* feat: link Slack thread/Linear ticket in PRs and append ticket to title
When opening PRs, include any referenced Slack thread or Linear ticket
in the description and append the resolvable ticket number to the title.
Adds a Slack permalink to the webhook prompt so the agent has a
ready-to-link thread URL.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: use [closes <TICKET>] format in PR title suffix
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: deterministically append source refs to private-repo PRs only
Move the Slack/Linear source-reference linking out of the prompt and into
open_pull_request, gated to private repos so private Slack thread URLs and
Linear identifiers are never published to a public PR. Reverts the prompt
instruction and webhook permalink injection in favor of this server-side append.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
prepare_review_repo is best-effort, but the system prompt unconditionally
told the agent the repo is checked out at the PR head. On a reused sandbox,
a dirty worktree (or a transient fetch failure) makes 'git checkout <sha>'
fail; prep returns False, the old checkout stays in place, and the reviewer
confidently reads stale code — observed as 'I rechecked the current head'
replies quoting pre-push code.
- checkout with --force so leftover worktree state can't block it, verify
HEAD matches the requested sha, tolerate 'git fetch --all' failures
- when prep fails, the prompt now warns the checkout may be stale and tells
the agent to re-fetch/checkout (or fall back to API file contents) before
trusting local files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: track PR lifecycle state per thread for sidebar
Persist a PR's draft/open/merged/closed state on the agent thread and keep
it in sync as PR webhooks fire, so the Agents UI can show per-thread PR
status the way Cursor does. open_pull_request now records the initial
draft/open state and pr_title; thread summaries expose diffStats; and the
PR webhook refreshes pr_state on close/reopen/draft/ready transitions.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: consolidate PR state mapping into shared derive_pr_state helper
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: refresh sandbox GitHub proxy token before mid-run expiry
GitHub App installation tokens expire after exactly 1 hour. The LangSmith
sandbox proxy was configured once at run start with a snapshot of that
token, so runs longer than ~1h hit 401s on every gh/git call. Record the
proxy token's expiry per thread and add a before-model hook that
re-configures the proxy with a fresh token when it nears expiry.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve repo-scoped proxy token on mid-run refresh
Reviewer runs mint a repository-scoped installation token. Record the
repo scope per thread alongside the expiry so the before-model refresh
re-mints a token with the same scope instead of an installation-wide
token, avoiding privilege expansion on long reviewer runs.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update passthrough stub for github_proxy_repositories param
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: keep review check visible on follow-up commits and stop using neutral
The "Open SWE Review" check completed as `neutral` whenever findings were
surfaced, which GitHub renders as a confusing "neutral check" group. Always
complete it as `success` (informational/non-blocking), matching Devin and
Corridor — the finding count stays in the title and findings post as comments.
Also create a fresh check run on the new head SHA in the push re-review path:
GitHub only shows check runs on a PR's current head, so the check vanished
after a follow-up push (and the stale id settled on an outdated commit).
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface settled review check when push leaves diff unchanged
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: report Open SWE Review as a PR check run
Auto-review dispatch now creates an in-progress 'Open SWE Review' check run
on the PR head SHA; publish_review completes it (neutral with findings,
success when clean). An after-agent hook fails the check if the run dies
before publishing. Requires the GitHub App's Checks: Read & write permission;
all calls are best-effort so a missing permission never breaks reviews.
* fix: address review feedback on check-run settling
Keep review_check_run_id when the completion PATCH fails so a later
publish or the after-agent hook can retry instead of hanging the check;
count out-of-diff findings toward the check conclusion.
* fix: retry failed check completion with the real publish conclusion
A transient PATCH failure after a successful publish previously left the
check id for the after-agent hook, which settled it as 'failure'. Persist
the intended result as review_check_pending_result and have the hook
prefer it over the generic failure fallback.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: prep reviewer repo at init and load repo skills
Clone + checkout the PR head during reviewer agent init so SkillsMiddleware
can discover the repo's .agents/skills and .claude/skills from disk at its
one-shot scan, and so the LLM no longer narrates the clone mid-run.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: load reviewer skills from trusted base sha and fetch PR pull ref
Address review findings: skills are now extracted from the PR base sha via
git archive into a dir outside the checkout (prevents PR-authored SKILL.md
prompt injection), and repo prep fetches refs/pull/<n>/head with a strict
checkout so fork PRs fail loudly instead of silently reviewing the default
branch.
* fix: drop ref from skill-extraction log to satisfy CodeQL
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Pull the api-standards skill from the LangSmith Context Hub at reviewer
run start and inject it into the system prompt, gated on the PR adding or
modifying an API surface. Best-effort: failures fall back to no supplement.
Co-authored-by: GowriH-1 <218394553+GowriH-1@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Add conversations.info fetch so a repo:owner/name (or GitHub URL) token
in a Slack channel's topic/purpose pins the channel to a repo, slotting
in just below thread metadata in get_slack_repo_config.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat(reviewer): surface dashboard UI link on PR reviews [INF-0000]
Post a transient "review in progress" comment (with an "Open in Web"
dashboard link) when a reviewer run starts, then delete it once the
review lands. The published review body now carries the same
"Open in Web" link, so the link persists on the review itself.
The transient comment's id is tracked in reviewer thread metadata
(status_comment_id) so it can be deleted on completion.
* refactor(reviewer): inline dashboard URL helper, drop redundant future import [INF-0000]
The bot's numeric noreply (215916821+open-swe[bot]@users.noreply.github.com)
introduced in ae946d1a doesn't resolve to a GitHub account Vercel accepts,
breaking preview deploys on PRs in langchainplus. Revert OPEN_SWE_BOT_EMAIL
to open-swe@users.noreply.github.com.
Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
* feat: add scheduled web agents
Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
* fix: secure scheduled agent repositories
Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
* feat: rebuild scheduled agents as Automations tab
Scrap the inline ScheduledAgentsPanel and replace it with a dedicated
Automations tab: sidebar nav entry, list view with stat cards + empty
state, and a full editor (name, Active toggle, repo, scheduled trigger
picker, agent instructions + model).
* fix: clear collapsed-sidebar button on mobile in Automations
* fix: allow clearing automation repo on update
---------
Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
Reviewer/push runs execute in a worker process, but the GitHub token was
cached by the webhook handler in the API server process — a different
process — so the worker's in-process cache was always cold. resolve_github_token
then failed (User not authenticated / Unknown source: github_push) and only the
app-token fallback kept reviews working, noisily.
The reviewer always acts as the GitHub App (open-swe[bot]), so resolve the
installation token directly at run start, scoped to the repo. This also bypasses
org SAML enforcement that blocks user OAuth tokens. Drop the now-dead
cross-process cache writes in the webhook reviewer-dispatch handlers, and stop
leave_failure_comment raising on the github_push source.
Open SWE Review now runs from automated PR triggers, so drop the old Slack/GitHub review keyword entrypoints and keep PR comments on the regular agent path.
* feat: add Slack Open in Web link
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: skip web link for Slack reviewer runs
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* test: accept include_dashboard_link kwarg in Slack reviewer test double
---------
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: open-swe[bot] <johannes@langchain.dev>
The Co-authored-by trailer and bot git identity used
open-swe@users.noreply.github.com, which resolves to the separate
open-swe *user* account rather than the open-swe[bot] GitHub App.
Switch OPEN_SWE_BOT_EMAIL to the bot's noreply address
(215916821+open-swe[bot]@users.noreply.github.com) so co-author credit
and the fallback author identity point at the bot.
Drive the prompt trailer and sandbox git config from the constant
instead of hardcoding the address.
* fix: scope public reviewer tokens
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: simplify reviewer token wiring; fix push re-scope + red test
- Remove the redundant _check_or_recreate_sandbox_for_proxy /
_refresh_github_proxy_or_recreate_for_proxy wrappers and call the
underlying functions directly (they already default the token to None).
- process_github_push_event: re-scope the GitHub App token when the push
payload lacked repo privacy/id but PR metadata reveals a public repo, so
reviewer.py never proxies a full-installation token for a public PR.
- Clarify the two-token sequence in trigger_pr_review_from_ref.
- Fix pre-existing failing test test_proxy_refresh_failure_recreates_sandbox
and add coverage for _reviewer_token_for_repo + push-event scoping.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: deliver Slack account-link prompt as a visible threaded reply
Blocked Slack users got no prompt at all. Prod logs show chat.postEphemeral
returns ok, but ephemeral messages are silently dropped in Slack's assistant
threads (where Open SWE runs), so the user sees nothing. Post the prompt as a
normal threaded reply instead — the same channel the agent uses to reply.
* fix: deliver Slack auth-failure prompt as a visible threaded reply
leave_failure_comment() tried an ephemeral message first and only fell back
to a thread reply on failure. Ephemeral messages succeed (ok) but are dropped
in Slack's assistant threads, so the fallback never fired and the user saw no
auth-failure prompt. Post the visible threaded reply directly, matching the
account-link prompt fix.
* fix: prompt blocked Slack users with a generic, token-free dashboard link
Addresses the review findings that posting the per-user account-link token /
auth URL in a visible thread lets any channel member bind their GitHub account
to the triggering user's Slack identity.
Drop the per-user signed link entirely. Both the account-link prompt
(_post_account_link_prompt) and the runtime auth-failure prompt
(leave_failure_comment) now post a plain dashboard settings link
(build_settings_url) as a visible threaded reply. The user signs in with GitHub
from their own session and connects Slack via verified OIDC on the settings
page — no secret in the thread, nothing to hijack, and no DM machinery.
* feat: nudge first-time users to connect Slack from the dashboard home
Show a Connect Slack banner on the agents landing page whenever Slack OAuth is
enabled and the user hasn't linked Slack yet. A first-time user (no Slack
mapping) sees it immediately after signing in; it disappears once connected.
* feat: prompt first-time users to connect Slack via a dialog
Replace the inline Connect Slack card on the agents home with a modal dialog
(Base UI). It opens automatically once the mapping query resolves to
"not connected" and closes itself once Slack is linked; "Maybe later" dismisses
it for the session. No new dependency — uses the design system's Base UI.
* copy: frame Slack connect as resolving the user's GitHub account
Drop 'act/reply on your behalf' wording across the connect-Slack dialog, the
Slack thread prompts (blocked + auth-failure), and the settings description.
Connecting Slack lets Open SWE resolve the user's GitHub account when they tag
it in Slack.
Replace the double-attribution PR body footer (_Opened collaboratively by
{user} and open-swe._) with a single Cursor-style footer linking to the
project. Since PRs are now opened as the triggering user, the user no longer
needs to be named in the footer. The commit Co-authored-by trailer is kept.
Legacy footers are migrated on PR updates.
* feat: open Slack-triggered PRs as the triggering user
Route the Slack per-user GitHub token through the dashboard OAuth store
(the backend the self-service link prompt populates) and block runs that
lack a valid user token, prompting the user to (re-)link. Per-user OAuth
now wins over bot-token-only mode for mapped Slack/dashboard users.
Flip commit/PR authorship across all sources: the triggering user is the
commit author (via repo-local git identity using their resolvable GitHub
noreply email) and open-swe[bot] is the Co-authored-by collaborator.
* fix: address PR review — shell-escape commit identity, fix token cache impersonation
- Shell-escape the triggering user's name/email with shlex.quote before
embedding them in the repo-setup `git config` command, so a name like
O'Connor (or a crafted one) can't break or inject into the command.
- Stop consulting the shared thread-metadata token cache in
_resolve_dashboard_user_token. Slack thread ids are shared across the
conversation, so a cached token from a prior triggering user could be
returned for the current github_login. Always resolve by login from the
dashboard OAuth store instead.
* feat: dashboard self-service user mapping + UI cleanup
- Add session-scoped GET/PUT /dashboard/api/my-mapping so users can set their
own work email / Slack member ID (keyed by their GitHub login, source=self).
- Slack account-link prompt now redirects to Profile Settings after auth.
- Rename "My Settings" -> "Profile Settings" and "Cloud Agents" -> "Open SWE
Agent"; remove the Integrations tab/section (folded out, low value for now)
and redirect /integrations to Profile Settings.
- Add a "User mapping" section to Profile Settings (work email used by Slack
and Linear, optional Slack member ID).
- Make dashboard auth cookies scheme-aware: Secure;SameSite=None over HTTPS,
non-Secure;SameSite=Lax over http://localhost so local login works.
* feat: self-service Slack account linking via Sign in with Slack (OIDC)
Replace the spoofable manual work-email/Slack-ID form with a verified
"Sign in with Slack" flow so a logged-in GitHub user can only ever link
their own Slack identity.
- New agent/dashboard/slack_oauth.py: OIDC authorize URL, code exchange,
userInfo identity parse, optional workspace gate, configured check.
- routes.py: session-gated GET /slack/login and /slack/callback that upsert
the mapping from Slack-verified user_id + email (source=slack_oauth).
Remove the spoofable PUT /my-mapping; expose slack_oauth_enabled on /me.
- UI: drop the editable inputs; add a Connect Slack button + status to the
User mapping section.
Admin-managed mappings are unaffected and still resolve at trigger time.
* fix: include GitHub username in collaboration footer
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: clarify legacy footer replacement
Co-authored-by: Johannes du Plessis <51395795+johannes117@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>
* chore: remove legacy mapping + admin profiles section, page user mappings
- Delete the hardcoded github_user_email_map.py and the one-time
POST /admin/user-mappings/import endpoint + Import legacy mapping UI
button (the Store is now the sole source of truth post-import).
- Remove the per-user profiles admin section and its GET/PUT
/admin/profiles endpoints + ProfileForm component; users still manage
their own profile via My Settings.
- Page the user mappings list: /admin/user-mappings now takes
page/page_size and returns {items,total,page,page_size}; the admin UI
shows 20 rows per page with Previous/Next controls.
* Address review: fix stale import-button doc + clamp mappings page on shrink
* Replace hardcoded GitHub-email map with Store-backed user mapping
Move the static GITHUB_USER_EMAIL_MAP to a Store-backed bidirectional
mapping (GitHub login <-> work email <-> optional Slack ID) with an
in-process cache, self-service onboarding, and admin management.
- agent/dashboard/user_mappings.py: Store CRUD + login/email/slack-id
indexes, sync cache readers for hot paths, async fallthrough, and a
bulk_import that preserves existing richer records.
- Migrate all read sites (auth.py, agent_overrides.py, authorship.py,
github_comments.py, webapp.py x2) off the dict.
- Unmapped Slack tags now run on the GitHub App installation token
(use_installation_token_fallback) and get an ephemeral "link your
GitHub account" prompt carrying the Slack id + email via a signed
account-link token threaded through the OAuth state.
- OAuth callback completes a self-service (org-gated) mapping from that
token, falling back to the verified GitHub email.
- Admin CRUD endpoints + one-time legacy import; dashboard UI section.
- Legacy dict retained only as the import payload (no longer read).
Tests: mapping store, account-link round-trip + completion, mapped vs
unmapped Slack flows; existing trust-gate tests updated to prime cache.
* Address review: cold-cache email resolution + stale alias de-indexing
- agent_overrides: add resolve_login_from_email_async that falls through to
the Store on a cold cache; use it at the async repo-resolution call sites
(Slack repo config, Linear comment, owner-metadata) so a mapped user still
resolves to their GitHub login + dashboard default_repo on a fresh worker.
- user_mappings.upsert_mapping: de-index the existing login before re-indexing
so a changed email/Slack id no longer leaves stale aliases resolving to the
login in-process.
- Tests for both fixes; update Slack repo-config test to patch the async resolver.
* Lock dashboard login to GitHub org members
Add an org-membership gate to the dashboard OAuth callback. After
resolving the GitHub login, enforce_org_login_gate(login) checks the
existing ALLOWED_GITHUB_ORGS allowlist before issuing a session.
- Reuses ALLOWED_GITHUB_ORGS (no new config knob) and
is_user_active_org_member (installation-token check, so no extra
OAuth scope and private memberships are visible).
- Fail-open when unset/blank so existing deployments keep working;
fail-closed on API errors.
- Gate runs before the session cookie/token is persisted.
Adds unit tests and documents the behavior in INSTALLATION.md.
* docs: document Organization Members permission required for org login gate
* fix: reset stale sandbox creation sentinel
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: treat SANDBOX_CREATING as a timestamped cross-process lock
Only reset the sentinel when proven stale (older than the creation
timeout); otherwise wait for the worker that holds the lock so a
concurrent run does not create a duplicate sandbox.
* feat(analyzer): outcomes dataset + bootstrap/continual split via skills
Rename the review_style_analyzer graph to `analyzer` and split it into two
modes, plus capture reviewer finding outcomes for continual learning.
- Outcomes dataset: upsert resolved-by-commit (positive), dismissed (false
positive), and GitHub/Slack thumbs findings into a single LangSmith dataset
(openswe-reviewer-outcomes), keyed deterministically per finding+source.
Emit points wired into update_finding, resolve_finding_thread, and the
GitHub/Slack reaction handlers.
- Two playbooks delivered as deepagents skills (bootstrap-repo-analysis,
continual-learning), served as virtual files via a CompositeBackend /skills/
route + StateBackend (seeded into the run files channel at invoke time, never
written to the sandbox). Mode is set by the launcher; continual runs fall
back to the GitHub App installation token.
- Split launcher into start_bootstrap_analysis + start_continual_run; register
a per-repo nightly continual-learning cron when bootstrap completes.
- New read_finding_outcomes tool feeds confirmed/dismissed findings back to the
continual playbook.
Tests for outcome label mapping, skills helper, and cron idempotency.
* fix(analyzer): anchor continual cron runs to a real thread_id
The nightly continual-learning cron is threadless, and get_analyzer
early-returns an empty agent when configurable.thread_id is missing — so
every cron-launched run no-op'd before reading outcomes or saving a refined
prompt. Include the repo's deterministic analyzer thread_id in the continual
run configurable so the run executes; the threadless run carries no message
history, so nightly runs don't accumulate context.
* refactor(analyzer): move cron lifecycle calls out of the review-styles store
Drop the inline `analyzer_cron` imports from review_styles.py (added only to
dodge a circular import) by relocating the cron-trigger calls to the layer
above the store: registration to the save_review_style tool (after a prompt is
saved) and removal to the dashboard delete route. review_styles.py is now a
pure store again with top-level imports only.
* refactor: hoist reviewer_outcomes imports to module level
Move the two inline emit_finding_status_outcome imports introduced in this PR
(update_finding, resolve_finding_thread) to top-level imports. reviewer_outcomes
only depends on langsmith, so there is no circular import to avoid.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: propagate Slack reply errors
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: classify Slack 429 as rate_limited with retry-after
Slack chat.postMessage rate limiting returns HTTP 429, which raise_for_status
turned into a generic http_error and told the agent to retry immediately,
ignoring Slack's retry window. Special-case 429 (threading Retry-After) and
normalize the ratelimited body code before the generic HTTP path so the
existing rate_limited hint actually fires.
---------
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: route PR review requests through agent tool
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: align public repo gate test with agent routing
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: allow app-token PR review requests
Co-authored-by: Johannes du Plessis <51395795+johannes117@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>
* feat(reviewer): inline AGENTS.md into reviewer system prompt
Fetches AGENTS.md from the PR's head_sha via the GitHub contents API
during reviewer setup and inlines it as a "Repository conventions"
block in the system prompt. Mirrors how the per-repo review style
prompt is already wired.
The main agent has long had a mandatory step to read AGENTS.md after
cloning, but the reviewer often skips cloning entirely (it can
`gh pr diff` directly), so it never saw the file. Loading it
deterministically means the reviewer judges findings against the
project's own conventions instead of relying on the model to fetch
the file itself.
* fix(reviewer): fetch AGENTS.md from base_sha, not head_sha
The reviewer inlines AGENTS.md into its system prompt. Reading from
head_sha means a PR author can edit AGENTS.md in the same PR being
reviewed and smuggle instructions like "ignore all bugs" / "publish
no findings" into the reviewer's prompt. Switch to base_sha (the
target branch's pre-PR state, which is trusted) and update the prompt
text to reflect that the contents come from the base, not the head.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat(ui): add Agents chat UI ported from open-swe-app
Introduce a Cursor-style Agents surface separate from the dashboard, with ported chat/diff components and mock thread data until LangGraph APIs land.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(dashboard): wire Agents UI to LangGraph thread APIs
Add dashboard thread list/detail/run/message/stream endpoints with a LangGraph message adapter, dashboard OAuth auth for runs, and TanStack Query hooks replacing mock data.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(dashboard): single agent reply per turn in Agents UI
Use UUID thread IDs LangGraph accepts, skip confirming_completion for
dashboard threads, and merge adapter agent messages so duplicate bubbles
do not render.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(ui): polish Agents UI with floating prompt and layout cleanup
Remove no-op chrome (git panel, headers, sidebar search), port CloudPromptBar
from open-swe-app, and refine chat layout so messages scroll behind the input.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(agent): patch deepagents reducer for None messages on checkpoint replay
LangGraph thread state could 500 when cancelled runs left messages as None.
Apply the reducer guard before graph import, fall back to metadata in the
dashboard API, and adjust Agents prompt bar layout.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(ui): unify sidebar user menu and clean up Agents UI navigation
Extract SidebarUserMenu so the dashboard and Agents sidebars render the
same profile button, drop the redundant Agents nav row in favor of the
existing Back to Agents link, add the open-swe logo header to the Agents
sidebar, flatten the New Agent button, and cap the home screen run list
to keep the prompt input in view.
* feat(ui): resizable/collapsible sidebar shared across dashboard and Agents
Add a useSidebarLayout hook + SidebarFrame wrapper so both sidebars
share a persisted width (default 260px, drag to resize, 200-420 range)
and a collapse toggle that hides the panel and surfaces a floating
reopen button. Also adds a DELETE /threads/{id} endpoint and an X-on-
hover thread delete control in the Agents sidebar.
* feat(ui): instant user message and busy indicator on Agents transition
Stash submitted prompts in sessionStorage, pre-populate the new thread
detail cache, and merge pending prompts into the rendered message list
so the Agents page renders the user bubble plus the existing thinking
spinner immediately instead of flashing a skeleton and "Agent is
starting" while the run boots.
* feat(ui): token-stream agent replies in the Agents thread view
Opt the LangGraph runs into messages-tuple streaming and forward those
events through the existing SSE channel. The frontend now applies
AIMessageChunk deltas directly to the cached thread (cancelling any
in-flight refetch first so optimistic tokens are not clobbered) and
keeps positional pending prompts so the user bubble stays in the right
place while the agent streams its reply.
* fix(dashboard): await threads.join_stream before iterating
threads.join_stream is async def returning an AsyncIterator, so it must
be awaited before async for. The SSE endpoint was raising
TypeError: 'async for' requires an object with __aiter__ method, got
coroutine on every connection.
* fix(dashboard): drop messages-tuple stream_mode that broke thinking-mode tool turns
Setting stream_mode=["values","messages-tuple","updates"] on
runs.create forces langchain_anthropic into streaming, and on the
second model call (after tool execution) its serialized thinking
blocks come back malformed, so Anthropic rejects the request with
'messages.1.content.0.thinking.thinking: Field required'. Revert to
the default stream_mode so claude-opus thinking + tool use runs to
completion. The frontend keeps the messages-event handler in place
as a no-op fallback for when streaming is re-enabled.
* feat(agents): per-thread model picker wired through to the run
Add optional model_id/effort to the create-thread and send-message
request bodies, forward them as agent_model_id/agent_effort in the
LangGraph run configurable, and record the resolved choice in thread
metadata so the UI can show the model the run is actually using.
get_agent now picks the per-thread override last (highest priority over
team default + profile override) and falls back gracefully when it is
absent or unsupported.
The frontend prompt bar becomes a controlled component fed by a
shared useModelOptions hook (options + profile -> defaultSelection).
AgentsHome seeds the picker from the user's profile default; the
thread view seeds from the thread's recorded model/effort and lets
each follow-up retarget the run.
* refactor(ui): align Agents prompt bar layout with open-swe-app PromptBar
Drop the absolute-positioned send button, restore the original
px-4 py-3.5 min-h-[106px] flex-col container, and move the model
picker into a mt-auto pt-2 footer row so the placeholder text and
the model selector share the same horizontal padding.
* chore: fix lint/format CI failures
Remove unused imports and reformat two files flagged by ruff.
* fix(tests): stop messages-reducer patch tests from polluting the suite
Restore agent modules after reducer patch tests and import LangSmithSandbox
from agent.server in proxy refresh tests so isinstance checks stay valid.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: tune reviewer for precision — web/wiki tools + recalibrated prompt
Reviewer agent now has web_search, fetch_url, and http_request alongside the
finding tools, so it can verify library semantics and consult the DeepWiki
auto-generated wiki for public repos (https://deepwiki.com/<owner>/<repo>)
before flagging cross-file or architectural concerns.
Prompt rewritten to push precision over recall:
- explicit severity ladder pushing reviews toward bimodal high/low instead of
defaulting to medium
- ≤200-char description target (gold set averages ~186 chars; we were at ~436)
- mandatory docs / wiki / code lookup before flagging concurrency, security,
or perf — the three categories that dominated false positives
- "do not flag" list covering compiler/linter-catchable nits, speculative
claims without a concrete attacker/interleaving/scale, style preferences
the codebase doesn't share, and test-quality nits on non-test diffs
- smart file-selection guidance for large PRs (deprioritize generated /
vendored / pure-rename hunks)
Eval config switched to openai:gpt-5.5 + high reasoning effort for the next
benchmark run.
* trim prompt
* subagent prompting
* confidence ratings
* added medium
* enforce confidence threshold
* .
* reviewer: precision-tuned prompt + drop confidence gate
Rewrites the reviewer system prompt around a defensibility bar (anchor +
failure mode + maintainer wouldn't say "not a bug"), an explicit do-not-file
list (style nits, speculation, scope-policing, same-bug fan-out), and a
checklist of 10 bug archetypes drawn from a per-PR audit of the eval golden
set. The audit showed 145 FPs in the last eval split ~28% speculative, ~26%
style-nit, ~31% real-but-unscored (mostly same-archetype fan-out); the new
prompt targets each class directly.
Confidence is still recorded on every finding for post-hoc calibration but
no longer gates publication — the audit showed the gate was a no-op (agent
self-rated 65% of findings "high" regardless), and the prompt's defensibility
bar is the actual discipline. Drops CONFIDENCE_ORDER, CONFIDENCE_THRESHOLD,
the confidence_threshold kwarg on filter_findings_for_publish, the
confidence_filtered score_mode, and the min_confidence kwarg on the eval
target's _extract_comments — all dead once the gate is gone.
Also removes the "informational" severity tier from the Severity enum,
SEVERITY_ORDER, and all validators / tests / docstrings. It was reserved for
FYI observations the dataset never rewards.
* benchmax
* adding google provider
* slight steering
* tuning
* more tuning
* fix
* cleanup
* reducing overfitting
* Add per-repo review style profiles and inject them into the reviewer.
Dashboard users can analyze historical PR review feedback per repository,
edit the resulting style guide, and have it loaded from LangGraph Store at
reviewer runtime (including Martian eval runs) keyed by owner/name.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix review style job errors leaking exception details to clients.
Return generic dashboard messages while logging full stack traces server-side.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: tighten reviewer eval workflow
Require the reviewer to verify and dedupe findings before recording them, and make benchmark runs safe to execute against deployed reviewer graphs without posting GitHub reviews.
* chore: move reviewer eval settings to config
Load reviewer benchmark settings from the default eval config file so deployed eval runs do not require a wide CLI surface.
* feat: allow reviewer eval model overrides
Pass reviewer model and reasoning effort from the eval config into reviewer runs so isolated benchmark deployments can test Opus 4.7 high thinking.
* fix: use adaptive thinking for Opus 4.7
Switch Opus 4.7 model overrides to Anthropic adaptive thinking with effort instead of the deprecated budgeted thinking payload rejected by the API.
* refactor: use latest Anthropic effort API
Remove legacy Anthropic budget-token thinking support and route Anthropic efforts through adaptive thinking plus effort.
* revert prompting
* feat: dashboard backend — GitHub OAuth, profile CRUD, admin endpoints
Adds agent/dashboard/ FastAPI router mounted at /dashboard/api covering:
- GitHub App OAuth login → JWT cookie session (cross-domain ready)
- profile CRUD against LangGraph Store with model+effort validation
- admin gate via CONFIGURED_ADMINS
- /repos via /user/installations using the user's encrypted OAuth token
CORS allowlist on webapp.py is opt-in via DASHBOARD_ALLOWED_ORIGINS so the
Vercel-hosted frontend can call the LangSmith deployment with credentials.
* feat: apply dashboard profile model/effort overrides in get_agent
Look up the triggering user's GitHub login from config (direct field or
GITHUB_USER_EMAIL_MAP reverse lookup), read their profile from the Store,
and apply default_model + reasoning_effort to make_model when both are
valid. Effort 'max' is captured on the profile but not yet wired through —
the OpenAI Reasoning Literal doesn't accept it.
* feat: ui/ TanStack Start dashboard for profile config
Scaffolded with the shadcn b7CScJIjA preset (TanStack Start template,
base-ui primitives, Tailwind v4). Three routes:
- /login — Sign in with GitHub (links to /dashboard/api/auth/login)
- /profile — Edit default model, reasoning effort, default repo
- /admin — Admin-only: list users and edit other profiles
API client (src/lib/api.ts) uses credentials: include so the osw_session
cookie set by the OAuth callback rides cross-origin. VITE_DASHBOARD_API_BASE_URL
points at the LangSmith deployment.
Effort options re-render when the model changes; 'max' on Opus 4.7 is
captured on the profile but ignored downstream until anthropic reasoning
is wired through make_model.
* feat: searchable Combobox for default repo picker
Replaces the Select with a base-ui Combobox so users can filter by typing,
the popup is wider than the trigger so full owner/repo names are readable,
and the list caps at max-h-80 to stay on screen.
* fix: address review comments + wire default_repo and Anthropic thinking
Security/correctness fixes from PR review:
* Open redirect: validate `redirect_to` in `/auth/login` against
`DASHBOARD_BASE_URL` + `DASHBOARD_ALLOWED_ORIGINS` before signing it
into the state JWT. Anything off-allowlist falls back to the dashboard
base URL. (PR #1302 r3250054386)
* Login CSRF: bind the OAuth `state` to the requesting browser. At
`/auth/login` we generate a fresh nonce, set it as a short-lived
HttpOnly SameSite=Lax cookie scoped to `/dashboard/api/auth`, and
embed `hash_state_nonce(nonce)` in the state JWT. At `/auth/callback`
we require the cookie nonce to hash-match the state JWT's nonce_hash
(constant-time compare). (PR #1302 r3250054395)
* RMW race in profile vs token writes: split storage into two
namespaces — `["profiles"]` for user-editable settings and
`["oauth_tokens"]` for the encrypted GitHub token. Each upsert now
only writes its own namespace so an in-flight profile save can no
longer clobber a fresh token from a concurrent re-login (and vice
versa). (PR #1302 r3250054393)
* /repos pagination: follow `Link: rel="next"` for both
`/user/installations` and per-installation `/repositories` with
per_page=100, capped at 1000 items. (PR #1302 r3250054401)
Feature wires:
* default_repo: applied as a fallback in `get_slack_repo_config` (after
explicit-repo / thread metadata, before the env defaults) and in the
Linear webhook (after comment-body extraction, before team mapping).
Both paths resolve the triggering user's GitHub login via
GITHUB_USER_EMAIL_MAP and read the profile's default_repo.
* Anthropic "thinking" effort: `make_model` now accepts a `thinking`
kwarg; `get_agent` maps profile effort {low,medium,high,xhigh,max}
to budget_tokens {1k,4k,12k,32k,60k} when the chosen model is
anthropic. OpenAI path still ignores "max" since the Literal doesn't
accept it.
The SLACK_ASSISTANTS_API_ENABLED env flag and its gating function
are removed. set_slack_assistant_status now always proceeds when a
bot token and channel/thread are provided.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* feat: TTL and revocation handling for cached GitHub OAuth tokens [closes AB-2322]
Persist github_token_expires_at alongside github_token_encrypted, treat
expired cache entries as missing so we re-resolve before kicking off
runs, and invalidate the cached ciphertext on a downstream 401 so the
next invocation gets a fresh token instead of replaying a revoked one.
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* webapp: forward installation-token expiry to reviewer cache writes
The three reviewer-thread persist sites in webapp.py were calling
get_github_app_installation_token() (no expiry) and persist_encrypted_github_token
without expires_at, so cached App tokens were treated as never-expiring even
though they actually expire in ~1 hour.
---------
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>
* feat: add 10 more tips to the trace-reply rotation
The TRACE_REPLY_TIPS pool only had 9 tips, so users mostly saw the same
ones. Added 10 more grounded in actual features (review command, image
attachments, GitHub-issue triggers, persistent sandboxes, OAuth fallback,
etc.) so the rotation surfaces more of what open-swe can actually do.
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* swap out 3 tips per review feedback
Replaced the suggestion-blocks, sandbox-auto-recovery, and OAuth-fallback
tips with three more practically useful ones: cross-posted Slack message
resolution, the web_search tool, and the Linear ticket-management tools.
Co-authored-by: Johannes du Plessis <51395795+johannes117@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>
When the primary model raises a transient provider error (5xx, 429,
connection/timeout) the request is retried once against a fallback
model from the other provider. Anthropic primaries fall back to
OpenAI and vice versa. Also bumps the SDK max_retries from the
default 2 to 6 so quick blips stay on the primary and keep prompt
caching warm.
Triggered by 529 OverloadedError traces that ended runs silently
with no Slack/Linear/PR reply.
Appending "Please react with 👍 or 👎..." to every Slack completion
message ended up being repetitive noise. Drop the prompt-side instruction
and add the same ask as one of the rotating tips on the trace reply, so
users still see it occasionally without it cluttering each final summary.
Now that assistant.threads.setStatus carries the "is thinking…"
indicator, the per-run greeting phrase + auto-unfurl on the LangSmith
link are just visual noise stacking on top of it. The trace reply now
posts only `<url|View trace>` + a tip, with link unfurling off so the
smith.langchain.com card no longer appears.
Adds an `unfurl_links`/`unfurl_media` knob to post_slack_thread_reply_with_ts
(default-on to preserve behaviour for every other caller).
* feat: add Slack reaction feedback to LangSmith
Record Slack reaction feedback against explicitly mapped LangGraph runs so user ratings are idempotent and tied to the message they reacted to.
* Address review feedback on Slack reaction → LangSmith feedback
- langsmith.py: drop lru_cache on _build_langsmith_feedback_clients so
rotated keys / late env hydration are picked up; dedupe by (key, url)
tuple instead of key alone so the same key pointing at different
endpoints (cloud + self-hosted) builds both clients.
- langsmith.py: treat LangSmithNotFoundError on delete_feedback as
success — out-of-order or redelivered reaction_removed events would
otherwise loop forever on Slack's retry policy.
- slack_feedback.py: include channel_id in _feedback_key so the same
message_ts in two channels can't collide on the same feedback id.
- slack_feedback.py: treat conflicting +/- reactions from one user as
ambiguous (clear feedback) instead of averaging to a misleading 0.5.
- slack_feedback.py + slack.py + webapp.py: gate reaction handling to
the user who triggered the run (stored in the slack_run_map mapping
alongside run_id). Prevents bystanders in shared channels from
polluting eval feedback.
