mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 05:43:14 +00:00
* 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>
279 lines
8.3 KiB
TypeScript
279 lines
8.3 KiB
TypeScript
import { useMutation, useQuery, useQueryClient } from "@tanstack/react-query"
|
|
import { useNavigate } from "@tanstack/react-router"
|
|
import { useEffect } from "react"
|
|
|
|
import { agentsApi } from "./api"
|
|
import type { QueryClient } from "@tanstack/react-query"
|
|
import type {
|
|
ScheduleUpdateRequest,
|
|
SidebarThreads,
|
|
ThreadsPageParams,
|
|
} from "./api"
|
|
import type { AgentThread, Chunk, ImageChunk, Message } from "./types"
|
|
|
|
export const agentThreadKeys = {
|
|
lists: ["agent-threads", "lists"] as const,
|
|
sidebar: (params: { activeLimit: number; resolvedLimit: number }) =>
|
|
["agent-threads", "lists", "sidebar", params] as const,
|
|
detail: (threadId: string) => ["agent-threads", threadId] as const,
|
|
prDiff: (threadId: string) => ["agent-threads", threadId, "pr-diff"] as const,
|
|
page: (params: ThreadsPageParams) =>
|
|
["agent-threads", "lists", "page", params] as const,
|
|
}
|
|
|
|
export function invalidateAgentThreadLists(queryClient: QueryClient): void {
|
|
void queryClient.invalidateQueries({ queryKey: agentThreadKeys.lists })
|
|
}
|
|
|
|
export function seedAgentThreadLists(
|
|
queryClient: QueryClient,
|
|
thread: AgentThread
|
|
): void {
|
|
queryClient.setQueriesData<SidebarThreads>(
|
|
{ queryKey: ["agent-threads", "lists", "sidebar"] },
|
|
(prev) => {
|
|
if (!prev) return prev
|
|
const activeItems = [
|
|
thread,
|
|
...prev.active.items.filter((item) => item.id !== thread.id),
|
|
].slice(0, prev.active.limit)
|
|
const resolvedItems = prev.resolved.items.filter(
|
|
(item) => item.id !== thread.id
|
|
)
|
|
return {
|
|
...prev,
|
|
active: { ...prev.active, items: activeItems },
|
|
resolved: { ...prev.resolved, items: resolvedItems },
|
|
}
|
|
}
|
|
)
|
|
}
|
|
|
|
export const agentScheduleKeys = {
|
|
all: ["agent-schedules"] as const,
|
|
}
|
|
|
|
// Sidebar lists and detail reads return the same per-thread summary, so warming
|
|
// the detail cache from the already-fetched sidebar avoids a fan-out of one
|
|
// request per thread. Navigation stays instant; the real (mark-viewed) fetch
|
|
// fires only when a thread is actually opened. The active thread is skipped so
|
|
// its live detail query stays the source of truth.
|
|
export function useSeedAgentThreadDetails(
|
|
threads: Array<AgentThread>,
|
|
activeThreadId?: string
|
|
) {
|
|
const queryClient = useQueryClient()
|
|
|
|
useEffect(() => {
|
|
for (const thread of threads) {
|
|
if (thread.id === activeThreadId) continue
|
|
// Seed as already-stale: the detail GET is what marks a thread viewed
|
|
// server-side, so opening a seeded entry must still refetch despite the
|
|
// detail query's `staleTime` (which exists for the optimistic seed).
|
|
queryClient.setQueryData(agentThreadKeys.detail(thread.id), thread, {
|
|
updatedAt: 0,
|
|
})
|
|
}
|
|
}, [activeThreadId, queryClient, threads])
|
|
}
|
|
|
|
const SIDEBAR_ACTIVE_LIMIT = 50
|
|
|
|
function sidebarThreads(data?: SidebarThreads): Array<AgentThread> {
|
|
return [...(data?.active.items ?? []), ...(data?.resolved.items ?? [])]
|
|
}
|
|
|
|
function sidebarRefetchInterval(query: { state: { data?: SidebarThreads } }) {
|
|
return sidebarThreads(query.state.data).some(
|
|
(thread) => thread.status === "running"
|
|
)
|
|
? 2000
|
|
: false
|
|
}
|
|
|
|
export function useSidebarThreads(resolvedLimit: number) {
|
|
const params = {
|
|
activeLimit: SIDEBAR_ACTIVE_LIMIT,
|
|
resolvedLimit,
|
|
}
|
|
return useQuery({
|
|
queryKey: agentThreadKeys.sidebar(params),
|
|
queryFn: () => agentsApi.listSidebarThreads(params),
|
|
refetchInterval: sidebarRefetchInterval,
|
|
placeholderData: (prev) => prev,
|
|
})
|
|
}
|
|
|
|
export function useAgentThread(threadId: string) {
|
|
return useQuery({
|
|
queryKey: agentThreadKeys.detail(threadId),
|
|
queryFn: () => agentsApi.getThread(threadId),
|
|
// Lets the optimistic detail seeded by `AgentsHome` survive until the
|
|
// proxied run.start stamps the server-side thread; an immediate refetch
|
|
// would 404 and bounce the route back to /agents.
|
|
staleTime: 30_000,
|
|
})
|
|
}
|
|
|
|
export function useAgentThreadPrDiff(threadId: string, enabled: boolean) {
|
|
return useQuery({
|
|
queryKey: agentThreadKeys.prDiff(threadId),
|
|
queryFn: () => agentsApi.getThreadPrDiff(threadId),
|
|
enabled,
|
|
staleTime: 30_000,
|
|
retry: false,
|
|
})
|
|
}
|
|
|
|
export function useAgentSchedules() {
|
|
return useQuery({
|
|
queryKey: agentScheduleKeys.all,
|
|
queryFn: () => agentsApi.listSchedules(),
|
|
})
|
|
}
|
|
|
|
export function useCreateAgentSchedule() {
|
|
const queryClient = useQueryClient()
|
|
|
|
return useMutation({
|
|
mutationFn: agentsApi.createSchedule,
|
|
onSuccess: () => {
|
|
queryClient.invalidateQueries({ queryKey: agentScheduleKeys.all })
|
|
},
|
|
})
|
|
}
|
|
|
|
export function useUpdateAgentSchedule() {
|
|
const queryClient = useQueryClient()
|
|
|
|
return useMutation({
|
|
mutationFn: (vars: { scheduleId: string; body: ScheduleUpdateRequest }) =>
|
|
agentsApi.updateSchedule(vars.scheduleId, vars.body),
|
|
onSuccess: () => {
|
|
queryClient.invalidateQueries({ queryKey: agentScheduleKeys.all })
|
|
},
|
|
})
|
|
}
|
|
|
|
export function useDeleteAgentSchedule() {
|
|
const queryClient = useQueryClient()
|
|
|
|
return useMutation({
|
|
mutationFn: agentsApi.deleteSchedule,
|
|
onSuccess: () => {
|
|
queryClient.invalidateQueries({ queryKey: agentScheduleKeys.all })
|
|
},
|
|
})
|
|
}
|
|
|
|
export interface CreateAgentThreadVariables {
|
|
prompt: string
|
|
images?: Array<ImageChunk>
|
|
repo?: string | null
|
|
repo_explicitly_none?: boolean
|
|
model_id?: string | null
|
|
effort?: string | null
|
|
}
|
|
|
|
/**
|
|
* Build the placeholder thread shown the instant a run is started from the
|
|
* home page — before the server has stamped the thread record. Seeded into
|
|
* the detail + list caches by `AgentsHome` so the `$threadId` route renders
|
|
* immediately (the 30s `staleTime` keeps it from refetching into a 404), then
|
|
* reconciled to server truth by the list's running refetch + the stream's
|
|
* `onCreated` / `onCompleted` invalidations.
|
|
*/
|
|
export function optimisticThread(
|
|
threadId: string,
|
|
vars: CreateAgentThreadVariables
|
|
): AgentThread {
|
|
const now = Date.now()
|
|
const text = vars.prompt.trim()
|
|
const repoFullName = vars.repo ?? ""
|
|
const chunks: Array<Chunk> = [
|
|
...(vars.images ?? []),
|
|
...(text ? [{ kind: "text", text } satisfies Chunk] : []),
|
|
]
|
|
const message: Message = {
|
|
id: `optimistic-user-${threadId}`,
|
|
author: "user",
|
|
timestamp: new Date(now).toISOString(),
|
|
chunks,
|
|
}
|
|
return {
|
|
id: threadId,
|
|
title: text.slice(0, 80) || "New agent",
|
|
repo: repoFullName.split("/")[1] ?? "",
|
|
repoFullName,
|
|
branch: "main",
|
|
model: vars.model_id ?? "Default",
|
|
effort: vars.effort ?? null,
|
|
source: "dashboard",
|
|
status: "running",
|
|
viewed: true,
|
|
viewedAt: now,
|
|
isOwner: true,
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
traceUrl: null,
|
|
messages: message.chunks.length > 0 ? [message] : [],
|
|
}
|
|
}
|
|
|
|
export interface SendAgentMessageVariables {
|
|
content: string
|
|
images?: Array<ImageChunk>
|
|
model_id?: string | null
|
|
effort?: string | null
|
|
plan_mode?: boolean
|
|
}
|
|
|
|
export function useCancelAgentThread(threadId: string) {
|
|
const queryClient = useQueryClient()
|
|
|
|
return useMutation({
|
|
mutationFn: () => agentsApi.cancelThread(threadId),
|
|
onSuccess: (thread) => {
|
|
queryClient.setQueryData(agentThreadKeys.detail(threadId), thread)
|
|
invalidateAgentThreadLists(queryClient)
|
|
},
|
|
})
|
|
}
|
|
|
|
export function useDeleteAgentThread() {
|
|
const queryClient = useQueryClient()
|
|
const navigate = useNavigate()
|
|
|
|
return useMutation({
|
|
mutationFn: (threadId: string) => agentsApi.deleteThread(threadId),
|
|
onSuccess: (_, threadId) => {
|
|
queryClient.removeQueries({ queryKey: agentThreadKeys.detail(threadId) })
|
|
invalidateAgentThreadLists(queryClient)
|
|
const path = window.location.pathname
|
|
if (path.includes(`/agents/${threadId}`)) {
|
|
navigate({ to: "/agents" })
|
|
}
|
|
},
|
|
})
|
|
}
|
|
|
|
export function useResolveAgentThread() {
|
|
const queryClient = useQueryClient()
|
|
|
|
return useMutation({
|
|
mutationFn: (vars: { threadId: string; resolved: boolean }) =>
|
|
agentsApi.resolveThread(vars.threadId, vars.resolved),
|
|
onSuccess: (thread, vars) => {
|
|
queryClient.setQueryData(agentThreadKeys.detail(vars.threadId), thread)
|
|
invalidateAgentThreadLists(queryClient)
|
|
},
|
|
})
|
|
}
|
|
|
|
export function useThreadsPage(params: ThreadsPageParams) {
|
|
return useQuery({
|
|
queryKey: agentThreadKeys.page(params),
|
|
queryFn: () => agentsApi.listThreadsPage(params),
|
|
placeholderData: (prev) => prev,
|
|
})
|
|
}
|