")
|
|
|
|
|
pr_metadata = await fetch_github_pr_metadata(pr_ref, token=token)
|
|
|
|
|
if not pr_metadata:
|
|
|
|
|
raise HTTPException(502, "Could not fetch pull request metadata")
|
|
|
|
|
|
|
|
|
|
head = pr_metadata.get("head") or {}
|
|
|
|
|
base = pr_metadata.get("base") or {}
|
|
|
|
|
configurable = {
|
|
|
|
|
"repo": {"owner": owner, "name": repo},
|
|
|
|
|
"pr_number": pr_number,
|
|
|
|
|
"pr_url": pr_metadata.get("html_url") or pr_ref.url,
|
|
|
|
|
"branch_name": head.get("ref", ""),
|
|
|
|
|
"head_sha": head.get("sha", ""),
|
|
|
|
|
"base_sha": base.get("sha", ""),
|
|
|
|
|
}
|
|
|
|
|
return asdict(await resolve_pr_trace(configurable=configurable))
|