open-swe/ui/vite.config.ts

232 lines
7.6 KiB
TypeScript
Raw Permalink Normal View History

feat: plan mode with model-driven entry and collaborative review (#1580) * 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>
2026-06-23 15:06:58 -04:00
import http from "node:http"
import { defineConfig } from "vite"
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
import { devtools } from "@tanstack/devtools-vite"
import { tanstackStart } from "@tanstack/react-start/plugin/vite"
import viteReact from "@vitejs/plugin-react"
import viteTsConfigPaths from "vite-tsconfig-paths"
import tailwindcss from "@tailwindcss/vite"
import { nitro } from "nitro/vite"
import { VitePWA } from "vite-plugin-pwa"
import type {Plugin} from "vite";
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
feat: plan mode with model-driven entry and collaborative review (#1580) * 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>
2026-06-23 15:06:58 -04:00
// Dev-only: when E2E_HARNESS is set (the `dev:mock` local harness) serve the app
// and the harness from one origin by proxying the API routes + the Yjs collab
// WebSocket to the harness. Same-origin keeps the session cookie on the WS, which
// the plan-review collab requires. Inert in production (E2E_HARNESS unset).
function mockHarnessProxy(): Plugin | null {
const target = process.env.E2E_HARNESS
if (!target) return null
const prefixes = [
"/dashboard/api",
"/webhooks",
"/mock",
"/control",
"/fake-gh",
"/fake-slack",
"/static",
"/ok",
]
const matches = (url?: string): boolean =>
!!url &&
prefixes.some(
(p) => url === p || url.startsWith(`${p}/`) || url.startsWith(`${p}?`)
)
const upstream = new URL(target)
return {
name: "mock-harness-proxy",
enforce: "pre",
async configureServer(server) {
const { createProxyServer } = await import("httpxy")
const proxy = createProxyServer({ target })
proxy.on("error", () => {})
server.middlewares.use((req, res, next) => {
if (matches(req.url)) void proxy.web(req, res).catch(() => {})
else next()
})
// Proxy the Yjs WebSocket by hand (httpxy's ws upgrade is unreliable here).
// Only claim our paths; Vite's own HMR socket upgrade is left untouched.
server.httpServer?.on("upgrade", (req, socket, head) => {
if (!matches(req.url)) return
const proxyReq = http.request({
host: upstream.hostname,
port: upstream.port,
method: "GET",
path: req.url,
headers: req.headers,
})
proxyReq.on("upgrade", (proxyRes, proxySocket, proxyHead) => {
const lines = Object.entries(proxyRes.headers)
.map(([k, v]) => `${k}: ${Array.isArray(v) ? v.join(", ") : v}`)
.join("\r\n")
socket.write(
`HTTP/1.1 ${proxyRes.statusCode} ${proxyRes.statusMessage}\r\n${lines}\r\n\r\n`
)
if (proxyHead.length) socket.write(proxyHead)
feat: plan mode with model-driven entry and collaborative review (#1580) * 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>
2026-06-23 15:06:58 -04:00
if (head?.length) proxySocket.write(head)
proxySocket.on("error", () => socket.destroy())
socket.on("error", () => proxySocket.destroy())
proxySocket.pipe(socket)
socket.pipe(proxySocket)
})
proxyReq.on("error", () => socket.destroy())
proxyReq.end()
})
},
}
}
fix(ui): drive Vercel dashboard-API proxy through Nitro routeRules (#76) The Vercel deploy 404'd at `/` because PR #75's `vercel-build` script (`scripts/build-vercel-output.mjs`) ran `rm -rf .vercel/output` and rebuilt it from `.output/public`. On Vercel CI, Nitro's Vercel preset auto-activates (from the VERCEL env var) and emits the Build Output API layout to `.vercel/output` itself during `vite build`; the script then clobbered that correct output with a static-only config that could not resolve the SPA `_shell.html` fallback or the server functions, so production returned `404: NOT_FOUND` even though the build was READY. Stop fighting Nitro and drive the proxy through it instead: - Remove `scripts/build-vercel-output.mjs` and the `vercel-build` script; restore the plain `vite build` for both local and Vercel builds. - Add an env-driven Nitro `routeRules` proxy in `vite.config.ts`. Nitro's Vercel preset compiles a plain external-URL `proxy` rule into a CDN-level rewrite in `.vercel/output/config.json` at build time, reading LANGGRAPH_BACKEND_URL (the per-project Vercel env var). Proxy, not redirect, so the osw_session cookie stays first-party (same-origin). The build fails loudly if LANGGRAPH_BACKEND_URL is missing on Vercel; the rule is omitted for plain local/off-Vercel builds (which use the E2E_HARNESS mock proxy). - `vercel.json`: `buildCommand` back to `bun run build`; drop the `.output/public` outputDirectory so Vercel serves Nitro's `.vercel/output`. Validated with `LANGGRAPH_BACKEND_URL=... NITRO_PRESET=vercel bun run build`: the generated `.vercel/output/config.json` contains the `/dashboard/api/(.*)` -> backend rewrite ahead of `handle: filesystem` and the SPA catch-all, `_shell.html` and the 699 hashed assets are emitted, and typecheck passes. Supersedes the broken approach in #75.
2026-06-30 12:06:32 -04:00
// Same-origin proxy for the dashboard API. Vercel reads vercel.json BEFORE the build
// and never interpolates env into it, and prod promotes by fast-forward (so `dev` and
// `main` ship a byte-identical vercel.json that cannot encode a per-project backend).
// So the per-project backend is driven through Nitro instead: this `routeRules` proxy
// is compiled by Nitro's Vercel preset into a CDN-level rewrite in
// `.vercel/output/config.json` at build time, reading LANGGRAPH_BACKEND_URL from the
// per-project Vercel env var. Proxy (not redirect) keeps the osw_session cookie
// first-party on the Vercel origin. The `**` wildcard maps 1:1 to the destination.
function backendProxyRouteRules():
| Record<string, { proxy: string }>
| undefined {
const backend = process.env.LANGGRAPH_BACKEND_URL?.replace(/\/$/, "")
// Nitro's Vercel preset auto-activates from the VERCEL env var; NITRO_PRESET=vercel
// forces it locally. On Vercel the backend is mandatory — fail loudly rather than
// ship a build whose API calls 404, which is exactly how the previous approach broke.
const onVercel =
!!process.env.VERCEL || process.env.NITRO_PRESET === "vercel"
if (onVercel && process.env.VITE_DASHBOARD_API_BASE_URL) {
throw new Error(
"VITE_DASHBOARD_API_BASE_URL must not be set on Vercel builds - the API is " +
"same-origin via the LANGGRAPH_BACKEND_URL CDN proxy. A baked-in absolute " +
"API base sends OAuth logins to the backend host and breaks the state cookie.",
)
}
fix(ui): drive Vercel dashboard-API proxy through Nitro routeRules (#76) The Vercel deploy 404'd at `/` because PR #75's `vercel-build` script (`scripts/build-vercel-output.mjs`) ran `rm -rf .vercel/output` and rebuilt it from `.output/public`. On Vercel CI, Nitro's Vercel preset auto-activates (from the VERCEL env var) and emits the Build Output API layout to `.vercel/output` itself during `vite build`; the script then clobbered that correct output with a static-only config that could not resolve the SPA `_shell.html` fallback or the server functions, so production returned `404: NOT_FOUND` even though the build was READY. Stop fighting Nitro and drive the proxy through it instead: - Remove `scripts/build-vercel-output.mjs` and the `vercel-build` script; restore the plain `vite build` for both local and Vercel builds. - Add an env-driven Nitro `routeRules` proxy in `vite.config.ts`. Nitro's Vercel preset compiles a plain external-URL `proxy` rule into a CDN-level rewrite in `.vercel/output/config.json` at build time, reading LANGGRAPH_BACKEND_URL (the per-project Vercel env var). Proxy, not redirect, so the osw_session cookie stays first-party (same-origin). The build fails loudly if LANGGRAPH_BACKEND_URL is missing on Vercel; the rule is omitted for plain local/off-Vercel builds (which use the E2E_HARNESS mock proxy). - `vercel.json`: `buildCommand` back to `bun run build`; drop the `.output/public` outputDirectory so Vercel serves Nitro's `.vercel/output`. Validated with `LANGGRAPH_BACKEND_URL=... NITRO_PRESET=vercel bun run build`: the generated `.vercel/output/config.json` contains the `/dashboard/api/(.*)` -> backend rewrite ahead of `handle: filesystem` and the SPA catch-all, `_shell.html` and the 699 hashed assets are emitted, and typecheck passes. Supersedes the broken approach in #75.
2026-06-30 12:06:32 -04:00
if (!backend) {
if (onVercel) {
throw new Error(
"LANGGRAPH_BACKEND_URL is required for Vercel builds (set it per Vercel " +
"project: dev project -> dev langgraph URL, prod project -> prod langgraph URL).",
)
}
// Off Vercel with no backend configured (plain local `vite build`, tests): omit the
// proxy. Local dev gets its API via the E2E_HARNESS mock proxy above instead.
return undefined
}
return { "/dashboard/api/**": { proxy: `${backend}/dashboard/api/**` } }
}
chore: sync upstream/main, defer #1621 modular webhooks (#81) * chore: bake sfw binary into sandbox image (#1611) sfw only ships a launcher that fetches its real binary at first run and does a daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in the sandbox (restricted egress; the proxy injects the GitHub App installation token, which lacks access to that repo), so `sfw yarn install` errors with "could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline. * feat: editable plan mode + fix review-plan banner overlap (#1610) * feat: editable plan mode + fix review-plan banner overlap Lets the thread owner edit the plan markdown by hand from the plan-review page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id} endpoint that re-publishes the plan and mirrors it into the sandbox plan.md, so approve hands the edited plan to the agent as the source of truth. Also fixes the collapsed git-panel's floating expand button covering the "Review plan ->" banner by reserving space for it. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: abort plan approval when the published plan read fails get_plan_content() swallowed store errors and returned None, so a transient failure during approve would still mark the plan approved and dispatch the generic fallback text — silently dropping an owner's edited plan. Read the plan strictly (raise_on_error=True) so approval aborts instead, matching the comment read. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: show message timestamps (#1609) * feat: show message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: suppress fallback message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: stable message + tool-call hover timestamps Stamp a stable client-side arrival time per message and tool call (keyed by id, persisted to localStorage). Messages render the timestamp inline; tool rows reveal a dim timestamp chip on hover. Real backend created_at still takes precedence when present. * fix: hide client-stamped message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add PR trace resolution (#1612) * feat: add PR trace resolution Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: inject reviewer trace context as JSON Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: address review on PR trace resolution Use the documented LangSmith metadata filter syntax (and(eq(metadata_key,...), eq(metadata_value,...))) instead of has(metadata, '{...}'), which does not match runs — _list_thread_runs was silently returning nothing. Bound full-text searches to a 90-day window so they don't hit LangSmith's large-window rate limit. Also folds in the best-effort branch->head-sha resolver (dropping the weighted scoring/threshold + repo/file evidence + GitHub hydration), sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint. The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session were removed; resolution now runs deterministically from the trusted run config with no model-controlled pr_url or thread_id. * fix: scope branch trace search to the repo Branch names like fix-tests aren't unique across repos (or older PRs) in a shared tracing project, so an unscoped branch hit could resolve to an unrelated thread and write its runs into the reviewer sandbox. Require the repo slug to co-occur with the branch in matched runs; the full head SHA stays unscoped since it is globally unique. Addresses open-swe review on PR #1612. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: include plan links in PR descriptions (#1613) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: gate workflow pushes with approval (#1614) * feat: gate workflow pushes with approval Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve proxy refresh test compatibility Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: bind workflow approvals to pushed ref Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: recover thread work as patch (#1615) * feat: recover thread work as patch Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: search sandbox cwd for recovery patches Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: omit plan link in PR description when no plan exists (#1618) Plan links in PR descriptions were always built from the thread id, so runs that never produced a plan linked to an empty plan-review page. Now the plan content store is consulted first; the link is only added when a plan with non-empty markdown actually exists. A transient store failure degrades gracefully (no link) rather than blocking PR creation. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add filter & grouping menu to agents threads sidebar (#1617) Add a Cursor-style control to the agents sidebar that groups (None/Date/ Status/Project), filters (ownership, status, source, pull request, model, repo, include-resolved), and compacts the threads list. All client-side over already-fetched sidebar threads; preferences persist in localStorage. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: update langsmith sdk to 0.9.3 (#1616) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: clickable shared PR header in git panel and reviews (#1620) * feat: clickable shared PR header in git panel and reviews Replace the standalone "View PR" button in the agent git panel with a clickable PR title, matching the reviews view. Extract a shared PrHeader component reused by both the git panel and the review main body. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * refactor: drop PrHeader wrapper, use shared component directly The review-side PrHeader was just a thin adapter mapping detail -> the shared component's props. Inline it at the call site and use the shared PrHeader directly so there's a single component. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * refactor: durable interrupt dispatch + completion webhook (#1621) * wip(rebuild): core reliability spine - remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring) - dispatch core: agent/dispatch.py with multitask_strategy=interrupt + durability=sync + completion webhook; reroute all webhook + plan triggers; drop the racy in-process lock + is_thread_active busy-check - completion webhook: agent/completion.py + /webhooks/run-complete loopback route for failure/timeout replies (idempotent) Co-authored-by: open-swe[bot] * feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning Parallel batch on top of the reliability spine: - async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden the IP check to 'not is_global' (+ IPv4-mapped unwrap) - reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list -> cancel_many), wired into the scheduler graph via task='reconcile' - shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare httpx.AsyncClient() across utils/dashboard/webapp/middleware - run budget: MODEL_CALL_RECURSION_LIMIT 5000->250 - fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8) - drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls) - confirm tool-result eviction + summarization auto-wired via backend - slim system prompt ~8% (full harness-profile rewrite deferred) Co-authored-by: open-swe[bot] * feat(rebuild): harness-profile prompt + split webhooks out of webapp - prompt.py: own the system prompt via a registered harness profile (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that share it stay safe), registered across all 4 providers; per-thread values stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped ALL-CAPS markers. - webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the routes + tests; moved handlers reach shared helpers via the webapp namespace to preserve the test suite's monkeypatch targets. Full suite: 1168 passing, lint clean. Co-authored-by: open-swe[bot] * Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks Reverts the 250 cap from the run-budget change — long-running tasks legitimately need many model calls. The notify_step_limit_reached safety net still fires if a run does hit the cap, so runs end with a signal either way. Co-authored-by: open-swe[bot] * fix: address PR review (auth, SSRF, interrupted status, redirect headers) - completion.py: drop `interrupted` from failure statuses — with multitask_strategy=interrupt a follow-up ends the prior run as interrupted, which is healthy, not a failure to report. [open-swe] - /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest. [corridor-security] - SSRF: extract the URL validator to agent/utils/url_safety.py and apply it before server-side image fetches in multimodal.fetch_image_block. [corridor-security] - http_request: preserve caller headers/extensions across redirect hops instead of dropping them on the first hop. [open-swe] Co-authored-by: open-swe[bot] * chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo) Co-authored-by: open-swe[bot] * fix: fail closed on run-complete webhook auth when secret unset Corridor follow-up: verify_run_complete_token returns False (not True) when RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never unauthenticated. Logs a startup warning when the secret is absent, and dispatch skips registering the webhook when there's no secret (no rejected callbacks). Co-authored-by: open-swe[bot] --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: restore forced tool call to prevent premature run stops (#1622) Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task. Shipping to test whether it fixes runs that stop halfway through. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619) Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1. - [Release notes](https://github.com/langchain-ai/langgraph/releases) - [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1) --- updated-dependencies: - dependency-name: langgraph-checkpoint dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * fix: post reviewer resolution notes verbatim (#1624) * fix: post reviewer resolution notes verbatim Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: stabilize dashboard follow-up e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve dashboard attribution in e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: make e2e attribution marker durable Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: only echo found e2e attribution Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: check live dashboard attribution in e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625) Installs hung when prefixed with sfw inside the sandbox (trace 019f0608 stalled on a pending `sfw npm install` execute, never returned). Strip the Socket Firewall guidance from the agent and reviewer prompts so installs run through the project's package manager directly. sfw stays in the Docker image; nothing invokes it now. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: make plan view mobile friendly (#1636) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: fall back to vision model for image threads (#1626) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: surface Slack thread errors (#1627) * fix: surface Slack thread errors Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: don't set failure_reply_posted on Slack preprocessing errors The preprocessing error handler was setting failure_reply_posted=True, the same idempotency flag handle_run_completion checks to suppress duplicate run-failure replies. Since preprocessing failures happen before any run exists but the flag persists on the thread, a subsequent run failure on the same thread would be silently ignored. The preprocessing handler already posts its own Slack reply, so the run-completion idempotency flag should not be set here. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: avoid recapping Slack replies (#1629) * chore: avoid recapping Slack replies Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: simplify Slack reply prompt wording Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: update Slack trace reply on web handoff (#1630) * fix: update Slack trace reply on web handoff Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: trigger web handoff on dashboard starts Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: format web handoff as contextual fragment Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve trace_message_ts when overwriting Slack run mapping When store_slack_run_mapping is called without trace_message_ts (e.g. on follow-up Slack mentions), it was unconditionally overwriting the thread-level mapping and clobbering the timestamp captured from the initial trace reply. After that, _notify_slack_web_handoff could not find the original message, so a subsequent move to Web silently skipped the Slack trace update. Now, when trace_message_ts is not passed, the existing thread mapping is read first and its trace_message_ts is preserved. * style: ruff format --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643) * fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures shiki lazy-imports a grammar per language and these libs only live inside lazy route components, so Vite's startup scanner never sees them. They get discovered on first thread navigation, triggering a dep re-optimize + force-reload that aborts the in-flight route-chunk import, surfacing as "Failed to fetch dynamically imported module: .../$threadId.tsx". Pre-bundle them (and the github themes + common code-block languages) via optimizeDeps.include so the optimize happens once at startup. Dev-only; production bundles are unaffected. * fix: pre-bundle canonical shiki docker/make langs instead of aliases --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: show queued dashboard follow-ups (#1631) * feat: show queued dashboard follow-ups Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: de-dupe queued follow-ups while streaming --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * feat: notify Slack on plan approval (#1632) * feat: notify Slack on plan approval Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: post Slack approval notice after successful dispatch Move the _maybe_post_plan_approved_to_slack call until after _dispatch_followup succeeds so the Slack thread is not told implementation is beginning before the LangGraph run is created. Addresses PR review comment. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * feat: include Slack channel context in prompts (#1633) Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> * chore: keep plan guidance high-level (#1634) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: publish plans from sandbox files (#1635) * feat: publish plans from sandbox files Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: avoid fixed plan filenames Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: virtualize local sandbox file paths Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve plan_file_path across set_plan_status set_plan_status was rewriting the content record with only markdown and status, dropping plan_file_path. After a reject, the owner's dashboard edit would mirror to a different file than the agent's original, and the next save_plan could republish the stale file. Preserve plan_file_path when updating status. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: return to thread after plan approval (#1637) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add Slack breakout thread tool (#1638) * feat: add Slack breakout thread tool Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: make fake LLM scripts declarative Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: exclude slack_start_new_thread from plan mode The breakout tool can dispatch a fresh agent run that starts outside the current plan-mode state, bypassing the approval flow. Add it to PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating tools while planning. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: require bun for ui agent work (#1639) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: request actions read for sandbox logs (#1642) * fix: request actions read for sandbox logs Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: restore actions:read scope after workflow push After an approved workflow push, the guard was restoring the proxy with BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which includes actions: read) and fall back to BASE if the install hasn't granted Actions read — mirroring the pattern in _create_sandbox_with_proxy. Addresses review comment on PR #1642. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: widen split review diffs (#1647) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: install missing deps before verification (#1646) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: switch ui to pnpm (#1645) * chore: require pnpm for ui agent work Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: switch ui to pnpm Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * ci: use corepack for ui pnpm e2e build Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add Sonnet 5 to model picker (#1651) * chore: update Sonnet examples to Sonnet 5 Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: add Sonnet 5 to model picker Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * Remove dead breakout-thread e2e scenario after dropping the tool The merge resolution deferred upstream's Slack breakout-thread tool (slack_start_new_thread, #1638) since it depends on the #1621 dispatch module, but the e2e harness still scripted it. Removing the tool name from fake_llm.py's _tool_step call left a malformed scenario, crashing the langgraph-dev web server at import (TypeError: _tool_step() missing 'call_id') and failing Playwright E2E. Drop the "breakout" script scenario, its _is_breakout_request helper + ScriptRule, and the corresponding full_flow.spec.ts test. * Revert upstream pnpm switch; keep bun for the UI build The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/ global-setup.ts and ui/package.json, but our fork builds the UI with bun (vercel.json + the E2E workflow's setup-bun). That left the Playwright globalSetup running `corepack pnpm install --frozen-lockfile` with no pnpm-lock.yaml, failing E2E at UI build time. Revert global-setup.ts and ui/package.json to the dev (bun) baseline, drop the merge-added ui/pnpm-lock.yaml, and remove the re-added ui/AGENTS.md (our fork had deleted it). * Align plan-review e2e + UI with the HEAD (pre-#1635) backend The merge left a split plan vertical: the backend save_plan/plan_api are HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/ #1637 per #80), but the plan UI and e2e harness were upstream's. The fake_llm scenario called save_plan(plan_file_path=...) — upstream's file-based #1635 contract — while HEAD save_plan takes plan_markdown, so the plan never saved and PlanReview never rendered (E2E failure on the plan-review locator). Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts / $threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the whole plan flow (save -> render -> approve -> implement) is consistent with the HEAD backend. --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev> Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com> Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
// shiki lazily `import()`s one grammar per language on first render. These libs
// also only live inside lazy route components, so Vite's startup scanner never
// reaches them — it discovers them on first thread navigation, re-optimizes deps,
// and force-reloads, aborting the in-flight route-chunk import ("Failed to fetch
// dynamically imported module"). Pre-bundling them up front avoids the reload.
// Uncommon languages not listed just trigger a one-time, graceful re-optimize.
const SHIKI_LANGS = [
"bash",
"c",
"cpp",
"csharp",
"css",
"diff",
"docker",
"go",
"graphql",
"html",
"java",
"javascript",
"json",
"jsonc",
"jsx",
"kotlin",
"lua",
"make",
"markdown",
"php",
"python",
"ruby",
"rust",
"scala",
"shellscript",
"sql",
"swift",
"toml",
"tsx",
"typescript",
"xml",
"yaml",
]
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
const config = defineConfig({
chore: sync upstream/main, defer #1621 modular webhooks (#81) * chore: bake sfw binary into sandbox image (#1611) sfw only ships a launcher that fetches its real binary at first run and does a daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in the sandbox (restricted egress; the proxy injects the GitHub App installation token, which lacks access to that repo), so `sfw yarn install` errors with "could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline. * feat: editable plan mode + fix review-plan banner overlap (#1610) * feat: editable plan mode + fix review-plan banner overlap Lets the thread owner edit the plan markdown by hand from the plan-review page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id} endpoint that re-publishes the plan and mirrors it into the sandbox plan.md, so approve hands the edited plan to the agent as the source of truth. Also fixes the collapsed git-panel's floating expand button covering the "Review plan ->" banner by reserving space for it. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: abort plan approval when the published plan read fails get_plan_content() swallowed store errors and returned None, so a transient failure during approve would still mark the plan approved and dispatch the generic fallback text — silently dropping an owner's edited plan. Read the plan strictly (raise_on_error=True) so approval aborts instead, matching the comment read. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: show message timestamps (#1609) * feat: show message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: suppress fallback message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: stable message + tool-call hover timestamps Stamp a stable client-side arrival time per message and tool call (keyed by id, persisted to localStorage). Messages render the timestamp inline; tool rows reveal a dim timestamp chip on hover. Real backend created_at still takes precedence when present. * fix: hide client-stamped message timestamps Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add PR trace resolution (#1612) * feat: add PR trace resolution Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: inject reviewer trace context as JSON Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: address review on PR trace resolution Use the documented LangSmith metadata filter syntax (and(eq(metadata_key,...), eq(metadata_value,...))) instead of has(metadata, '{...}'), which does not match runs — _list_thread_runs was silently returning nothing. Bound full-text searches to a 90-day window so they don't hit LangSmith's large-window rate limit. Also folds in the best-effort branch->head-sha resolver (dropping the weighted scoring/threshold + repo/file evidence + GitHub hydration), sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint. The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session were removed; resolution now runs deterministically from the trusted run config with no model-controlled pr_url or thread_id. * fix: scope branch trace search to the repo Branch names like fix-tests aren't unique across repos (or older PRs) in a shared tracing project, so an unscoped branch hit could resolve to an unrelated thread and write its runs into the reviewer sandbox. Require the repo slug to co-occur with the branch in matched runs; the full head SHA stays unscoped since it is globally unique. Addresses open-swe review on PR #1612. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: include plan links in PR descriptions (#1613) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: gate workflow pushes with approval (#1614) * feat: gate workflow pushes with approval Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve proxy refresh test compatibility Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: bind workflow approvals to pushed ref Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: recover thread work as patch (#1615) * feat: recover thread work as patch Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: search sandbox cwd for recovery patches Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: omit plan link in PR description when no plan exists (#1618) Plan links in PR descriptions were always built from the thread id, so runs that never produced a plan linked to an empty plan-review page. Now the plan content store is consulted first; the link is only added when a plan with non-empty markdown actually exists. A transient store failure degrades gracefully (no link) rather than blocking PR creation. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add filter & grouping menu to agents threads sidebar (#1617) Add a Cursor-style control to the agents sidebar that groups (None/Date/ Status/Project), filters (ownership, status, source, pull request, model, repo, include-resolved), and compacts the threads list. All client-side over already-fetched sidebar threads; preferences persist in localStorage. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: update langsmith sdk to 0.9.3 (#1616) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: clickable shared PR header in git panel and reviews (#1620) * feat: clickable shared PR header in git panel and reviews Replace the standalone "View PR" button in the agent git panel with a clickable PR title, matching the reviews view. Extract a shared PrHeader component reused by both the git panel and the review main body. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * refactor: drop PrHeader wrapper, use shared component directly The review-side PrHeader was just a thin adapter mapping detail -> the shared component's props. Inline it at the call site and use the shared PrHeader directly so there's a single component. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * refactor: durable interrupt dispatch + completion webhook (#1621) * wip(rebuild): core reliability spine - remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring) - dispatch core: agent/dispatch.py with multitask_strategy=interrupt + durability=sync + completion webhook; reroute all webhook + plan triggers; drop the racy in-process lock + is_thread_active busy-check - completion webhook: agent/completion.py + /webhooks/run-complete loopback route for failure/timeout replies (idempotent) Co-authored-by: open-swe[bot] * feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning Parallel batch on top of the reliability spine: - async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden the IP check to 'not is_global' (+ IPv4-mapped unwrap) - reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list -> cancel_many), wired into the scheduler graph via task='reconcile' - shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare httpx.AsyncClient() across utils/dashboard/webapp/middleware - run budget: MODEL_CALL_RECURSION_LIMIT 5000->250 - fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8) - drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls) - confirm tool-result eviction + summarization auto-wired via backend - slim system prompt ~8% (full harness-profile rewrite deferred) Co-authored-by: open-swe[bot] * feat(rebuild): harness-profile prompt + split webhooks out of webapp - prompt.py: own the system prompt via a registered harness profile (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that share it stay safe), registered across all 4 providers; per-thread values stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped ALL-CAPS markers. - webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the routes + tests; moved handlers reach shared helpers via the webapp namespace to preserve the test suite's monkeypatch targets. Full suite: 1168 passing, lint clean. Co-authored-by: open-swe[bot] * Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks Reverts the 250 cap from the run-budget change — long-running tasks legitimately need many model calls. The notify_step_limit_reached safety net still fires if a run does hit the cap, so runs end with a signal either way. Co-authored-by: open-swe[bot] * fix: address PR review (auth, SSRF, interrupted status, redirect headers) - completion.py: drop `interrupted` from failure statuses — with multitask_strategy=interrupt a follow-up ends the prior run as interrupted, which is healthy, not a failure to report. [open-swe] - /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest. [corridor-security] - SSRF: extract the URL validator to agent/utils/url_safety.py and apply it before server-side image fetches in multimodal.fetch_image_block. [corridor-security] - http_request: preserve caller headers/extensions across redirect hops instead of dropping them on the first hop. [open-swe] Co-authored-by: open-swe[bot] * chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo) Co-authored-by: open-swe[bot] * fix: fail closed on run-complete webhook auth when secret unset Corridor follow-up: verify_run_complete_token returns False (not True) when RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never unauthenticated. Logs a startup warning when the secret is absent, and dispatch skips registering the webhook when there's no secret (no rejected callbacks). Co-authored-by: open-swe[bot] --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: restore forced tool call to prevent premature run stops (#1622) Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task. Shipping to test whether it fixes runs that stop halfway through. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619) Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1. - [Release notes](https://github.com/langchain-ai/langgraph/releases) - [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1) --- updated-dependencies: - dependency-name: langgraph-checkpoint dependency-version: 4.1.1 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * fix: post reviewer resolution notes verbatim (#1624) * fix: post reviewer resolution notes verbatim Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: stabilize dashboard follow-up e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve dashboard attribution in e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: make e2e attribution marker durable Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: only echo found e2e attribution Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: check live dashboard attribution in e2e Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625) Installs hung when prefixed with sfw inside the sandbox (trace 019f0608 stalled on a pending `sfw npm install` execute, never returned). Strip the Socket Firewall guidance from the agent and reviewer prompts so installs run through the project's package manager directly. sfw stays in the Docker image; nothing invokes it now. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: make plan view mobile friendly (#1636) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: fall back to vision model for image threads (#1626) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: surface Slack thread errors (#1627) * fix: surface Slack thread errors Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: don't set failure_reply_posted on Slack preprocessing errors The preprocessing error handler was setting failure_reply_posted=True, the same idempotency flag handle_run_completion checks to suppress duplicate run-failure replies. Since preprocessing failures happen before any run exists but the flag persists on the thread, a subsequent run failure on the same thread would be silently ignored. The preprocessing handler already posts its own Slack reply, so the run-completion idempotency flag should not be set here. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: avoid recapping Slack replies (#1629) * chore: avoid recapping Slack replies Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: simplify Slack reply prompt wording Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: update Slack trace reply on web handoff (#1630) * fix: update Slack trace reply on web handoff Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: trigger web handoff on dashboard starts Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: format web handoff as contextual fragment Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve trace_message_ts when overwriting Slack run mapping When store_slack_run_mapping is called without trace_message_ts (e.g. on follow-up Slack mentions), it was unconditionally overwriting the thread-level mapping and clobbering the timestamp captured from the initial trace reply. After that, _notify_slack_web_handoff could not find the original message, so a subsequent move to Web silently skipped the Slack trace update. Now, when trace_message_ts is not passed, the existing thread mapping is read first and its trace_message_ts is preserved. * style: ruff format --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643) * fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures shiki lazy-imports a grammar per language and these libs only live inside lazy route components, so Vite's startup scanner never sees them. They get discovered on first thread navigation, triggering a dep re-optimize + force-reload that aborts the in-flight route-chunk import, surfacing as "Failed to fetch dynamically imported module: .../$threadId.tsx". Pre-bundle them (and the github themes + common code-block languages) via optimizeDeps.include so the optimize happens once at startup. Dev-only; production bundles are unaffected. * fix: pre-bundle canonical shiki docker/make langs instead of aliases --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: show queued dashboard follow-ups (#1631) * feat: show queued dashboard follow-ups Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: de-dupe queued follow-ups while streaming --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * feat: notify Slack on plan approval (#1632) * feat: notify Slack on plan approval Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: post Slack approval notice after successful dispatch Move the _maybe_post_plan_approved_to_slack call until after _dispatch_followup succeeds so the Slack thread is not told implementation is beginning before the LangGraph run is created. Addresses PR review comment. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> * feat: include Slack channel context in prompts (#1633) Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> * chore: keep plan guidance high-level (#1634) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: publish plans from sandbox files (#1635) * feat: publish plans from sandbox files Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: avoid fixed plan filenames Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: virtualize local sandbox file paths Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve plan_file_path across set_plan_status set_plan_status was rewriting the content record with only markdown and status, dropping plan_file_path. After a reject, the owner's dashboard edit would mirror to a different file than the agent's original, and the next save_plan could republish the stale file. Preserve plan_file_path when updating status. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: return to thread after plan approval (#1637) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add Slack breakout thread tool (#1638) * feat: add Slack breakout thread tool Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: make fake LLM scripts declarative Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: exclude slack_start_new_thread from plan mode The breakout tool can dispatch a fresh agent run that starts outside the current plan-mode state, bypassing the approval flow. Add it to PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating tools while planning. --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: require bun for ui agent work (#1639) Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: request actions read for sandbox logs (#1642) * fix: request actions read for sandbox logs Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: restore actions:read scope after workflow push After an approved workflow push, the guard was restoring the proxy with BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which includes actions: read) and fall back to BASE if the install hasn't granted Actions read — mirroring the pattern in _create_sandbox_with_proxy. Addresses review comment on PR #1642. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: widen split review diffs (#1647) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: install missing deps before verification (#1646) Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: switch ui to pnpm (#1645) * chore: require pnpm for ui agent work Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: switch ui to pnpm Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * ci: use corepack for ui pnpm e2e build Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * feat: add Sonnet 5 to model picker (#1651) * chore: update Sonnet examples to Sonnet 5 Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: add Sonnet 5 to model picker Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * Remove dead breakout-thread e2e scenario after dropping the tool The merge resolution deferred upstream's Slack breakout-thread tool (slack_start_new_thread, #1638) since it depends on the #1621 dispatch module, but the e2e harness still scripted it. Removing the tool name from fake_llm.py's _tool_step call left a malformed scenario, crashing the langgraph-dev web server at import (TypeError: _tool_step() missing 'call_id') and failing Playwright E2E. Drop the "breakout" script scenario, its _is_breakout_request helper + ScriptRule, and the corresponding full_flow.spec.ts test. * Revert upstream pnpm switch; keep bun for the UI build The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/ global-setup.ts and ui/package.json, but our fork builds the UI with bun (vercel.json + the E2E workflow's setup-bun). That left the Playwright globalSetup running `corepack pnpm install --frozen-lockfile` with no pnpm-lock.yaml, failing E2E at UI build time. Revert global-setup.ts and ui/package.json to the dev (bun) baseline, drop the merge-added ui/pnpm-lock.yaml, and remove the re-added ui/AGENTS.md (our fork had deleted it). * Align plan-review e2e + UI with the HEAD (pre-#1635) backend The merge left a split plan vertical: the backend save_plan/plan_api are HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/ #1637 per #80), but the plan UI and e2e harness were upstream's. The fake_llm scenario called save_plan(plan_file_path=...) — upstream's file-based #1635 contract — while HEAD save_plan takes plan_markdown, so the plan never saved and PlanReview never rendered (E2E failure on the plan-review locator). Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts / $threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the whole plan flow (save -> render -> approve -> implement) is consistent with the HEAD backend. --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev> Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com> Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
optimizeDeps: {
include: [
"workbox-window",
"streamdown",
"shiki",
"@pierre/diffs",
"@pierre/diffs/react",
"@pierre/trees",
"@pierre/trees/react",
"@shikijs/themes/github-light",
"@shikijs/themes/github-dark",
...SHIKI_LANGS.map((lang) => `@shikijs/langs/${lang}`),
],
},
worker: { format: "es" },
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
plugins: [
feat: plan mode with model-driven entry and collaborative review (#1580) * 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>
2026-06-23 15:06:58 -04:00
mockHarnessProxy(),
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
devtools(),
fix(ui): drive Vercel dashboard-API proxy through Nitro routeRules (#76) The Vercel deploy 404'd at `/` because PR #75's `vercel-build` script (`scripts/build-vercel-output.mjs`) ran `rm -rf .vercel/output` and rebuilt it from `.output/public`. On Vercel CI, Nitro's Vercel preset auto-activates (from the VERCEL env var) and emits the Build Output API layout to `.vercel/output` itself during `vite build`; the script then clobbered that correct output with a static-only config that could not resolve the SPA `_shell.html` fallback or the server functions, so production returned `404: NOT_FOUND` even though the build was READY. Stop fighting Nitro and drive the proxy through it instead: - Remove `scripts/build-vercel-output.mjs` and the `vercel-build` script; restore the plain `vite build` for both local and Vercel builds. - Add an env-driven Nitro `routeRules` proxy in `vite.config.ts`. Nitro's Vercel preset compiles a plain external-URL `proxy` rule into a CDN-level rewrite in `.vercel/output/config.json` at build time, reading LANGGRAPH_BACKEND_URL (the per-project Vercel env var). Proxy, not redirect, so the osw_session cookie stays first-party (same-origin). The build fails loudly if LANGGRAPH_BACKEND_URL is missing on Vercel; the rule is omitted for plain local/off-Vercel builds (which use the E2E_HARNESS mock proxy). - `vercel.json`: `buildCommand` back to `bun run build`; drop the `.output/public` outputDirectory so Vercel serves Nitro's `.vercel/output`. Validated with `LANGGRAPH_BACKEND_URL=... NITRO_PRESET=vercel bun run build`: the generated `.vercel/output/config.json` contains the `/dashboard/api/(.*)` -> backend rewrite ahead of `handle: filesystem` and the SPA catch-all, `_shell.html` and the 699 hashed assets are emitted, and typecheck passes. Supersedes the broken approach in #75.
2026-06-30 12:06:32 -04:00
nitro({ routeRules: backendProxyRouteRules() }),
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
viteTsConfigPaths({
projects: ["./tsconfig.json"],
}),
tailwindcss(),
tanstackStart({ spa: { enabled: true } }),
VitePWA({
injectRegister: false,
registerType: "prompt",
outDir: ".output/public",
devOptions: {
// Off in dev: the service worker precaches assets and defeats HMR (and
// a stale registration lingers per-origin). Dev is HMR-only.
enabled: false,
},
integration: {
closeBundleOrder: "pre",
},
manifest: {
id: "/",
name: "Open SWE",
short_name: "Open SWE",
description: "Open-source coding agents for Slack, Linear, and GitHub.",
start_url: "/",
scope: "/",
display: "standalone",
theme_color: "#000000",
background_color: "#ffffff",
icons: [
{
src: "/favicon.png",
sizes: "192x192",
type: "image/png",
},
{
src: "/logo512.png",
sizes: "512x512",
type: "image/png",
purpose: "any maskable",
},
],
},
workbox: {
navigateFallback: "/_shell.html",
navigateFallbackDenylist: [/^\/dashboard\/api\//, /^\/_serverFn\//],
globPatterns: ["**/*.{js,css,png,svg,ico,webmanifest}"],
additionalManifestEntries: [
{ url: "/_shell.html", revision: new Date().toISOString() },
],
},
}),
feat: open-swe dashboard for per-user profile config (#1302) * 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.
2026-05-15 11:23:53 -07:00
viteReact(),
],
})
export default config