* feat: add plan mode for read-only research and planning
Adds a per-run plan_mode flag that puts the agent in a read-only
research phase: a strong prompt section is injected and mutating tools
are stripped via ExcludeToolsMiddleware so the agent proposes a
reviewable implementation plan before any edits. Surfaced in the
dashboard UI with a Plan toggle (Shift+Tab) wired through the thread API.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: enforce plan-mode read-only at tool layer and disable subagents
Addresses PR review: plan mode previously relied on prompt text to keep
the shell read-only and left the task subagent (built with its own
write/PR/Linear tools) unrestricted. Now `task` is excluded so research
cannot be delegated to a mutating subagent, and a new
PlanModeShellGuardMiddleware enforces a read-only command allowlist on
`execute`, blocking writes, git state changes, installs, redirection,
and command substitution regardless of model/prompt-injection compliance.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: harden plan-mode shell guard against wrapped mutations
Block git global options that take values (-C, --git-dir, ...) from being
misread as the subcommand, reject config-injection options (-c,
--config-env, --exec-path), and drop the env command wrapper that could
run arbitrary commands.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add plan mode with enter_plan_mode tool, profile/team defaults, Slack commands and approval flow
- enter_plan_mode tool: agent self-activates plan mode via Command(update={'plan_mode': True})
- Plan mode resolution: per-thread > profile default > team default > False
- PLAN_MODE_GUIDANCE_SECTION: always-present prompt section telling agent about the tool
- profile_plan_mode_default and team plan_mode_default settings
- Slack plan on/off/status commands with thread metadata persistence
- slack_thread_reply plan_approval=True renders Approve/Revise/Cancel buttons
- Interactivity handler: approve triggers implementation run, cancel posts confirmation
- Frontend: plan_mode_default in Profile/ProfileUpdate/TeamSettings types and UI toggles
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* test: add tests for enter_plan_mode tool, profile/team defaults, Slack plan commands, approval blocks
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor(plan-mode): drop shell guard, rely on prompt for read-only discipline
Remove PlanModeShellGuardMiddleware and its enforcement of read-only shell
commands during plan mode. Plan mode now relies on the system prompt to
instruct the agent not to run mutating commands; the mutating-tool exclusion
(ExcludeToolsMiddleware) is retained.
* test(open-swe): add Playwright E2E for the Slack → PR → web handoff
Local, secrets-free end-to-end suite that drives the full happy path through mock Slack/GitHub control panels and the real dashboard UI. Only the LLM and external SaaS HTTP boundaries (GitHub/Slack APIs, OAuth token mint) are faked — the real process_slack_mention, get_agent, deepagents loop, tools, middleware, and dashboard authorization all run under `langgraph dev` with a scripted fake chat model and a local temp-dir sandbox.
- full_flow: a Slack mention runs the agent, which implements a change in the sandbox, opens a PR against a fake GitHub remote, and replies with the PR link in the same thread.
- dashboard: clicking the bot's real "Open in Web" link loads the built ui/ app (served same-origin); the thread owner can continue the conversation, while a different user sees the same thread read-only (no composer).
Wired into Agent CI as a `Playwright E2E` job that runs on pull requests.
* fix(open-swe): serve E2E UI assets via explicit route; pin Playwright
The dashboard E2E served the built ui/ SPA's /assets via app.mount(StaticFiles), but LangGraph's custom-app loader serves APIRoutes and drops sub-app Mounts, so /assets 404'd under `langgraph dev` in CI — the React app never booted and the composer/transcript never rendered. Serve assets via an explicit route instead.
Also pin @playwright/test to the latest (1.61.0) for reproducible runs, and make the owner composer assertion tolerant of either hydration state.
* test(open-swe): record Playwright trace + video on every E2E run
Capture a replayable trace (DOM snapshots, network, console, source) and a screen recording for every test, not just retries, plus a screenshot on failure. The CI job already uploads playwright-report/ and test-results/, so each run now has a downloadable replay; documented how to open it.
* feat(plan-mode): collaborative plan review with BlockNote + Yjs
When the agent enters plan mode it writes the plan as a markdown file in the
sandbox (save_plan tool), publishes it, and posts a review link to the source
channel. Reviewers open the plan inside the dashboard (under the /agents shell),
read it rendered in a BlockNote editor, and leave inline comments synced live
over Yjs. Only the thread owner can approve; any reviewer can request changes.
On approve/reject the comments are harvested and handed to the agent for the
follow-up run; the agent never sees comments mid-review.
- agent: enter_plan_mode persists plan state; new save_plan tool; prompt shares
the plan-review link.
- dashboard: Yjs WebSocket collab server (pycrdt-websocket) with store-backed
snapshots; plan content/status store; plan REST API (get/approve/reject,
owner-only approve, client-harvested comments); planStatus on thread summaries.
- ui: BlockNote native comments (CommentsExtension + YjsThreadStore) plan page
mounted under the agents shell, with a "Review plan" banner in the thread view
and a back-link; theme-aware (dark mode) using the dashboard tokens.
- e2e: Playwright coverage of the full Slack -> plan -> review -> approve -> PR
flow, including cross-user comment sync and owner-only approval.
* fix(plan-mode): address review feedback (authz, overrides, leaks, deps)
- plan-collab WS: authorize per-thread before joining a room (same read gate as
the REST API) — previously any logged-in user could join any thread (IDOR).
- plan-collab: tie the snapshot flusher to active connections (refcount) so each
opened plan no longer leaks a permanent 1.5s task on the shared event loop.
- plan decisions: include thread_id in the follow-up run configurable so the run
resumes the existing thread; set plan_mode explicitly so approve forces it off.
- get_agent: an explicit per-thread plan_mode (Slack `plan off`, approved plan,
dashboard toggle) now overrides profile/team defaults instead of falling back.
- plan mode tool gating moved to a state-aware PlanModeMiddleware installed
unconditionally, so a mid-run enter_plan_mode restricts the next model turn;
before_agent resets stale plan_mode so a later run isn't forced back into it.
- exclude write-capable http_request from plan mode.
- pin pycrdt / pycrdt-websocket with upper bounds.
Includes the latest base (#1583): E2E UI assets served via explicit route
(fixes the Playwright CI failure — LangGraph's app loader drops sub-app mounts).
* style: ruff format plan_collab.py
* fix(plan-mode): owner-gate Slack approval + same-origin check on collab WS
- Slack "Approve & Implement" now verifies the clicking user is the plan
requester (owner, via the stored triggering_user_id) before implementing —
matching the dashboard API's owner-only approval. Non-owners are pointed to
Revise / feedback.
- The plan-collab WebSocket validates the handshake Origin against the dashboard
allowlist before accept() (no-op when unconfigured, e.g. local/dev), mirroring
the REST require_same_origin CSRF defense.
* fix(plan-mode): enter plan mode only via the model + local mock dev harness
Plan mode is now entered solely when the model calls enter_plan_mode.
Removed the per-user and team plan_mode_default settings (backend + UI)
and the Slack `plan on/off/status` toggle.
- enter_plan_mode returns a terminating ToolMessage, fixing the missing
ToolMessage error that silently dropped plan mode mid-run.
- PlanReview: defer Yjs provider/doc teardown so React StrictMode's dev
remount doesn't destroy and then reuse the collaboration provider.
- e2e plan_review spec asserts plan_mode actually engages.
- LangSmith trace-url resolution is best-effort: bail before any API
call when the tenant is unset, cache failures, log at debug.
- Add `pnpm run dev:mock`: same-origin Vite HMR harness with a real LLM,
Alice/Bob mock users, and a GitHub login picker.
* docs(plan-mode): drop stale references to removed profile/team defaults
The plan_mode middleware docstring and the approve/reject dispatch comment
still described the profile/team plan_mode_default resolution that no longer
exists; reword to match model-driven entry + the per-thread carry.
* feat(plan-mode): let any reviewer edit the plan, not just comment
Drop the owner/commenter split for the plan document: everyone with read
access edits and comments alike (DefaultThreadStoreAuth "editor" for all,
editor always editable until a decision, anyone seeds the empty doc). This
matches the collab WS, which already relays frames to every readable user.
Plan approval stays owner-gated.
* test(plan-mode): assert plan-mode entry via the tool's success message
plan_mode lives only in run state for tool gating; it is not a persisted
thread-state channel, so the previous `values.plan_mode === true` poll
could never pass. Assert instead that enter_plan_mode's success ToolMessage
("Plan mode is active …") lands in the thread — which only happens when the
tool's Command applies cleanly, the exact regression this guards.
---------
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat(dashboard): let any org member post to a thread, with attribution
Posting to an Agents chat thread from the web UI was restricted to the
thread owner. Open it to any authenticated org member (login is already
org-gated by OAuth) on both write paths — the queued follow-up
(send_dashboard_message) and the idle-thread run.start
(_enrich_run_start_command). Non-owner messages are prefixed with the
poster's verified GitHub login (@login:) so the agent and owner can tell
who sent them. Thread management (cancel/delete/resolve) stays owner-only,
and the UI now shows the composer to non-owners.
* fix(dashboard): keep non-run.start commands owner-only
Non-owner posting is allowed only via the attributed run.start path. Other
write commands (e.g. input.respond) carry unattributed user input, so the
commands proxy keeps them owner-only instead of readable-by-any-org-member.
* docs(e2e): drop per-test details from the E2E README
* fix: render GitHub-hosted images in PR descriptions on reviews page
PR description images hosted on GitHub (user-attachment uploads and
*.githubusercontent.com) render broken on the reviews page because
private-repo attachments require GitHub auth the browser session lacks.
Add an authenticated backend image proxy (host-allowlisted to guard
against SSRF) and route those image URLs through it from the reviews UI.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: harden PR image proxy (IDOR, SVG XSS, unbounded buffering)
Address review findings on the review-page image proxy:
- IDOR: the proxy fetched any *.githubusercontent.com URL with the App
installation token, gated only by route-param repo access, so a user
authorized for one repo could read images from another private repo the
App can see. Bind the URL to the authorized PR — only proxy URLs that
appear in that PR's body.
- SVG XSS: served any image/* inline from the API origin, including
image/svg+xml which can run script. Restrict to safe raster types and
add X-Content-Type-Options: nosniff + a locked-down CSP.
- DoS: enforced the size cap only after buffering the full response.
Stream and abort once the cap is exceeded.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Streamdown bundles Mermaid and renders ```mermaid blocks itself; a
diagram it can't parse throws during render and, with no boundary,
white-screens the whole review page. Wrap the markdown render so any
crash falls back to the raw text instead.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Replace the floating finding cards with inline annotations in the PR diff.
An anchored finding shows a collapsed header at its line and expands the full
details in place; non-anchored findings expand inline in the side-panel row.
Expand state is lifted into a context so it survives Pierre's annotation
windowing and the side panel can drive it.
Removes the anchored/fallback floating cards and their rAF/ResizeObserver
scroll-tracking. Also stops the line-selection highlight from bleeding behind
the inline annotation row.
* fix: reviewer reviews full diff; fix review UI scroll + dark-mode composer
- Drop the 200K-char PR diff truncation. The head/tail slice silently dropped
whole files out of the middle; the reviewer's large context window reviews
the complete diff. The grouping pass uses the full diff too. Other #1567 caps
(fetch_url, Slack, pagination, message queue) are kept.
- Sidebar file/group click now lands flush at the top under virtualization:
re-assert alignment after the Virtualizer's mid-scroll height reconciliation
settles, instead of trusting scrollIntoView's estimate-based target.
- Review chat composer textarea no longer shows a lighter square in dark mode
(override the Textarea's dark:bg-input default with dark:bg-transparent).
* fix: anchored finding card sits flush in the diff gutter, no side-panel overlap
The card was positioned next to the anchor and clamped to window.innerWidth, so
when the anchor sat near the diff/side-panel boundary the 412px card spilled
across into the side panel. Pin it flush to the diff column's right edge and
clamp its width to the column so it never overlaps the side panel and shrinks to
fit a narrow column.
* fix: anchored finding card sits over the side panel, not the diff
Flip the horizontal anchor: place the card flush against the diff column's right
edge and extend it rightward over the side panel, instead of leftward over the
diff. Width still caps at the preferred size and shrinks to fit a narrow panel.
* fix: anchor finding card to diff content edge + small-screen fallback
- Anchor to the centered diff content's right edge instead of the full-width
scroller, removing the centering-whitespace gap so the card sits closer to the
diff.
- Below xl the side panel is hidden and the diff fills the viewport, leaving no
gutter; positioning against the content edge would collapse the card to ~0px.
Fall back to overlaying the diff flush-right when there's no usable gutter
(addresses Open SWE review finding f_f6ea77527c).
* fix: anchor finding card next to the annotation, close to the hunk
Anchor the card's left to the finding's annotation (anchorRect.right) instead of
the diff content's right edge, so it sits right by the hunk and overlaps the diff
edge rather than parking out in the gutter. Extends right over the side panel,
clamped to stay on-screen (also keeps it readable below xl with no side panel).
* fix: finding card width shrinks to fit a small side panel
Size the card to the room to the right of the annotation (capped at the
preferred width) so it narrows as the side panel shrinks instead of overflowing.
Below a readable minimum, hold that width and shift left over the diff.
* feat: reviews page split view, add-to-chat, virtualization + perf
- Virtualize the diff (Pierre Virtualizer + worker pool), mirroring the agent
chat panel, so large PRs window rows instead of materializing every line.
- Split chat and diff into independent scroll containers and make chat
auto-scroll fully contained, so typing/streaming no longer moves the diff.
- Memoize FileDiffCard with stable callbacks so focusing a finding re-renders
only the affected card.
- Add a persisted unified/split diff toggle.
- Add highlight-to-chat: select lines (drag / shift-click) + gutter "+" to drop
a file:line snippet into the chat composer.
- Rebuild sidebar group rows: whole card scrolls to the group (incl. the
expanded explanation), Read explanation stays a separate toggle, memoized.
* feat: add-to-chat uses attachment pills + selection popup / ⌘L
Replace the raw-snippet injection with a Cursor-style flow:
- Selecting lines shows a floating "Add to Chat ⌘L" popup at the pointer; ⌘L
adds the current selection without it. Removes the auto-adding gutter "+".
- "Add to chat" now creates a removable attachment pill in the composer (and a
pill in the sent message bubble) instead of pasting raw text. The code is
still serialized into the message content so the model receives it as context.
* feat: restore gutter + drag-handle for line selection
Re-enable Pierre's gutter '+' as a click-and-drag line selector (with the
highlight growing as you drag) — the affordance that was lost when the
auto-adding gutter button was removed. It no longer auto-adds: the commit flows
through onLineSelected to the 'Add to Chat' popup / ⌘L.
* fix: live selection highlight while dragging + reposition Add to Chat popup
- Feed onLineSelectionChange into the controlled selection so rows highlight
live as you drag, not just on release (Pierre only paints the controlled
selection when the prop updates). Popup now fires on onLineSelectionEnd.
- Anchor the popup's bottom-left to the drag handle (drop horizontal centering)
so it no longer overlaps the '+' button.
* fix: anchor Add to Chat popup to gutter handle + click-away to unselect
- Position the popup from the gutter '+' handle's rect (in the diff shadow DOM,
placed on the selection's bottom line) instead of the pointer-release point,
which landed inconsistently. Falls back to the pointer if not found.
- Clear the line selection (and popup) on any outside pointer-down.
* fix: sidebar-collapse header overlap + PR review comments
- Lift useSidebarLayout to AgentsShell (single source), share collapsed via
context, and pad the reviews header left when the sidebar is collapsed so the
fixed collapse toggle no longer overlaps the header content.
- add-to-chat: collect each diff side separately so a selection that spans a
deletion->addition no longer pastes wrong-file lines (PR comment).
- chat: clear attachments after sending via a suggested prompt, so an attached
snippet isn't silently resent on the next message (PR comment).
* fix: anchored finding card positions to the right of the diff again
The virtualization refactor moved the card inside the main-width Virtualizer
scroller, so it clamped over the diff. Render it in the outer container as a
viewport-fixed card clamped to window width (right gutter / over the side panel,
like prod) and track the finding as the diff scrolls (rAF-throttled), hiding
when the finding scrolls out of view.
The thread detail endpoint already returned metadata for non-owners, but
the transcript hydration endpoints (state, stream/events, history, pr-diff)
all asserted ownership and 404-ed. This caused the UI to redirect non-owners
back to /agents when they clicked an "Open in Web" link shared in Slack.
Dashboard login is already gated by ALLOWED_GITHUB_ORGS, so any logged-in
user is a trusted org member. This commit:
- Adds _thread_is_readable / _assert_thread_readable helpers that grant
read access to any surfaced-source thread for authenticated users
- Relaxes read endpoints (state, stream/events, history, pr-diff, SSE
stream) to use readable checks instead of ownership checks
- Keeps write endpoints (send message, cancel, delete, resolve, run
commands) owner-only
- Adds an isOwner field to the thread summary so the frontend can render
a read-only mode (hides the prompt bar, resolve/delete buttons)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: activate PR babysitting UI toggles for autofix and trigger mode
Remove the "coming soon" gating on the Autofix Mode, Autofix Severity
Threshold, and Trigger Mode controls in the review settings page so
admins can enable CI auto-fix and review-comment resolution on PRs
that Open SWE opens. The backend (ci_autofix.py, webapp.py webhook
routing) was already fully wired — only the UI was disabled.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: simplify autofix to on/off toggle, remove severity threshold
Replace the four-level AutofixMode (off/low/medium/high) and the
autofix_severity_threshold setting with a single boolean
autofix_enabled toggle. The severity threshold was leftover from the
reviewer finding-severity model and does not apply to CI autofix;
the agent should fix any failing CI and resolve any comments on PRs
it opens.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: move autofix toggle to per-user profile, remove team-level setting
The autofix toggle is now per-user (auto_fix_ci in the user profile)
instead of team-level (admin-only). This uses the existing auto_fix_ci
field that was already in ProfileUpdate but never wired up.
Changes:
- ci_autofix.py: check per-user auto_fix_ci profile flag after
resolving the agent thread's github_login, instead of checking
team-level autofix_enabled before knowing the PR
- webapp.py: removed early is_autofix_enabled() webhook gates; the
per-user check now happens in ci_autofix.py once the thread is found
- team_settings.py: removed autofix_enabled field, is_autofix_enabled()
- cloud-agents.tsx: enabled the auto_fix_ci toggle (was comingSoon)
- review.tsx: removed the admin-level autofix switch
- Updated tests and AGENTS.md
The agent graph (not the reviewer) is what gets dispatched - this was
already correct in ci_autofix.py line 223: client.runs.create(
thread_id, "agent", ...).
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: batch PR babysitting events
Remove the leftover trigger-mode gate from PR babysitting and batch new CI/review events while an agent run is already active so the running agent can handle the latest PR state before finishing. Also moves review-feedback permission checks behind the per-user opt-out and applies the auto-fix profile gate to merge-conflict babysitting.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: consume batched babysitting events
Teach the agent queue middleware to turn pending PR babysitting metadata into an injected instruction for the active run, so batched CI/review events are not dropped while still avoiding duplicate run creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review findings in PR babysitting batching
- Route batched events through the LangGraph store (read in-process by the
message-queue middleware) instead of a per-model-call threads.get on every
agent thread.
- Only record an attempt / mark the head SHA handled on a real dispatch, not
on a batch, so an event isn't permanently dropped if the in-flight run ends
before consuming it.
- Carry the reviewer's comment through batched review feedback instead of
replacing it with a generic re-check nudge.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add user-scoped Currents.dev API key for e2e test investigation
Allow each user to configure their own Currents.dev API key on the
Profile Settings page. The key is encrypted at rest in a per-user
LangGraph Store namespace and feeds server-side read-only tools that
query the Currents REST API (runs, instances, projects, test results)
so agent runs can inspect e2e test failures including screenshots and
DOM snapshots.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: add pagination cursors to currents_list_project_runs
Address review feedback: forward starting_after/ending_before cursor
parameters to /projects/{projectId}/runs so the agent can paginate
beyond the first 50 results.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Move merged_prs to the primary sort key in the agent usage leaderboard,
ahead of agent_loc, prs_opened, and agent_runs. Update the UI description
to reflect the new ranking order.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add browser notifications for agent run completion
Request notification permission when a user starts their first agent
run from the home page. A toggle in Profile Settings lets users
enable/disable desktop notifications. When a run transitions from
running to a terminal state (finished/error/interrupted), a browser
notification is fired — suppressed for the thread the user is
currently viewing.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: notify for active thread when page is in background tab
Only suppress the notification for the active thread when the page is
actually visible. If the user switched to another browser tab, the
notification fires even for the thread they have open.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
At mobile widths the resizable git panel collided with the chat column's
360px min-width, overflowing the viewport. Treat mobile (<768px) like the
sidebar: the git panel becomes a full-screen overlay the user navigates to
and back from, while desktop keeps the inline resizable panel.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: handle images sent to non-vision models in Slack, Linear, and web UI
Add vision capability checks across all image input paths. When a user
sends images to a text-only model (e.g. GLM 5.2, DeepSeek V4 Pro), the
images are now skipped and a warning is injected into the prompt instead
of sending unsupported content to the model.
- Slack: resolve model at webhook time, skip image fetch + add warning
- Linear: same pattern as Slack
- Queued message middleware: read resolved model from thread metadata,
strip images from queued payloads for text-only models
- Web UI: disable submit + show inline warning when images are attached
to a non-vision model selection
- Shared: resolve_agent_model_id helper + vision_not_supported_warning
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* test: mock resolve_agent_model_id in Slack mention test
The test_process_slack_mention_queues_active_thread_message test was
missing a mock for the new resolve_agent_model_id call added to the
Slack webhook handler, causing a TypeError when image URLs triggered
the model resolution path.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: include vision warning in queued payload for text-only models
Update the prompt variable (not just content_blocks) before clearing
image_urls so the queued payload also carries the warning text when a
Slack/Linear follow-up arrives while the thread is busy.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Restore a subtle blue --ui-accent token (driving send/stop buttons and
accent spots), the blue git status indicators for renamed/copied files,
and color the thread-list diff stat badge. Keeps the overall greyscale
aesthetic with tasteful blue/green/red accents.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Run reviewer eval in a GitHub Action; make dashboard a read-only progress view
The dashboard launched the eval as a subprocess inside the serving deployment
worker, so a container recycle killed long runs and discarded results that had
already completed server-side. Move the harness to a workflow_dispatch Action
(run on prod). run_eval now publishes status/progress/log-tail to the LangGraph
store record the dashboard reads, so /admin/evals stays a live view; a killed
Action surfaces as failed via the stale-heartbeat reconcile.
* reviewer_eval workflow: pass inputs via env, no shell interpolation
Addresses the reviewer finding: workflow_dispatch string inputs were
interpolated into the run: block (limit unquoted), allowing shell injection in
a job holding LANGSMITH/ANTHROPIC keys. Pass inputs through env and reference
quoted "$VARS"; validate limit is numeric and build its flag in bash.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Strip the blue/cool cast from the agent + reviewer chat and shared UI.
Neutralize the --ui-* (agents.css) and shadcn (styles.css) color tokens
to pure neutral grays (chroma/hue zeroed, lightness preserved); primary
and filled buttons become inverse-foreground neutral solids. Replaces a
few hardcoded blue/cyan spots (send button, prompt bar bg, context ring,
loop dot, git renamed status) with neutral tokens. Semantic green/amber/
red are kept.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Lighter, more consistent type across the dashboard and agent UI:
unify title sizes, drop semibold/bold in chrome to medium, harmonize
stray text-sm to text-xs, normalize chat markdown headings, and enable
antialiased font smoothing (fixes heavy text on dark backgrounds).
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* 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>
* feat(ui): flatten reviews file tree and refine pierre tree styling
Switch the reviews-page file tree off forced full expansion so it renders
as a compact, flattened directory tree (single-child chains merged into one
row) like the pierre "flattened directories" preset. Expand only the
selected file's ancestors so the active diff stays revealed. Refine the
shared tree theme: subtle accent-tinted hover/selection and a complete
git-status palette (renamed/untracked/ignored) plus search input fg.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix(ui): neutralize pierre tree filenames and selection styling
Use neutral grey/white filename colors instead of git-status accents,
apply unsafe CSS overrides for selected-row contrast, and switch to
complete icons in both agent and review file trees.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Extend the first-run Slack connect modal into a two-step onboarding
dialog that first prompts new users to pick a default agent model
(persisted to their profile) before connecting Slack, so model choice
happens up front during onboarding alongside Slack authentication.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Drive dashboard-triggered reviewer eval runs with per-run model, effort,
score mode, severity threshold, cap, limit, and concurrency overrides, plus
per-example start/finish/error logging in the eval target.
Rework the admin eval form from the label-left/control-right SettingsRow
(which crushed the description column when packing 3-4 wide inputs) into
stacked field groups with captioned inputs in a responsive grid.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Clears ~83 pre-existing eslint errors in the UI: auto-fixable rules
(array-type, import/order, sort-imports, type-only imports, redundant
assertions/conditions) plus manual fixes for unnecessary conditions and
banned @ts-nocheck directives. The 8 ported components excluded from
tsconfig are now also ignored by eslint so type-aware linting no longer
fails to parse them.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: keep prompt bar editable while a run streams
The follow-up submit path awaited stream.submit, which resolves only when the
run finishes. That kept the react-query mutation isPending for the whole run,
so AgentThreadView disabled the prompt bar textarea the entire time the agent
was streaming - the user saw the "queue next" placeholder but couldn't click
in or type. Fire the run without awaiting its full lifecycle (matching the
new-thread path in AgentsHome) so the input stays editable for queueing.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor(ui): guard double-submit internally instead of via disabled prop
Stop threading a run-lifecycle signal (the send mutation's isPending) into the
prompt bar to gate the input. Instead, the prompt bar owns a synchronous
double-submit guard (submittingRef) plus a short-lived isSubmitting state
scoped to the in-flight send. The textarea now stays editable while a run
streams (so follow-ups can be queued), and onSubmit is awaitable so the guard
tracks the actual send request rather than the run.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix(ui): surface failed run-start instead of leaving thread running
When stream.submit rejects (e.g. 401 expired token or 409 active-run
race), the fire-and-forget catch was a no-op while onSuccess had already
optimistically set status: running, leaving the thread stuck in a busy
state with no surfaced error. Clear the busy state and mark the thread
errored on submit failure.
Co-authored-by: open-swe[bot] <open-swe@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: chat with your PR on the review page
Add a sandbox-less `chat` graph that answers questions about a single PR
from its diff, the published review findings, and read-only GitHub access.
- agent/chat.py: deepagents graph, no sandbox (default StateBackend, file
mutation + execute tools excluded). PR context is seeded as virtual files
under /pr/; a repo-scoped App token is resolved in-graph.
- tools: read_repo_file, search_repo_code, list_review_findings.
- dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph
stream/commands/state/history proxy pinned to the chat assistant, seeds
diff/findings/overview on first run. Gated by repo access.
- UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon).
* feat: admin setting for review-chat default model
Add a 'Open SWE Review Chat' default to team settings (default_chat_model /
default_chat_reasoning_effort). get_team_default_model("chat") inherits the
Agent default when unset; the chat graph resolves through it. Admin RolePicker
gains an 'Agent default' inherit option that clears the override.
* feat: multi-conversation review chat (tabs, new chat, history)
Replace the single per-PR chat thread with multiple per-user conversations:
- threads minted client-side; first message persists with a title derived
from the prompt.
- list + delete endpoints; chat panel gets a tab strip (history), new-chat
(+), close (x), refresh, an intro greeting, and suggested prompts.
- get_review_chat now returns availability only (ids are client-minted).
* ui fixes
* ui: review-chat history dropdown, full-width AI replies, resizable side panel
* fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Hover swaps the PR icon/badge (which has its own padding) for the
resolve/delete action buttons, changing the row's natural height. Pin
the row to a fixed height so the swap no longer shifts its size.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Replace the hard inset box-shadow scroll indicators on bash/shell tool
output with a mask-image gradient so the output softly fades at the
scroll edges, matching the user message bubble treatment.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Replace the hard inset box-shadow scroll indicators on long user
messages with a mask-image gradient so the text softly fades at the
scroll edges instead of showing a heavy shadow.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The TanStack route generator appends an @tanstack/react-start Register
module-augmentation block on every dev/build, but main's committed
routeTree.gen.ts predates it, so the file shows as modified after every
run. Commit the current generator output so local regeneration is a no-op.
Type-only and under // @ts-nocheck, so no build/lint impact.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stream reviewer eval logs on a dedicated admin page
Stream the eval subprocess output into a rolling log_tail and persist it
during the run (was only captured at exit), so the live output is visible
while the eval runs. Move the eval runner off the admin page onto its own
/admin/evals page (linked like Review Style Prompts) with a live log viewer.
* chore: drop unrelated SSR-register drift from generated route tree
* fix(ui): pre-bundle workbox-window to stop dev re-optimize reload
The PWA service worker (devOptions.enabled) pulls workbox-window, which
Vite discovers after first render and re-optimizes, forcing a reload that
cancels in-flight code-split route imports (Failed to fetch dynamically
imported module). Pre-bundling it via optimizeDeps.include avoids the
mid-session reload.
* fix(ui): suppress html hydration warning for pre-hydration theme script
The inline theme script sets class="dark"/color-scheme on <html> before
React hydrates, so the prerendered HTML never matches. suppressHydrationWarning
on <html> silences the (expected) one-level attribute mismatch.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The subagent card listed every nested tool call, ballooning the card as
the subagent ran. Show a single status line (current activity + step
count) until a richer activity UI lands.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The git panel can now be dragged toward full window width, but its max was
reserved against window.innerWidth (ignoring the sidebar), letting the panel
squeeze the chat below a usable width. Clamp the panel against the actual
container width and give the chat column a matching min-width floor.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The git panel was capped at a fixed 720px max width, which wasted space on
wide/ultrawide screens. Make the max width dynamic relative to the viewport
(window width minus a minimum chat width) so it can be dragged up to ~50/50
or wider, and re-clamp on window resize.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: trigger reviewer evals from the admin page
Add an admin-only "Reviewer eval" section + endpoints that launch the
reviewer benchmark as an isolated subprocess against the running
deployment, with live status and the LangSmith experiment link. Route
eval traces to a dedicated open-swe-evals project so they stay out of
the production tracing project.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: reconcile reviewer eval status via heartbeat, not local process
The persisted record is shared across workers but _PROCS is process-local.
The owning worker now refreshes a heartbeat while the subprocess runs, and
status is only reconciled to failed once the heartbeat is stale, so a poll on
a worker without the local handle no longer kills a live run (and a duplicate
start is rejected across workers).
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The bash command card had only pb-1 on the header block, leaving the
content cramped against the card's bottom edge until output streamed in
(which adds its own pb-2). Apply pb-3 when there is no output yet so the
card looks uniformly padded in the pending/in-progress state.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* perf: speed up Reviews list (My PRs + All PRs)
Push the "My PRs" author filter into the threads.search metadata
(pr.author containment) instead of scanning up to 1000 reviewer threads
in Python, and replace the per-repo GitHub access check (an N+1 of
sequential GET /repos calls) with a single per-login accessible-repo set,
cached for 60s. Detail endpoints still re-validate access live.
Frontend: prefetch the inactive tab and adjacent page on hover/focus so
tab switches and pagination are instant.
* fix: don't cache repo access for the reviews list
The /reviews list is an authorization boundary for private PR metadata
(repo/PR titles, branches, authors, finding counts). A cross-request TTL
cache on the accessible-repo set could surface that metadata for up to
60s after a user lost repo access. Resolve the set fresh per request
instead — still a fixed, repo-count-independent burst of GitHub calls
(no per-repo N+1), with no staleness.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: mark threads resolved to hide from sidebar [closes resolve-threads]
Add a resolved flag (thread metadata) so users can clear finished
threads from the sidebar without deleting them. Resolved threads move to
a collapsible "Resolved" group (capped at 20 with a "Show all" link) and
are fully searchable/filterable + paginated on a new /agents/threads
page driven by URL query params. Sending a new message auto-unresolves.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: refresh paginated agent thread lists
Invalidate all agent thread list queries when thread lifecycle events change sidebar data, keeping the new paginated sidebar cache in sync.
---------
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: render Reviews page diffs with pierre MultiFileDiff
The Reviews detail page used a hand-rolled hunk renderer with no syntax
highlighting. Switch it to the same pierre MultiFileDiff + theming the agent
chat git panel uses.
- review-diff API now returns full original/modified file contents instead of
hunks, via a shared build_pr_diff_files helper extracted from thread_api
- findings render as right-anchored markers (pierre line annotations); focus
highlight uses selectedLines; floating finding card still anchors to the marker
* feat: auto-collapse a review diff card when marked as viewed
* fix: URL-encode file path in Contents API fetch
Filenames containing reserved URL characters (#, ?) were truncated, so those
files rendered as empty/unrenderable. quote(path, safe='/') preserves the path
separators while escaping the rest.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add UI hotkey wiring and Cmd/Ctrl+B sidebar toggle
Add a reusable useHotkey hook for registering global keyboard
shortcuts (with 'mod' resolving to Cmd on macOS, Ctrl elsewhere),
and wire up the first shortcut: mod+b toggles the left sidebar.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: ignore key repeat for sidebar toggle hotkey
Holding Cmd/Ctrl+B fired repeated keydown events, toggling the sidebar
multiple times. Add an ignoreRepeat option to useHotkey and enable it for
the sidebar toggle so one held press toggles once.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Brendan Whiting <16016903+bwhiting2356@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>
Once an agent turn finishes, its reasoning/tool/exploration steps collapse
behind a single "Worked for …" toggle so the chat shows only the final reply,
mirroring Devin's transcript. Work stays expanded live and auto-collapses on
completion; the final reply text/cards remain visible.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The sidebar expand and collapse toggle buttons were missing the
cursor-pointer style, so hovering didn't show a pointer cursor.
Co-authored-by: Brendan Whiting <16016903+bwhiting2356@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
The prompt bar only accepted images via drag-and-drop or the file picker.
Pasting an image from the clipboard inserted the file name as text instead
of attaching the image. Add an onPaste handler that extracts image files
from the clipboard and attaches them as pending images.
Co-authored-by: Brendan Whiting <16016903+bwhiting2356@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
