From 2c91a80f691f5098cf48057900daca1b0b27baf6 Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 3 Oct 2026 13:58:39 +0000 Subject: [PATCH] feat(onboarding): ask before discovering projects and let the user choose The onboarding scan started on its own, discarded what it found, claimed to read email and calendars, simulated progress for everyone who could not scan, and its project creation always failed (wrong Space fields and a space lookup by title across tenants). Discovery now asks first and creates nothing without a choice: - The scan step appears only for the deployment owner when ONBOARDING_SCAN_HOME is set; everyone else skips it. The simulated scan is gone. - It shows the folder and asks. Only directory listings are read: git projects up to four levels deep, their languages and a few tools (Docker, GitHub Actions, Terraform). Symlinks are never followed and each chosen folder is resolved again before use, so nothing outside the folder is reached. Results stay with the account that scanned. - Found projects are a checklist (none preselected); found languages and tools are facts (preselected). "Add" creates one project space per chosen project with createSpaceForMember and wireProjectWorkspace in the user's own organization, reusing the user's own space already linked to that folder, and saves the chosen facts as onboarding facts under the profile lock and fact limit. - When a connection becomes connected (direct connect, authorization round trip, or catalog reconciliation), "Uses " is remembered as a tools fact from the connector. Revoking keeps it. The E2E harness now points ONBOARDING_SCAN_HOME at a fixture folder and starts without a deployment owner, so owner-only onboarding steps appear only in specs that take the seat through /__e2e/deployment-owner. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01MRtGG9ARfqqhma3t85Ro2u --- .env.example | 6 +- apps/api/src/connected-app-facts.ts | 50 + apps/api/src/onboarding-scan.test.ts | 208 ++- apps/api/src/onboarding-scan.ts | 1134 ++++++----------- apps/api/src/router.ts | 49 +- apps/web/e2e/onboarding-discovery.spec.ts | 76 ++ .../onboarding/OnboardingScanProgress.tsx | 186 --- .../onboarding/OnboardingScanStep.tsx | 250 ++++ apps/web/src/pages/Onboarding.tsx | 18 +- packages/contracts/src/index.ts | 1 + packages/contracts/src/onboarding-scan.ts | 49 + packages/contracts/src/rpc.ts | 22 +- packages/testkit/src/authorization.test.ts | 25 +- packages/testkit/src/cli/harness.ts | 59 +- .../src/onboarding-discovery.postgres.test.ts | 363 ++++++ .../testkit/src/onboarding-scan-fixture.ts | 35 + 16 files changed, 1494 insertions(+), 1037 deletions(-) create mode 100644 apps/api/src/connected-app-facts.ts create mode 100644 apps/web/e2e/onboarding-discovery.spec.ts delete mode 100644 apps/web/src/components/onboarding/OnboardingScanProgress.tsx create mode 100644 apps/web/src/components/onboarding/OnboardingScanStep.tsx create mode 100644 packages/contracts/src/onboarding-scan.ts create mode 100644 packages/testkit/src/onboarding-discovery.postgres.test.ts create mode 100644 packages/testkit/src/onboarding-scan-fixture.ts diff --git a/.env.example b/.env.example index 5d588c8..8ebb743 100644 --- a/.env.example +++ b/.env.example @@ -25,9 +25,9 @@ PUBLIC_POSTHOG_KEY= PUBLIC_POSTHOG_HOST=https://us.i.posthog.com SIGNUPS_ENABLED=true SIGNUP_ALLOWLIST= -# First-run discovery. Leave unset and the onboarding scan never touches the host filesystem. -# Set a home-style directory (its Projects, Documents, src, ... subfolders are scanned) to let the -# deployment owner's own onboarding discover local projects. Other accounts never scan the host. +# First-run discovery. Leave unset and onboarding never looks at the host filesystem. +# Set a folder (for example a home folder) and the deployment owner's onboarding offers to list the +# git projects in it, reading file and folder names only. Other accounts never see the step. # ONBOARDING_SCAN_HOME= ENCRYPTION_KEY=replace-with-64-random-hex-characters DATA_DIR=./data diff --git a/apps/api/src/connected-app-facts.ts b/apps/api/src/connected-app-facts.ts new file mode 100644 index 0000000..5b83abe --- /dev/null +++ b/apps/api/src/connected-app-facts.ts @@ -0,0 +1,50 @@ +import { FEATURED_CONNECTOR_LABELS, matchFeaturedConnectorId } from "@rakazo/core"; +import type { PrismaClient } from "@rakazo/db"; +import { updateUserProfile } from "@rakazo/db"; +import { getLogger } from "@rakazo/logging"; + +/** + * The app's own name: a featured app's label, otherwise the label of the user's first account for + * it (later accounts may be named "Gmail 2" or renamed). + */ +async function connectedAppName( + prisma: PrismaClient, + connection: { userId: string; connectorId: string; provider: string }, +): Promise { + const featured = matchFeaturedConnectorId(connection.provider); + if (featured) return FEATURED_CONNECTOR_LABELS[featured]; + const first = await prisma.connection.findFirst({ + where: { + userId: connection.userId, + connectorId: connection.connectorId, + provider: connection.provider, + }, + orderBy: [{ createdAt: "asc" }, { id: "asc" }], + select: { displayName: true }, + }); + const name = first?.displayName.trim().slice(0, 80); + return name || null; +} + +/** + * Remembers "Uses " in the user's profile when one of their connections becomes connected. + * Revoking the connection keeps the fact; the user removes it in About you. Best effort: the + * connection itself has already succeeded, so a full profile or a database error only logs. + */ +export async function recordConnectedApp( + prisma: PrismaClient, + connection: { userId: string; connectorId: string; provider: string }, +): Promise { + try { + const name = await connectedAppName(prisma, connection); + if (!name) return; + await updateUserProfile(prisma, connection.userId, { + addFacts: [{ category: "tools", value: `Uses ${name}`, source: "connector" }], + }); + } catch (error) { + getLogger().error("connected app fact was not recorded", error, { + connectorId: connection.connectorId, + provider: connection.provider, + }); + } +} diff --git a/apps/api/src/onboarding-scan.test.ts b/apps/api/src/onboarding-scan.test.ts index ea2e625..9cbafd9 100644 --- a/apps/api/src/onboarding-scan.test.ts +++ b/apps/api/src/onboarding-scan.test.ts @@ -1,64 +1,192 @@ -import { mkdir, mkdtemp, writeFile } from "node:fs/promises"; +import { mkdir, mkdtemp, realpath, rm, symlink, writeFile } from "node:fs/promises"; import { tmpdir } from "node:os"; -import { join } from "node:path"; -import { afterEach, describe, expect, it, vi } from "vitest"; -import { getScanStatus, startOnboardingScan } from "./onboarding-scan.js"; +import path from "node:path"; +import type { PrismaClient } from "@rakazo/db"; +import { afterAll, describe, expect, it, vi } from "vitest"; +import { + applyOnboardingScan, + discoverOnboardingScan, + onboardingScanFolder, + onboardingScanStatus, + startOnboardingScan, +} from "./onboarding-scan.js"; -const owner = { userId: "user-owner", isDeploymentOwner: true }; -const member = { userId: "user-member", isDeploymentOwner: false }; +const owner = { userId: "user-owner", spaceId: "space-owner", isDeploymentOwner: true }; +const member = { userId: "user-member", spaceId: "space-member", isDeploymentOwner: false }; +const roots: string[] = []; -async function scanHomeWithOneFile(): Promise { - const home = await mkdtemp(join(tmpdir(), "evoo-scan-")); - await mkdir(join(home, "Projects")); - await writeFile(join(home, "Projects", "notes.ts"), "export const x = 1;\n"); - return home; +/** Fails the test if the scan writes anything before its checks pass. */ +const untouchedPrisma = new Proxy( + {}, + { + get() { + throw new Error("the database must not be touched"); + }, + }, +) as PrismaClient; + +async function tempDir(): Promise { + const dir = await realpath(await mkdtemp(path.join(tmpdir(), "evoo-scan-"))); + roots.push(dir); + return dir; +} + +async function files(root: string, entries: string[]): Promise { + for (const entry of entries) { + const file = path.join(root, entry); + await mkdir(path.dirname(file), { recursive: true }); + await writeFile(file, "x\n"); + } +} + +async function project(root: string, relative: string, entries: string[]): Promise { + await mkdir(path.join(root, relative, ".git"), { recursive: true }); + await files(path.join(root, relative), entries); } async function completed(scanId: string, userId: string) { return await vi.waitFor( - async () => { - const status = await getScanStatus(scanId, userId); - if (status.status !== "complete" && status.status !== "failed") throw new Error("pending"); + () => { + const status = onboardingScanStatus(scanId, userId); + if (status.status === "scanning") throw new Error("pending"); return status; }, - { timeout: 10_000, interval: 50 }, + { timeout: 10_000, interval: 20 }, ); } +afterAll(async () => { + await Promise.all(roots.map((root) => rm(root, { recursive: true, force: true }))); +}); + describe("onboarding scan", () => { - afterEach(() => { - vi.unstubAllEnvs(); + it("lists git projects with their languages and tools and never follows a symlink", async () => { + const home = await tempDir(); + const outside = await tempDir(); + // A home folder tracked by git is not itself a project. + await mkdir(path.join(home, ".git")); + await project(home, "code/atlas", [ + "src/a.ts", + "src/b.ts", + "src/c.ts", + "src/d.tsx", + "scripts/build.js", + "Dockerfile", + ".github/workflows/ci.yml", + "infra/main.tf", + "src/odd.constructor", + "node_modules/dep/index.js", + "node_modules/dep/more.js", + ]); + await project(home, "code/garden", ["main.py"]); + await project(home, "deep/a/b/edge", ["tool.py"]); + await project(home, "deep/a/b/c/too-deep", ["main.go"]); + await project(home, ".hidden/secret", ["main.go"]); + await project(home, "notes/node_modules/vendored", ["main.go"]); + await files(home, ["notes/todo.md"]); + await project(outside, "escaped", ["main.rs"]); + await symlink(path.join(outside, "escaped"), path.join(home, "linked")); + await symlink(outside, path.join(home, "code/atlas/src/outside")); + + const findings = await discoverOnboardingScan(home); + + expect(findings.projects).toEqual([ + { + id: "project-0", + name: "atlas", + path: "code/atlas", + languages: ["TypeScript", "JavaScript"], + tools: ["Docker", "GitHub Actions", "Terraform"], + }, + { id: "project-1", name: "garden", path: "code/garden", languages: ["Python"], tools: [] }, + { id: "project-2", name: "edge", path: "deep/a/b/edge", languages: ["Python"], tools: [] }, + ]); + expect(findings.facts).toEqual([ + { id: "language:Python", label: "Python", category: "work", value: "Codes in Python" }, + { + id: "language:JavaScript", + label: "JavaScript", + category: "work", + value: "Codes in JavaScript", + }, + { + id: "language:TypeScript", + label: "TypeScript", + category: "work", + value: "Codes in TypeScript", + }, + { id: "tool:Docker", label: "Docker", category: "tools", value: "Uses Docker" }, + { + id: "tool:GitHub Actions", + label: "GitHub Actions", + category: "tools", + value: "Uses GitHub Actions", + }, + { id: "tool:Terraform", label: "Terraform", category: "tools", value: "Uses Terraform" }, + ]); }); - it("hides a scan from every account except the one that started it", async () => { - const { scanId } = await startOnboardingScan({ actor: member }, {}); - await expect(getScanStatus(scanId, owner.userId)).rejects.toThrow(/Scan not found/); - await expect(getScanStatus(scanId, member.userId)).resolves.toMatchObject({ - status: expect.any(String), - }); - await expect(getScanStatus("scan_missing", member.userId)).rejects.toThrow(/Scan not found/); + it("offers a scan folder only to the deployment owner and only when it exists", async () => { + const home = await tempDir(); + await files(home, ["file.txt"]); + await expect(onboardingScanFolder(member, home)).resolves.toBeNull(); + await expect(onboardingScanFolder(owner, undefined)).resolves.toBeNull(); + await expect(onboardingScanFolder(owner, path.join(home, "missing"))).resolves.toBeNull(); + await expect(onboardingScanFolder(owner, path.join(home, "file.txt"))).resolves.toBeNull(); + await expect(onboardingScanFolder(owner, home)).resolves.toBe(home); + await expect(startOnboardingScan(member, home)).rejects.toMatchObject({ code: "FORBIDDEN" }); }); - it("never reads the host without a configured scan home", async () => { - const { scanId } = await startOnboardingScan({ actor: owner }, {}); + it("keeps a scan with the account that started it and returns only relative paths", async () => { + const home = await tempDir(); + await project(home, "code/atlas", ["index.ts"]); + const { scanId } = await startOnboardingScan(owner, home); + const status = await completed(scanId, owner.userId); - expect(status.status).toBe("complete"); - expect(status.result).toMatchObject({ localRepos: [], fileSummary: { totalFiles: 0 } }); + expect(status).toEqual({ + status: "complete", + projects: [{ id: "project-0", name: "atlas", path: "code/atlas" }], + facts: [{ id: "language:TypeScript", label: "TypeScript" }], + }); + expect(JSON.stringify(status)).not.toContain(home); + expect(() => onboardingScanStatus(scanId, member.userId)).toThrow( + expect.objectContaining({ code: "NOT_FOUND" }), + ); + expect(() => onboardingScanStatus("missing-scan", owner.userId)).toThrow( + expect.objectContaining({ code: "NOT_FOUND" }), + ); + await expect( + applyOnboardingScan(untouchedPrisma, member, home, { + scanId, + projectIds: ["project-0"], + factIds: [], + }), + ).rejects.toMatchObject({ code: "NOT_FOUND" }); }); - it("lets only the deployment owner discover the configured scan home", async () => { - // The shared test setup pins the emulated runtime, which also keeps the scan simulated. - vi.stubEnv("AGENT_RUNTIME", ""); - vi.stubEnv("SANDBOX_PROVIDER", ""); - const scanHome = await scanHomeWithOneFile(); + it("checks ownership, the folder and every chosen project again before writing", async () => { + const home = await tempDir(); + const outside = await tempDir(); + await project(home, "code/atlas", ["index.ts"]); + await project(home, "code/garden", ["main.py"]); + await project(outside, "elsewhere", ["main.rs"]); + const { scanId } = await startOnboardingScan(owner, home); + await completed(scanId, owner.userId); + const choice = { scanId, projectIds: ["project-1"], factIds: ["language:Python"] }; - const asMember = await startOnboardingScan({ actor: member, scanHome }, {}); - const memberStatus = await completed(asMember.scanId, member.userId); - expect(memberStatus.result).toMatchObject({ fileSummary: { totalFiles: 0 } }); + await expect( + applyOnboardingScan(untouchedPrisma, { ...owner, isDeploymentOwner: false }, home, choice), + ).rejects.toMatchObject({ code: "FORBIDDEN" }); + await expect( + applyOnboardingScan(untouchedPrisma, owner, outside, choice), + ).rejects.toMatchObject({ code: "FORBIDDEN" }); - const asOwner = await startOnboardingScan({ actor: owner, scanHome }, {}); - const ownerStatus = await completed(asOwner.scanId, owner.userId); - expect(ownerStatus.status).toBe("complete"); - expect(ownerStatus.result).toMatchObject({ fileSummary: { totalFiles: 1 } }); + // The chosen project became a symlink out of the scan folder after the scan. + await rm(path.join(home, "code/garden"), { recursive: true }); + await symlink(path.join(outside, "elsewhere"), path.join(home, "code/garden")); + await expect(applyOnboardingScan(untouchedPrisma, owner, home, choice)).rejects.toMatchObject({ + code: "BAD_REQUEST", + message: "That folder does not exist or is not readable.", + }); }); }); diff --git a/apps/api/src/onboarding-scan.ts b/apps/api/src/onboarding-scan.ts index 8d1c786..504cc84 100644 --- a/apps/api/src/onboarding-scan.ts +++ b/apps/api/src/onboarding-scan.ts @@ -1,815 +1,435 @@ -// Onboarding scan — real filesystem scan, Git analysis, and profile compilation. -// Runs synchronously on the host machine (no sandbox needed). -import { spawn } from "node:child_process"; -import { access, readdir, stat } from "node:fs/promises"; -import { dirname, join } from "node:path"; -import type { Actor } from "@rakazo/contracts"; +// Onboarding discovery. With the deployment owner's consent, it lists the code projects (git +// checkouts) in the configured scan folder and the languages and tools they use. It reads +// directory listings only, never file contents, and never follows a symlink, so nothing outside +// the folder is reached. Results stay with the account that started the scan, and nothing is +// created until the owner picks projects and facts from them. +import { randomUUID } from "node:crypto"; +import type { Dirent } from "node:fs"; +import { readdir, realpath, stat } from "node:fs/promises"; +import path from "node:path"; +import { ORPCError } from "@orpc/server"; +import type { + Actor, + OnboardingScanApplyInput, + OnboardingScanApplyResult, + OnboardingScanStatus, + UserFactCategory, +} from "@rakazo/contracts"; +import { ONBOARDING_SCAN_MAX_FACTS, ONBOARDING_SCAN_MAX_PROJECTS } from "@rakazo/contracts"; +import type { PrismaClient } from "@rakazo/db"; +import { + createSpaceForMember, + InvalidProjectWorkspacePathError, + InvalidSpaceNameError, + InvalidUserFactError, + SpaceLimitError, + updateUserProfile, + wireProjectWorkspace, +} from "@rakazo/db"; -// --------------------------------------------------------------------------- -// Types -// --------------------------------------------------------------------------- +/** Project roots are looked for at most this deep below the scan folder. */ +const PROJECT_DEPTH = 4; +/** Bounds the walk of a large home folder. */ +const MAX_DIRECTORIES = 5_000; +/** Bounds the language count inside one project. */ +const MAX_FILES_PER_PROJECT = 5_000; +const MAX_FILE_DEPTH = 8; +const MAX_LANGUAGES_PER_PROJECT = 3; +const SCAN_TTL_MS = 60 * 60_000; -interface ScanResult { - localRepos: RepoInfo[]; - projectFolders: ProjectFolder[]; - fileSummary: FileSummary; - profileSummary: ProfileSummary; - agentBriefing: string; - createdProjects: CreatedProject[]; - subAgentRoles: SubAgentRole[]; -} +const SKIPPED_DIRECTORIES = new Set([ + "node_modules", + "dist", + "build", + "out", + "target", + "vendor", + "venv", + "__pycache__", + "Library", +]); -interface RepoInfo { - path: string; +const LANGUAGES = new Map( + Object.entries({ + ts: "TypeScript", + tsx: "TypeScript", + mts: "TypeScript", + cts: "TypeScript", + js: "JavaScript", + jsx: "JavaScript", + mjs: "JavaScript", + cjs: "JavaScript", + py: "Python", + go: "Go", + rs: "Rust", + java: "Java", + kt: "Kotlin", + kts: "Kotlin", + swift: "Swift", + rb: "Ruby", + php: "PHP", + c: "C", + h: "C", + cc: "C++", + cpp: "C++", + cxx: "C++", + hpp: "C++", + cs: "C#", + dart: "Dart", + ex: "Elixir", + exs: "Elixir", + scala: "Scala", + lua: "Lua", + }), +); + +const COMPOSE_FILES = new Set([ + "docker-compose.yml", + "docker-compose.yaml", + "compose.yml", + "compose.yaml", +]); + +interface FoundProject { + id: string; name: string; - remote: string | null; - branch: string; - lastCommit: string | null; - languages: Record; - sizeBytes: number; -} - -interface ProjectFolder { + /** Relative to the scan folder. */ path: string; - name: string; - type: "git" | "workspace" | "documents" | "media" | "music" | "code"; - fileCount: number; - modifiedAt: string; -} - -interface FileSummary { - totalFiles: number; - totalSizeBytes: number; - byType: Record; - byExtension: Record; -} - -interface ProfileSummary { - interests: string[]; - skills: string[]; - workStyle: string; - communication: string; languages: string[]; - techStack: string[]; + tools: string[]; } -interface CreatedProject { +interface FoundFact { id: string; - name: string; - spaceId: string; - description: string; + label: string; + category: UserFactCategory; + /** Stored as data for the user's bots, so it stays a plain English statement. */ + value: string; } -interface ScanRecord { +export interface OnboardingScanFindings { + projects: FoundProject[]; + facts: FoundFact[]; +} + +interface ScanRecord extends OnboardingScanFindings { id: string; - botId: string; ownerUserId: string; - status: "scanning" | "connecting" | "building" | "briefing" | "complete" | "failed"; - progress: number; - message: string; - result: string; - startedAt: Date; - completedAt: Date | null; + /** Real path of the scanned folder. */ + home: string; + status: "scanning" | "complete" | "failed"; + finishedAt: number | null; + applying: boolean; } -// --------------------------------------------------------------------------- -// Registry (in-memory, 1h TTL) -// --------------------------------------------------------------------------- +/** Per API process; a scan only lives as long as the onboarding that started it. */ +const scans = new Map(); -const scanRegistry = new Map(); - -const emptyScanResult = (): ScanResult => ({ - localRepos: [], - projectFolders: [], - fileSummary: { totalFiles: 0, totalSizeBytes: 0, byType: {}, byExtension: {} }, - profileSummary: { - interests: [], - skills: [], - workStyle: "structured", - communication: "direct", - languages: [], - techStack: [], - }, - agentBriefing: "Profile ready", - createdProjects: [], - subAgentRoles: [], -}); - -async function runSimulatedScan(record: ScanRecord) { - const phases: Array<{ status: ScanRecord["status"]; progress: number; message: string }> = [ - { status: "scanning", progress: 25, message: "Scanning local files and repositories..." }, - { status: "connecting", progress: 40, message: "Connecting to your services..." }, - { status: "building", progress: 60, message: "Building your profile..." }, - { status: "briefing", progress: 80, message: "Briefing your agent team..." }, - ]; - for (const phase of phases) { - record.status = phase.status; - record.progress = phase.progress; - record.message = phase.message; - await new Promise((resolve) => setTimeout(resolve, 400)); - } - record.status = "complete"; - record.progress = 100; - record.message = "Scan complete — profile ready"; - record.result = JSON.stringify(emptyScanResult()); - record.completedAt = new Date(); +/** Code-point order, so results do not depend on the server's locale. */ +function compareText(left: string, right: string): number { + return left < right ? -1 : left > right ? 1 : 0; } -export interface OnboardingScanRequest { - actor: Pick; - botId?: string; - /** Home-style directory to discover. Unset keeps the scan off the host filesystem. */ - scanHome?: string; +/** Most frequent first, then by name. */ +function byCount([leftName, left]: [string, number], [rightName, right]: [string, number]): number { + return right - left || compareText(leftName, rightName); } -export async function startOnboardingScan( - { actor, botId, scanHome }: OnboardingScanRequest, - prisma: any, -): Promise<{ scanId: string }> { - const scanId = `scan_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`; - const record: ScanRecord = { - id: scanId, - botId: botId ?? "", - ownerUserId: actor.userId, - status: "scanning", - progress: 0, - message: "Scanning your computer...", - result: "[]", - startedAt: new Date(), - completedAt: null, - }; - scanRegistry.set(scanId, record); - - // Run async - void (async () => { - try { - // The host is the deployment owner's machine: only their onboarding may discover it, and - // only inside the directory the deployment explicitly configured. - if ( - !scanHome || - !actor.isDeploymentOwner || - process.env.AGENT_RUNTIME === "scripted" || - process.env.SANDBOX_PROVIDER === "fake" - ) { - await runSimulatedScan(record); - return; - } - const result = await executeFullScan(scanHome, botId ?? "", prisma); - record.status = "complete"; - record.progress = 100; - record.message = "Scan complete — profile ready"; - record.result = JSON.stringify(result); - record.completedAt = new Date(); - } catch (error) { - record.status = "failed"; - record.message = error instanceof Error ? error.message : "Scan failed"; - record.completedAt = new Date(); - } - })(); - - return { scanId }; -} - -export async function getScanStatus( - scanId: string, - userId: string, -): Promise<{ - status: ScanRecord["status"]; - progress: number; - message: string; - result?: unknown; -}> { - const record = scanRegistry.get(scanId); - if (!record || record.ownerUserId !== userId) throw new Error("Scan not found"); - const result = record.result ? JSON.parse(record.result) : undefined; - return { status: record.status, progress: record.progress, message: record.message, result }; -} - -// --------------------------------------------------------------------------- -// Full scan pipeline -// --------------------------------------------------------------------------- - -async function executeFullScan(homeDir: string, _botId: string, prisma: any): Promise { - // Phase 1: Local file scan - const [fileSummary, projectFolders] = await scanFiles(homeDir); - - // Phase 2: Git repository discovery - const localRepos = await discoverGitRepos(homeDir); - - // Phase 3: External service analysis (GitHub, etc.) - // Phase 4: Profile compilation from findings - const profileSummary = compileProfile(localRepos, fileSummary, projectFolders); - - // Phase 6: Project folder creation - const createdProjects = await createProjectFolders(localRepos, prisma); - - // Phase 7: Sub-agent role creation - const subAgentRoles = generateSubAgentRoles(profileSummary, localRepos); - - // Phase 5: Agent briefing (includes sub-agent roles) - const agentBriefing = generateBriefing(localRepos, profileSummary, fileSummary, subAgentRoles); - - return { - localRepos, - projectFolders, - fileSummary, - profileSummary, - agentBriefing, - createdProjects, - subAgentRoles, - }; -} - -// --------------------------------------------------------------------------- -// Phase 1: File scan -// --------------------------------------------------------------------------- - -async function scanFiles(homeDir: string): Promise<[FileSummary, ProjectFolder[]]> { - const summary: FileSummary = { totalFiles: 0, totalSizeBytes: 0, byType: {}, byExtension: {} }; - const folders: ProjectFolder[] = []; - - // Scan common directories - const scanDirs = [ - "Projects", - "Documents", - "Pictures", - "Music", - "Downloads", - "Desktop", - "src", - "code", - "work", - "data", - "repos", - "dev", - "workspace", - ]; - - for (const subDir of scanDirs) { - const dirPath = join(homeDir, subDir); - try { - await access(dirPath); - const stats = await scanDirectory(dirPath, homeDir, subDir); - summary.totalFiles += stats.totalFiles; - summary.totalSizeBytes += stats.totalSizeBytes; - Object.assign(summary.byType, stats.byType); - Object.assign(summary.byExtension, stats.byExtension); - - if (stats.totalFiles > 0) { - folders.push({ - path: dirPath, - name: subDir, - type: classifyFolderType(subDir), - fileCount: stats.totalFiles, - modifiedAt: new Date().toISOString(), - }); - } - } catch { - /* directory doesn't exist, skip */ - } - } - - return [summary, folders]; -} - -interface DirStats { - totalFiles: number; - totalSizeBytes: number; - byType: Record; - byExtension: Record; -} - -async function scanDirectory( - dirPath: string, - _homeDir: string, - _relativePath: string, -): Promise { - const stats: DirStats = { totalFiles: 0, totalSizeBytes: 0, byType: {}, byExtension: {} }; - +async function listDirectory(directory: string): Promise { try { - const entries = await readdir(dirPath, { withFileTypes: true }); + return (await readdir(directory, { withFileTypes: true })).sort((left, right) => + compareText(left.name, right.name), + ); + } catch { + return []; + } +} +/** isDirectory() is false for a symlink, so links (and anything they point to) are never walked. */ +function walkable(entry: Dirent): boolean { + return entry.isDirectory() && !entry.name.startsWith(".") && !SKIPPED_DIRECTORIES.has(entry.name); +} + +async function findProjectRoots(home: string): Promise { + const roots: string[] = []; + let visited = 0; + let level = [home]; + // Breadth first, so shallow projects win when a limit is reached. The scan folder itself is + // never a project: a home folder tracked by git still holds the projects below it. + for (let depth = 0; depth <= PROJECT_DEPTH && level.length > 0; depth += 1) { + const next: string[] = []; + for (const directory of level) { + if (roots.length >= ONBOARDING_SCAN_MAX_PROJECTS || visited >= MAX_DIRECTORIES) return roots; + visited += 1; + const entries = await listDirectory(directory); + if (depth > 0 && entries.some((entry) => entry.name === ".git")) { + roots.push(directory); + continue; + } + for (const entry of entries) { + if (walkable(entry)) next.push(path.join(directory, entry.name)); + } + } + level = next; + } + return roots; +} + +async function analyzeProject(root: string): Promise<{ languages: string[]; tools: string[] }> { + const counts = new Map(); + const tools = new Set(); + let files = 0; + const rootEntries = await listDirectory(root); + if (rootEntries.some((entry) => entry.name === ".github" && entry.isDirectory())) { + const github = await listDirectory(path.join(root, ".github")); + if (github.some((entry) => entry.name === "workflows" && entry.isDirectory())) { + tools.add("GitHub Actions"); + } + } + const visit = async (directory: string, depth: number, entries: Dirent[]): Promise => { for (const entry of entries) { - const fullPath = join(dirPath, entry.name); - - if (entry.isDirectory()) { - // Skip node_modules, .git, etc. - if (entry.name === "node_modules" || entry.name === ".git" || entry.name === ".venv") - continue; - const subStats = await scanDirectory(fullPath, _homeDir, _relativePath); - stats.totalFiles += subStats.totalFiles; - stats.totalSizeBytes += subStats.totalSizeBytes; - Object.assign(stats.byType, subStats.byType); - Object.assign(stats.byExtension, subStats.byExtension); - } else if (entry.isFile()) { - try { - const fileStat = await stat(fullPath); - stats.totalFiles++; - stats.totalSizeBytes += fileStat.size; - - // Classify by type - const type = classifyFileType(entry.name); - stats.byType[type] = (stats.byType[type] || 0) + 1; - - // Classify by extension - const ext = entry.name.split(".").pop()?.toLowerCase() || "none"; - stats.byExtension[ext] = (stats.byExtension[ext] || 0) + 1; - } catch { - /* permission denied */ + if (files >= MAX_FILES_PER_PROJECT) return; + if (entry.isFile()) { + files += 1; + const name = entry.name.toLowerCase(); + const extension = name.includes(".") ? name.slice(name.lastIndexOf(".") + 1) : ""; + const language = LANGUAGES.get(extension); + if (language) counts.set(language, (counts.get(language) ?? 0) + 1); + if (name === "dockerfile" || name.startsWith("dockerfile.") || COMPOSE_FILES.has(name)) { + tools.add("Docker"); } + if (extension === "tf") tools.add("Terraform"); + } else if (depth < MAX_FILE_DEPTH && walkable(entry)) { + const child = path.join(directory, entry.name); + await visit(child, depth + 1, await listDirectory(child)); } } - } catch { - /* permission denied */ - } - - return stats; + }; + await visit(root, 0, rootEntries); + const total = [...counts.values()].reduce((sum, count) => sum + count, 0); + const languages = [...counts.entries()] + .filter(([, count]) => count >= total * 0.1) + .sort(byCount) + .slice(0, MAX_LANGUAGES_PER_PROJECT) + .map(([language]) => language); + return { languages, tools: [...tools].sort() }; } -function classifyFileType(filename: string): string { - const ext = filename.split(".").pop()?.toLowerCase() || ""; - const codeExts = [ - "ts", - "tsx", - "js", - "jsx", - "py", - "go", - "rs", - "java", - "c", - "cpp", - "h", - "rb", - "php", - "swift", - "kt", - ]; - const docExts = ["md", "txt", "doc", "docx", "pdf", "rst", "tex"]; - const imageExts = ["png", "jpg", "jpeg", "gif", "svg", "ico", "webp", "bmp"]; - const musicExts = ["mp3", "wav", "flac", "aac", "ogg", "m4a", "wma"]; - - if (codeExts.includes(ext)) return "code"; - if (docExts.includes(ext)) return "documents"; - if (imageExts.includes(ext)) return "images"; - if (musicExts.includes(ext)) return "music"; - if (["json", "yaml", "yml", "toml", "cfg", "ini", "env", "sh", "bash", "zsh"].includes(ext)) - return "config"; - return "other"; +/** Labels used by the most projects first, then by name. */ +function rankLabels(lists: string[][]): string[] { + const counts = new Map(); + for (const list of lists) + for (const label of list) counts.set(label, (counts.get(label) ?? 0) + 1); + return [...counts.entries()].sort(byCount).map(([label]) => label); } -function classifyFolderType(name: string): ProjectFolder["type"] { - const lower = name.toLowerCase(); - if (lower.includes("music")) return "music"; - if (lower.includes("picture") || lower.includes("image") || lower.includes("photo")) - return "media"; - if (lower.includes("document") || lower.includes("doc")) return "documents"; - if ( - lower.includes("project") || - lower.includes("code") || - lower.includes("src") || - lower.includes("dev") || - lower.includes("workspace") || - lower.includes("repo") - ) - return "code"; - return "workspace"; +/** Lists the projects below a real (symlink-free) folder path, and what they use. */ +export async function discoverOnboardingScan(home: string): Promise { + const roots = await findProjectRoots(home); + const analyzed = await Promise.all( + roots.map(async (root) => ({ root, ...(await analyzeProject(root)) })), + ); + const projects = analyzed + .map(({ root, languages, tools }) => ({ + name: path.basename(root), + path: path.relative(home, root), + languages, + tools, + })) + .sort((left, right) => compareText(left.path, right.path)) + .map((project, index) => ({ id: `project-${index}`, ...project })); + const facts: FoundFact[] = [ + ...rankLabels(projects.map((project) => project.languages)).map((label) => ({ + id: `language:${label}`, + label, + category: "work" as const, + value: `Codes in ${label}`, + })), + ...rankLabels(projects.map((project) => project.tools)).map((label) => ({ + id: `tool:${label}`, + label, + category: "tools" as const, + value: `Uses ${label}`, + })), + ].slice(0, ONBOARDING_SCAN_MAX_FACTS); + return { projects, facts }; } -// --------------------------------------------------------------------------- -// Phase 2: Git repository discovery -// --------------------------------------------------------------------------- - -async function discoverGitRepos(homeDir: string): Promise { - const repos: RepoInfo[] = []; - +/** + * The scan reads the server's filesystem, so only the deployment owner may scan, and only the + * folder the deployment configured. Null hides the step. + */ +export async function onboardingScanFolder( + actor: Pick, + scanHome: string | undefined, +): Promise { + if (!actor.isDeploymentOwner || !scanHome) return null; try { - const gitDirs = await findGitDirectories(homeDir); - - for (const repoDir of gitDirs) { - try { - const repo = await analyzeGitRepo(repoDir, homeDir); - if (repo) repos.push(repo); - } catch { - /* skip broken repos */ - } - } - } catch { - /* git not available */ - } - - return repos; -} - -async function findGitDirectories(dir: string, depth: number = 0): Promise { - if (depth > 4) return []; // Limit search depth - const results: string[] = []; - - try { - const entries = await readdir(dir, { withFileTypes: true }); - for (const entry of entries) { - const fullPath = join(dir, entry.name); - if (entry.isDirectory()) { - if (entry.name === ".git") { - results.push(dirname(fullPath)); - } else if ( - entry.name !== "node_modules" && - entry.name !== ".git" && - entry.name !== ".venv" && - entry.name !== "dist" - ) { - results.push(...(await findGitDirectories(fullPath, depth + 1))); - } - } - } - } catch { - /* permission denied */ - } - - return results; -} - -async function analyzeGitRepo(repoDir: string, _homeDir: string): Promise { - try { - const name = repoDir.split("/").pop() || ""; - - // Get remote URL - const remoteResult = await spawnPromise("git", ["remote", "get-url", "origin"], { - cwd: repoDir, - }).catch(() => ({ stdout: "" })); - const remote = remoteResult.stdout.trim() || null; - - // Get current branch - const branchResult = await spawnPromise("git", ["branch", "--show-current"], { - cwd: repoDir, - }).catch(() => ({ stdout: "" })); - const branch = branchResult.stdout.trim() || "unknown"; - - // Get last commit - const commitResult = await spawnPromise("git", ["log", "-1", "--format=%H"], { - cwd: repoDir, - }).catch(() => ({ stdout: "" })); - const lastCommit = commitResult.stdout.trim() || null; - - // Get language stats via git ls-files + wc - const languages = await getRepoLanguages(repoDir); - - // Get directory size - const sizeResult = await spawnPromise("du", ["-sb", repoDir]).catch(() => ({ stdout: "0" })); - const sizeBytes = parseInt(sizeResult.stdout.split("\t")[0] || "0", 10); - - return { path: repoDir, name, remote, branch, lastCommit, languages, sizeBytes }; + const home = await realpath(scanHome); + return (await stat(home)).isDirectory() ? home : null; } catch { return null; } } -async function getRepoLanguages(repoDir: string): Promise> { - const langs: Record = {}; - try { - const { stdout } = await spawnPromise("git", ["ls-files"], { cwd: repoDir }).catch(() => ({ - stdout: "", - })); - const files = stdout.trim().split("\n").filter(Boolean); - for (const file of files) { - const ext = file.split(".").pop()?.toLowerCase() || ""; - const langMap: Record = { - ts: "TypeScript", - tsx: "TypeScript", - js: "JavaScript", - jsx: "JavaScript", - py: "Python", - go: "Go", - rs: "Rust", - java: "Java", - c: "C", - cpp: "C++", - rb: "Ruby", - php: "PHP", - swift: "Swift", - kt: "Kotlin", - }; - const lang = langMap[ext] || ext || "unknown"; - langs[lang] = (langs[lang] || 0) + 1; - } - } catch { - /* no languages */ +function forgetExpiredScans(now: number): void { + for (const [id, scan] of scans) { + if (scan.finishedAt !== null && now - scan.finishedAt > SCAN_TTL_MS) scans.delete(id); } - return langs; } -// --------------------------------------------------------------------------- -// Phase 3: Profile compilation -// --------------------------------------------------------------------------- - -function compileProfile( - repos: RepoInfo[], - fileSummary: FileSummary, - _folders: ProjectFolder[], -): ProfileSummary { - const interests: string[] = []; - const skills: string[] = []; - const techStack: string[] = []; - const languageSet = new Set(); - - // Extract tech stack from repos - for (const repo of repos) { - for (const lang of Object.keys(repo.languages)) { - techStack.push(lang); - languageSet.add(lang); - } - } - - // Extract interests from file types - for (const [type, count] of Object.entries(fileSummary.byType)) { - if (count > 5) { - interests.push(`${type} (${count} files)`); - } - } - - // Derive skills from languages - const langToSkill: Record = { - TypeScript: "TypeScript/JavaScript", - Python: "Python", - Go: "Go", - Rust: "Rust", - Java: "Java", - C: "C/C++", - "C++": "C/C++", - Ruby: "Ruby", - Swift: "Swift/Kotlin", - PHP: "PHP", +export async function startOnboardingScan( + actor: Pick, + scanHome: string | undefined, +): Promise<{ scanId: string }> { + const home = await onboardingScanFolder(actor, scanHome); + if (!home) throw new ORPCError("FORBIDDEN"); + forgetExpiredScans(Date.now()); + const running = [...scans.values()].find( + (scan) => scan.ownerUserId === actor.userId && scan.status === "scanning", + ); + if (running) return { scanId: running.id }; + const scan: ScanRecord = { + id: randomUUID(), + ownerUserId: actor.userId, + home, + status: "scanning", + projects: [], + facts: [], + finishedAt: null, + applying: false, }; - for (const lang of techStack) { - const skill = langToSkill[lang]; - if (skill && !skills.includes(skill)) skills.push(skill); - } + scans.set(scan.id, scan); + void discoverOnboardingScan(home) + .then((findings) => { + scan.projects = findings.projects; + scan.facts = findings.facts; + scan.status = "complete"; + }) + .catch(() => { + scan.status = "failed"; + }) + .finally(() => { + scan.finishedAt = Date.now(); + }); + return { scanId: scan.id }; +} - // Deduplicate - const uniqueInterests = [...new Set(interests)].slice(0, 10); - const uniqueSkills = [...new Set(skills)].slice(0, 15); - const uniqueTech = [...new Set(techStack)].sort(); +/** Another account's scan reads as missing. */ +function ownedScan(scanId: string, userId: string): ScanRecord { + const scan = scans.get(scanId); + if (!scan || scan.ownerUserId !== userId) throw new ORPCError("NOT_FOUND"); + return scan; +} +export function onboardingScanStatus(scanId: string, userId: string): OnboardingScanStatus { + const scan = ownedScan(scanId, userId); + if (scan.status !== "complete") return { status: scan.status }; return { - interests: uniqueInterests, - skills: uniqueSkills, - workStyle: - uniqueTech.length > 3 - ? "multi-language" - : uniqueTech[0] - ? `${uniqueTech[0]}-focused` - : "general", - communication: "structured", - languages: Array.from(languageSet), - techStack: uniqueTech, + status: "complete", + projects: scan.projects.map(({ id, name, path }) => ({ id, name, path })), + facts: scan.facts.map(({ id, label }) => ({ id, label })), }; } -// --------------------------------------------------------------------------- -// Phase 4: Agent briefing -// --------------------------------------------------------------------------- +const MISSING_FOLDER = "That folder does not exist or is not readable."; -function generateBriefing( - repos: RepoInfo[], - profile: ProfileSummary, - fileSummary: FileSummary, - subAgentRoles: SubAgentRole[], -): string { - const lines: string[] = []; - lines.push(`# User Profile Briefing`); - lines.push(``); - lines.push(`## Technical Profile`); - lines.push(`- **Tech Stack:** ${profile.techStack.join(", ") || "N/A"}`); - lines.push(`- **Languages:** ${profile.languages.join(", ") || "N/A"}`); - lines.push(`- **Work Style:** ${profile.workStyle}`); - lines.push(``); - lines.push(`## Local Repositories (${repos.length} found)`); - for (const repo of repos) { - lines.push( - `- **${repo.name}** — ${repo.branch}, ${Object.values(repo.languages).reduce((a, b) => a + b, 0)} files, ${repo.remote || "no remote"}`, - ); +/** Resolves a found project again, so a folder swapped for a symlink cannot leave the scan folder. */ +async function confinedProjectFolder(home: string, relative: string): Promise { + let folder: string; + try { + folder = await realpath(path.join(home, relative)); + } catch { + throw new InvalidProjectWorkspacePathError(MISSING_FOLDER); } - lines.push(``); - lines.push(`## File System Summary`); - lines.push(`- **Total Files:** ${fileSummary.totalFiles.toLocaleString()}`); - lines.push(`- **Total Size:** ${(fileSummary.totalSizeBytes / (1024 * 1024)).toFixed(0)} MB`); - lines.push( - `- **Categories:** ${Object.entries(fileSummary.byType) - .map(([t, c]) => `${t}(${c})`) - .join(", ")}`, - ); - lines.push(``); - lines.push(`## User Interests`); - lines.push(`- ${profile.interests.slice(0, 5).join("\n- ")}`); - lines.push(``); - lines.push(`## User Skills`); - lines.push(`- ${profile.skills.slice(0, 5).join("\n- ")}`); - lines.push(``); - lines.push(`## Assigned Specialist Roles`); - for (const role of subAgentRoles) { - lines.push(`### ${role.name}`); - lines.push(`- **Role:** ${role.role}`); - lines.push(`- **Description:** ${role.description}`); - lines.push(`- **Instructions:** ${role.instructions}`); - lines.push(`- **Skills:** ${role.skills.join(", ")}`); - lines.push(""); + const inside = path.relative(home, folder); + if (!inside || inside === ".." || inside.startsWith(`..${path.sep}`) || path.isAbsolute(inside)) { + throw new InvalidProjectWorkspacePathError(MISSING_FOLDER); } - lines.push(`---`); - lines.push( - `This profile should be used to tailor all future interactions, project recommendations, and agent assignments.`, - ); - return lines.join("\n"); + return folder; } -// --------------------------------------------------------------------------- -// Phase 5: Project folder creation -// --------------------------------------------------------------------------- +async function projectSpace( + prisma: PrismaClient, + actor: Pick, + name: string, + folder: string, +): Promise<{ id: string; name: string }> { + // Applying twice, or onboarding again, reuses the user's own space linked to this folder. + const existing = await prisma.space.findFirst({ + where: { + workspacePath: folder, + deletingAt: null, + memberships: { some: { userId: actor.userId } }, + }, + select: { id: true, name: true }, + orderBy: { createdAt: "asc" }, + }); + if (existing) return existing; + const space = await createSpaceForMember(prisma, { + currentSpaceId: actor.spaceId, + userId: actor.userId, + name: name.slice(0, 60), + }); + await wireProjectWorkspace(prisma, { spaceId: space.id, workspacePath: folder }); + return space; +} -async function createProjectFolders(repos: RepoInfo[], prisma: any): Promise { - const created: CreatedProject[] = []; +function toRpcError(error: unknown): unknown { + if ( + error instanceof SpaceLimitError || + error instanceof InvalidSpaceNameError || + error instanceof InvalidProjectWorkspacePathError || + error instanceof InvalidUserFactError + ) { + return new ORPCError("BAD_REQUEST", { message: error.message }); + } + return error; +} - for (const repo of repos) { - try { - // Check if space already exists - const existing = await prisma.space.findFirst({ where: { title: repo.name } }); - if (existing) { - created.push({ - id: existing.id, - name: repo.name, - spaceId: existing.id, - description: repo.remote || repo.path, - }); - continue; - } - // Create new space - const space = await prisma.space.create({ - data: { title: repo.name, path: repo.path }, - }); - created.push({ - id: space.id, - name: repo.name, - spaceId: space.id, - description: repo.remote || repo.path, - }); - } catch { - // Space might already exist or DB unavailable — skip +/** Creates a project space per chosen project and saves the chosen facts to the profile. */ +export async function applyOnboardingScan( + prisma: PrismaClient, + actor: Pick, + scanHome: string | undefined, + input: OnboardingScanApplyInput, +): Promise { + const scan = ownedScan(input.scanId, actor.userId); + if (scan.status !== "complete" || scan.applying) throw new ORPCError("CONFLICT"); + scan.applying = true; + try { + // Ownership or the configured folder can change after the scan; check again before writing. + if ((await onboardingScanFolder(actor, scanHome)) !== scan.home) { + throw new ORPCError("FORBIDDEN"); } + const projectIds = new Set(input.projectIds); + const factIds = new Set(input.factIds); + const projects = scan.projects.filter((project) => projectIds.has(project.id)); + const facts = scan.facts.filter((fact) => factIds.has(fact.id)); + // Every chosen folder is checked before anything is written. + const chosen = await Promise.all( + projects.map(async (project) => ({ + name: project.name, + folder: await confinedProjectFolder(scan.home, project.path), + })), + ); + const added = + facts.length > 0 + ? await updateUserProfile(prisma, actor.userId, { + addFacts: facts.map(({ category, value }) => ({ + category, + value, + source: "onboarding" as const, + })), + }) + : []; + const spaces: Array<{ id: string; name: string }> = []; + for (const { name, folder } of chosen) + spaces.push(await projectSpace(prisma, actor, name, folder)); + return { spaces, factsAdded: added.filter((fact) => fact.created).length }; + } catch (error) { + throw toRpcError(error); + } finally { + scan.applying = false; } - - return created; } - -// --------------------------------------------------------------------------- -// Phase 6: Sub-agent role creation -// --------------------------------------------------------------------------- - -interface SubAgentRole { - name: string; - role: string; - description: string; - instructions: string; - skills: string[]; -} - -function generateSubAgentRoles(profile: ProfileSummary, repos: RepoInfo[]): SubAgentRole[] { - const roles: SubAgentRole[] = []; - const hasCode = profile.languages?.length > 0; - const hasDesign = profile.interests?.some( - (i) => i.toLowerCase().includes("design") || i.toLowerCase().includes("ui"), - ); - const hasData = profile.interests?.some( - (i) => - i.toLowerCase().includes("data") || - i.toLowerCase().includes("analytics") || - i.toLowerCase().includes("database"), - ); - const hasDevOps = profile.interests?.some( - (i) => - i.toLowerCase().includes("infra") || - i.toLowerCase().includes("ops") || - i.toLowerCase().includes("deploy"), - ); - const hasMusic = profile.interests?.some((i) => i.toLowerCase().includes("music")); - const hasWriting = profile.interests?.some( - (i) => i.toLowerCase().includes("write") || i.toLowerCase().includes("blog"), - ); - - if (hasCode) { - const primaryLang = profile.languages?.[0] || "TypeScript"; - roles.push({ - name: "Code Engineer", - role: "software-engineer", - description: `Specializes in ${primaryLang} development and code review`, - instructions: `You are the Code Engineer specialist. Your expertise is in ${profile.languages?.join(", ") || "software development"}. Review code, write tests, debug issues, and implement features. You have access to the user's local repositories and can run commands to build and test code.`, - skills: profile.skills.filter( - (s) => s.toLowerCase().includes("code") || s.toLowerCase().includes("program"), - ), - }); - } - - if (hasDesign) { - roles.push({ - name: "UI/UX Designer", - role: "ui-designer", - description: "Creates polished interfaces and design systems", - instructions: - "You are the UI/UX Designer specialist. Focus on creating beautiful, accessible interfaces. Review designs, suggest improvements, and ensure consistency across the user's projects.", - skills: ["design", "UI/UX"], - }); - } - - if (hasData) { - roles.push({ - name: "Data Analyst", - role: "data-analyst", - description: "Analyzes data, creates reports, and extracts insights", - instructions: - "You are the Data Analyst specialist. Process data from the user's projects, create visualizations, generate reports, and provide actionable insights.", - skills: ["data analysis", "statistics"], - }); - } - - if (hasDevOps) { - roles.push({ - name: "DevOps Engineer", - role: "devops-engineer", - description: "Manages infrastructure, deployments, and CI/CD", - instructions: - "You are the DevOps Engineer specialist. Handle deployments, manage infrastructure, configure CI/CD pipelines, and ensure system reliability.", - skills: ["DevOps", "infrastructure"], - }); - } - - if (hasMusic) { - roles.push({ - name: "Music Producer", - role: "music-producer", - description: "Assists with music production and audio engineering", - instructions: - "You are the Music Producer specialist. Help with music composition, audio engineering, mixing, and mastering. You understand the user's music projects and can provide expert advice.", - skills: ["music production", "audio engineering"], - }); - } - - if (hasWriting) { - roles.push({ - name: "Content Writer", - role: "content-writer", - description: "Creates and edits written content", - instructions: - "You are the Content Writer specialist. Write blog posts, documentation, articles, and other content for the user's projects and personal use.", - skills: ["writing", "content creation"], - }); - } - - // Always include a general assistant - roles.unshift({ - name: "General Assistant", - role: "general-assistant", - description: "Handles general tasks and coordinates other specialists", - instructions: `You are the General Assistant and team coordinator. Your role is to handle general queries, coordinate with other specialists (${ - roles - .slice(1) - .map((r) => r.name) - .join(", ") || "none yet" - }), and manage the user's daily workflow. You have access to all tools and can delegate tasks to specialists when needed.`, - skills: ["task management", "coordination"], - }); - - return roles; -} - -// --------------------------------------------------------------------------- -// Utility -// --------------------------------------------------------------------------- - -function spawnPromise( - cmd: string, - args: string[], - options?: { cwd?: string }, -): Promise<{ stdout: string; stderr: string }> { - return new Promise((resolve, reject) => { - const child = spawn(cmd, args, { ...options, timeout: 15000 }); - let stdout = ""; - let stderr = ""; - child.stdout?.on("data", (d: Buffer) => { - stdout += d.toString(); - }); - child.stderr?.on("data", (d: Buffer) => { - stderr += d.toString(); - }); - child.on("error", () => reject(new Error("spawn failed"))); - child.on("close", (code) => { - if (code === 0 || code === null) resolve({ stdout, stderr }); - else reject(new Error(`exit ${code}`)); - }); - }); -} - -// Keep old registry cleanup -setInterval(() => { - const cutoff = Date.now() - 3600000; - for (const [id, r] of scanRegistry) { - if (r.completedAt && r.completedAt.getTime() < cutoff) scanRegistry.delete(id); - } -}, 60000); diff --git a/apps/api/src/router.ts b/apps/api/src/router.ts index 2baf21e..2af5c9a 100644 --- a/apps/api/src/router.ts +++ b/apps/api/src/router.ts @@ -157,6 +157,7 @@ import { resolveBusyBotName, toComputerStatus, } from "./computer-status.js"; +import { recordConnectedApp } from "./connected-app-facts.js"; import { listInbox } from "./inbox.js"; import { searchIntegrationCatalog } from "./integration-catalog.js"; import { @@ -180,7 +181,12 @@ import { promptFocus, startOnboarding, } from "./onboarding.js"; -import { getScanStatus, startOnboardingScan } from "./onboarding-scan.js"; +import { + applyOnboardingScan, + onboardingScanFolder, + onboardingScanStatus, + startOnboardingScan, +} from "./onboarding-scan.js"; import { listSpaceRuns } from "./runs.js"; import { addScreenProxyCapability } from "./screen-proxy.js"; import { querySpaceSearch } from "./search.js"; @@ -285,6 +291,11 @@ async function reconcilePendingConnections( : []), ]; if (updates.length > 0) await prisma.$transaction(updates); + const connected = new Set(sync.connectIds); + for (const row of rows) { + if (row.status !== "pending" || !connected.has(row.id)) continue; + await recordConnectedApp(prisma, { userId: owner.userId, connectorId, provider: row.provider }); + } } /** Serialize begin/revoke for one user+provider so slug-wide remote deletes cannot race a new connect. */ @@ -3434,16 +3445,18 @@ export function createRouter(deps: RouterDeps) { ); return { ok: true as const }; }), - scan: authed.onboarding.scan.handler(async ({ context, input }) => { - const { scanId } = await startOnboardingScan( - { actor: context.actor, botId: input.botId, scanHome: deps.env.onboardingScanHome }, - deps.prisma, - ); - return { scanId }; - }), - scanStatus: authed.onboarding.scanStatus.handler(async ({ context, input }) => { - return await getScanStatus(input.scanId, context.actor.userId); - }), + scanTarget: authed.onboarding.scanTarget.handler(async ({ context }) => ({ + folder: await onboardingScanFolder(context.actor, deps.env.onboardingScanHome), + })), + scan: authed.onboarding.scan.handler(({ context }) => + startOnboardingScan(context.actor, deps.env.onboardingScanHome), + ), + scanStatus: authed.onboarding.scanStatus.handler(async ({ context, input }) => + onboardingScanStatus(input.scanId, context.actor.userId), + ), + applyScan: authed.onboarding.applyScan.handler(({ context, input }) => + applyOnboardingScan(deps.prisma, context.actor, deps.env.onboardingScanHome, input), + ), }, integrationSetup: { get: authed.integrationSetup.get.handler(async ({ context }) => { @@ -3692,6 +3705,13 @@ export function createRouter(deps: RouterDeps) { } throw new IsolationError(); } + if (!auth.authorizationUrl) { + await recordConnectedApp(deps.prisma, { + userId: context.actor.userId, + connectorId: input.connectorId, + provider: input.provider, + }); + } return { connectionId: row.id, authorizationUrl: auth.authorizationUrl }; } catch (error) { if (error instanceof IsolationError) throw error; @@ -3997,6 +4017,13 @@ export function createRouter(deps: RouterDeps) { }, { timeout: 60_000 }, ); + if (row.status === "connected") { + await recordConnectedApp(deps.prisma, { + userId: context.actor.userId, + connectorId: row.connectorId, + provider: row.provider, + }); + } } return { id: row.id, diff --git a/apps/web/e2e/onboarding-discovery.spec.ts b/apps/web/e2e/onboarding-discovery.spec.ts new file mode 100644 index 0000000..0f639bc --- /dev/null +++ b/apps/web/e2e/onboarding-discovery.spec.ts @@ -0,0 +1,76 @@ +/** + * E2E: the deployment owner's onboarding asks before scanning the fixture home folder the + * harness configures, then adds only the projects and facts the user picks. + */ +import { expect, type Page, test } from "@playwright/test"; +import type { SpaceNavigation, UserProfileState } from "@rakazo/contracts"; +import { captureScreenshot, rpc, signup } from "./helpers"; + +const api = process.env.API_URL ?? "http://127.0.0.1:3110"; + +/** Advances whichever wizard step is showing until the scan step is reached. */ +async function walkToScanStep(page: Page) { + const surface = page.locator('[data-rakazo-surface="onboarding"]'); + await expect(async () => { + if ((await surface.getAttribute("data-onboarding-step")) === "scan") return; + const skip = page.getByRole("button", { name: /^Skip/ }).first(); + const next = (await skip.isVisible()) + ? skip + : page.getByRole("button", { name: "Continue", exact: true }); + await next.click({ timeout: 2_000 }); + await expect(surface).toHaveAttribute("data-onboarding-step", "scan", { timeout: 1_000 }); + }).toPass({ timeout: 60_000 }); +} + +test("asks before looking for projects and adds only what the user picks", async ({ + page, +}, testInfo) => { + const email = `discovery-${Date.now()}@rakazo.test`; + await signup(page, email, "password12", "Discovery"); + await page.waitForURL(/\/onboarding/, { timeout: 20_000 }); + // The harness starts without a deployment owner; this spec takes the seat for its run. + const owner = await page.request.post(`${api}/__e2e/deployment-owner`, { data: { email } }); + expect(owner.ok()).toBe(true); + const { previousOwnerUserId } = (await owner.json()) as { previousOwnerUserId: string | null }; + try { + await page.goto("/onboarding", { waitUntil: "domcontentloaded" }); + await walkToScanStep(page); + + await expect(page.getByRole("heading", { name: "Look for projects here?" })).toBeVisible(); + await expect(page.getByText(/rakazo-e2e-scan-home-/)).toBeVisible(); + await captureScreenshot(page, testInfo, "onboarding-discovery-consent"); + await page.getByRole("button", { name: "Look", exact: true }).click(); + + const projects = page.getByRole("group", { name: "Add as projects" }); + await expect(projects.getByRole("checkbox")).toHaveCount(2); + const atlas = projects.getByRole("checkbox", { name: /atlas/ }); + await expect(atlas).not.toBeChecked(); + await expect(projects.getByRole("checkbox", { name: /garden/ })).not.toBeChecked(); + await atlas.check(); + const facts = page.getByRole("group", { name: "Add to About you" }); + await expect(facts.getByRole("checkbox", { name: "TypeScript" })).toBeChecked(); + await facts.getByRole("checkbox", { name: "Python" }).uncheck(); + await captureScreenshot(page, testInfo, "onboarding-discovery-results"); + await page.getByRole("button", { name: "Add", exact: true }).click(); + await page.waitForURL(/\/app\/g\/[^/]+$/, { timeout: 30_000 }); + + const navigation = await rpc(page, "spaces/list", {}); + const names = navigation.spaces.map((space) => space.name); + expect(names).toContain("atlas"); + expect(names).not.toContain("garden"); + expect(navigation.spaces.find((space) => space.name === "atlas")?.workspace?.path).toMatch( + /code\/atlas$/, + ); + const values = (await rpc(page, "profile/get", {})).facts.map( + (fact) => fact.value, + ); + expect(values).toEqual( + expect.arrayContaining(["Codes in TypeScript", "Uses Docker", "Uses GitHub Actions"]), + ); + expect(values).not.toContain("Codes in Python"); + } finally { + await page.request.post(`${api}/__e2e/deployment-owner`, { + data: { userId: previousOwnerUserId }, + }); + } +}); diff --git a/apps/web/src/components/onboarding/OnboardingScanProgress.tsx b/apps/web/src/components/onboarding/OnboardingScanProgress.tsx deleted file mode 100644 index 16c41b4..0000000 --- a/apps/web/src/components/onboarding/OnboardingScanProgress.tsx +++ /dev/null @@ -1,186 +0,0 @@ -import { useEffect, useState } from "react"; -import { rpc } from "../../lib/rpc"; - -interface ScanStatus { - status: "scanning" | "connecting" | "building" | "briefing" | "complete" | "failed"; - progress: number; - message: string; - result?: unknown; -} - -const PHASES = [ - { - key: "scanning" as const, - label: "Scanning your computer...", - sublabel: "Files, folders, git repositories", - }, - { - key: "connecting" as const, - label: "Connecting to your services...", - sublabel: "GitHub, email, calendar", - }, - { - key: "building" as const, - label: "Building your profile...", - sublabel: "Interests, skills, preferences", - }, - { - key: "briefing" as const, - label: "Setting up your agent team...", - sublabel: "Project folders, role assignments", - }, -] as const; - -export function OnboardingScanProgress({ - onComplete, - botId, -}: { - onComplete: () => void; - botId?: string; -}) { - const [status, setStatus] = useState(null); - const [error, setError] = useState(null); - const [, setScanId] = useState(null); - - useEffect(() => { - let cancelled = false; - let pollingInterval: ReturnType | null = null; - - const run = async () => { - try { - const scanResult = await rpc.onboarding.scan(botId ? { botId } : {}); - if (cancelled) return; - setScanId(scanResult.scanId); - - // Poll for status - const poll = async () => { - try { - const s = await rpc.onboarding.scanStatus({ scanId: scanResult.scanId }); - if (cancelled) return; - setStatus(s); - if (s.status === "complete") { - onComplete(); - } else if (s.status === "failed") { - setError(s.message); - } - } catch { - // poll error — keep trying - } - }; - - // First poll immediately, then every 2s - await poll(); - pollingInterval = setInterval(poll, 2000); - } catch (err) { - if (!cancelled) setError(err instanceof Error ? err.message : "Scan failed"); - } - }; - - run(); - return () => { - cancelled = true; - if (pollingInterval) clearInterval(pollingInterval); - }; - }, [botId, onComplete]); - - if (error) { - return ( -
-

{error}

- -
- ); - } - - if (!status) { - return ( -
-
-

Preparing your profile...

-
- ); - } - - const currentPhaseIndex = PHASES.findIndex((p) => p.key === status.status); - const isComplete = status.status === "complete"; - - return ( -
-

- {isComplete ? "All set!" : "Getting to know you..."} -

-

- {isComplete - ? "Your profile and agent team are ready." - : "We're scanning your computer and services to personalize your experience."} -

- -
- {PHASES.map((phase, idx) => { - const isActive = idx === currentPhaseIndex && !isComplete; - const isDone = idx < currentPhaseIndex || isComplete; - return ( -
-
- {isDone ? ( - - ✓ - - ) : isActive ? ( - - ● - - ) : ( - - ○ - - )} -
-
-

- {phase.label} -

-

{phase.sublabel}

-
- {isActive && ( -
-
-
-
-
- )} -
- ); - })} -
- - {isComplete && ( -
- -
- )} -
- ); -} diff --git a/apps/web/src/components/onboarding/OnboardingScanStep.tsx b/apps/web/src/components/onboarding/OnboardingScanStep.tsx new file mode 100644 index 0000000..1b700c8 --- /dev/null +++ b/apps/web/src/components/onboarding/OnboardingScanStep.tsx @@ -0,0 +1,250 @@ +import { Trans, useLingui } from "@lingui/react/macro"; +import type { OnboardingScanFact, OnboardingScanProject } from "@rakazo/contracts"; +import { Button, Checkbox } from "@rakazo/ui-web"; +import { useEffect, useId, useRef, useState } from "react"; +import { rpc } from "../../lib/rpc"; +import { LoadingState } from "../ai/primitives"; + +const POLL_MS = 1_000; + +interface Found { + projects: OnboardingScanProject[]; + facts: OnboardingScanFact[]; +} + +function toggled(ids: string[], id: string, on: boolean): string[] { + return on ? [...ids, id] : ids.filter((entry) => entry !== id); +} + +/** + * Asks before looking at the server's scan folder, then lets the user choose which found projects + * become project spaces and which languages and tools go to About you. Nothing is created without + * a choice. Skips itself when this account cannot scan. + */ +export function OnboardingScanStep({ onDone }: { onDone: () => void }) { + const { t } = useLingui(); + const ids = useId(); + const done = useRef(onDone); + done.current = onDone; + const [folder, setFolder] = useState(null); + const [looking, setLooking] = useState(false); + const [scanId, setScanId] = useState(null); + const [found, setFound] = useState(null); + const [failed, setFailed] = useState(false); + const [projectIds, setProjectIds] = useState([]); + const [factIds, setFactIds] = useState([]); + const [saving, setSaving] = useState(false); + const [error, setError] = useState(null); + + useEffect(() => { + let cancelled = false; + rpc.onboarding + .scanTarget() + .then((target) => { + if (cancelled) return; + if (target.folder) setFolder(target.folder); + else done.current(); + }) + .catch(() => { + if (!cancelled) done.current(); + }); + return () => { + cancelled = true; + }; + }, []); + + useEffect(() => { + if (!scanId) return; + let cancelled = false; + let timer: ReturnType | undefined; + const poll = () => { + rpc.onboarding + .scanStatus({ scanId }) + .then((status) => { + if (cancelled) return; + if (status.status === "scanning") { + timer = setTimeout(poll, POLL_MS); + } else if (status.status === "failed") { + setFailed(true); + } else { + setFound({ projects: status.projects, facts: status.facts }); + setFactIds(status.facts.map((fact) => fact.id)); + } + }) + .catch(() => { + if (!cancelled) setFailed(true); + }); + }; + poll(); + return () => { + cancelled = true; + clearTimeout(timer); + }; + }, [scanId]); + + async function look() { + setLooking(true); + try { + setScanId((await rpc.onboarding.scan()).scanId); + } catch { + setFailed(true); + } + } + + async function add() { + if (!scanId) return; + setSaving(true); + setError(null); + try { + await rpc.onboarding.applyScan({ scanId, projectIds, factIds }); + done.current(); + } catch (reason) { + setError(reason instanceof Error ? reason.message : String(reason)); + setSaving(false); + } + } + + const continueButton = ( +
+ +
+ ); + + if (failed) { + return ( +
+

+ Could not look in this folder. +

+ {continueButton} +
+ ); + } + + if (found && found.projects.length === 0) { + return ( +
+

+ No projects found +

+ {continueButton} +
+ ); + } + + if (found) { + return ( +
+
+ +

+ Add as projects +

+ +
+ {found.projects.map((project) => ( + + ))} +
+
+ + {found.facts.length > 0 ? ( +
+ + Add to About you + +
+ {found.facts.map((fact) => ( + + ))} +
+
+ ) : null} + + {error ?

{error}

: null} + +
+ + +
+
+ ); + } + + if (looking) { + return ( +
+ +
+ ); + } + + if (!folder) return null; + + return ( +
+

+ Look for projects here? +

+

+ {folder} +

+

+ Only file and folder names are read. +

+
+ + +
+
+ ); +} diff --git a/apps/web/src/pages/Onboarding.tsx b/apps/web/src/pages/Onboarding.tsx index 0423eaa..75b9533 100644 --- a/apps/web/src/pages/Onboarding.tsx +++ b/apps/web/src/pages/Onboarding.tsx @@ -9,7 +9,7 @@ import { type OnboardingEmojiConfig, OnboardingOoDesigner, } from "../components/onboarding/OnboardingOoDesigner"; -import { OnboardingScanProgress } from "../components/onboarding/OnboardingScanProgress"; +import { OnboardingScanStep } from "../components/onboarding/OnboardingScanStep"; import { KOKORO_LOCAL_TOKEN, OnboardingVoiceStep, @@ -115,7 +115,6 @@ export function OnboardingPage() { const [profilePersisted, setProfilePersisted] = useState(false); const [crewReady, setCrewReady] = useState(false); const [_helpVibe, setHelpVibe] = useState(null); - const [scanBotId, setScanBotId] = useState(null); const [emojiConfig, setEmojiConfig] = useState(defaultEmojiConfig); const [prefs, setPrefs] = useState(defaultPreferences()); @@ -141,14 +140,6 @@ export function OnboardingPage() { if (cancelled) return; setBootstrapMe(me); setHelpVibe(inferHelpVibeHints(collectLocalProfileSignals(me))); - // Get bot ID for scan phase - try { - const botList = await rpc.bots.list(); - const mainBot = botList.find((b) => b.kind === "main"); - if (mainBot && !cancelled) setScanBotId(mainBot.id); - } catch { - /* best effort */ - } setIntegrationSetup(integrations); // The first step renders before this resolves; never pull a user back who moved on. if (!me.needsModel && integrations?.needsSetup) { @@ -513,12 +504,7 @@ export function OnboardingPage() {
) : null} - {step === "scan" ? ( - setStep("bot")} - botId={scanBotId ?? undefined} - /> - ) : null} + {step === "scan" ? setStep("bot")} /> : null} {step === "bot" && error ? (
diff --git a/packages/contracts/src/index.ts b/packages/contracts/src/index.ts index 3865e1b..af399a3 100644 --- a/packages/contracts/src/index.ts +++ b/packages/contracts/src/index.ts @@ -10,6 +10,7 @@ export * from "./integration-settings.js"; export * from "./local-settings.js"; export * from "./mcp.js"; export * from "./model-tiers.js"; +export * from "./onboarding-scan.js"; export * from "./openai-compatible-ui.js"; export * from "./project-goals.js"; export * from "./project-sessions.js"; diff --git a/packages/contracts/src/onboarding-scan.ts b/packages/contracts/src/onboarding-scan.ts new file mode 100644 index 0000000..97faa35 --- /dev/null +++ b/packages/contracts/src/onboarding-scan.ts @@ -0,0 +1,49 @@ +import * as z from "zod"; +import { Id } from "./ids.js"; + +/** Upper bounds on one scan's choices; the server lists at most this many projects and facts. */ +export const ONBOARDING_SCAN_MAX_PROJECTS = 30; +export const ONBOARDING_SCAN_MAX_FACTS = 20; + +/** The folder a consented scan would read, or null when this account cannot scan. */ +export const OnboardingScanTargetSchema = z.object({ folder: z.string().nullable() }); +export type OnboardingScanTarget = z.infer; + +export const OnboardingScanProjectSchema = z.object({ + id: z.string(), + name: z.string(), + /** Relative to the scanned folder. */ + path: z.string(), +}); +export type OnboardingScanProject = z.infer; + +export const OnboardingScanFactSchema = z.object({ + id: z.string(), + /** A language or tool name, e.g. "TypeScript". */ + label: z.string(), +}); +export type OnboardingScanFact = z.infer; + +export const OnboardingScanStatusSchema = z.discriminatedUnion("status", [ + z.object({ status: z.literal("scanning") }), + z.object({ status: z.literal("failed") }), + z.object({ + status: z.literal("complete"), + projects: z.array(OnboardingScanProjectSchema), + facts: z.array(OnboardingScanFactSchema), + }), +]); +export type OnboardingScanStatus = z.infer; + +export const OnboardingScanApplyInputSchema = z.object({ + scanId: z.string(), + projectIds: z.array(z.string()).max(ONBOARDING_SCAN_MAX_PROJECTS), + factIds: z.array(z.string()).max(ONBOARDING_SCAN_MAX_FACTS), +}); +export type OnboardingScanApplyInput = z.infer; + +export const OnboardingScanApplyResultSchema = z.object({ + spaces: z.array(z.object({ id: Id, name: z.string() })), + factsAdded: z.number().int().nonnegative(), +}); +export type OnboardingScanApplyResult = z.infer; diff --git a/packages/contracts/src/rpc.ts b/packages/contracts/src/rpc.ts index 6640d4c..48506ba 100644 --- a/packages/contracts/src/rpc.ts +++ b/packages/contracts/src/rpc.ts @@ -83,6 +83,12 @@ import { IntegrationSetupStateSchema, } from "./integration-settings.js"; import { ModelTierMappingSchema, SetModelTierInput } from "./model-tiers.js"; +import { + OnboardingScanApplyInputSchema, + OnboardingScanApplyResultSchema, + OnboardingScanStatusSchema, + OnboardingScanTargetSchema, +} from "./onboarding-scan.js"; import { CreateProjectGoalInput, ProjectGoalSchema, @@ -676,15 +682,13 @@ export const appContract = { z.object({ botId: Id, provider: z.string(), connectorId: z.string().default("composio") }), ) .output(z.object({ ok: z.literal(true) })), - scan: oc.input(z.object({ botId: Id.optional() })).output(z.object({ scanId: z.string() })), - scanStatus: oc.input(z.object({ scanId: z.string() })).output( - z.object({ - status: z.enum(["scanning", "connecting", "building", "briefing", "complete", "failed"]), - progress: z.number(), - message: z.string(), - result: z.any().optional(), - }), - ), + /** The folder a scan would read; null when this account cannot scan, so the step is skipped. */ + scanTarget: oc.output(OnboardingScanTargetSchema), + /** Start scanning that folder. Only called after the user agreed. */ + scan: oc.output(z.object({ scanId: z.string() })), + scanStatus: oc.input(z.object({ scanId: z.string() })).output(OnboardingScanStatusSchema), + /** Create a project space per chosen project and save the chosen facts. */ + applyScan: oc.input(OnboardingScanApplyInputSchema).output(OnboardingScanApplyResultSchema), }, integrationSetup: { get: oc.output(IntegrationSetupStateSchema), diff --git a/packages/testkit/src/authorization.test.ts b/packages/testkit/src/authorization.test.ts index ce1e785..21ffadd 100644 --- a/packages/testkit/src/authorization.test.ts +++ b/packages/testkit/src/authorization.test.ts @@ -556,19 +556,18 @@ describeWithDatabase("API authorization and resource isolation", () => { ).toMatchObject({ content: "owner-only-memory" }); // The user profile is per user: another user's fact ids and spaces are out of reach. - const ownerProfile = await rpc<{ facts: Array<{ id: string; status: string }> }>( - app, - owner, - "profile/update", - { - addFacts: [ - { category: "work", value: "Owner works nights" }, - { category: "health", value: "Owner health note", source: "onboarding" }, - ], - }, - ); - const ownerFactIds = ownerProfile.facts.map((fact) => fact.id); - expect(ownerProfile.facts.map((fact) => fact.status).sort()).toEqual(["active", "pending"]); + const ownerProfile = await rpc<{ + facts: Array<{ id: string; status: string; source: string }>; + }>(app, owner, "profile/update", { + addFacts: [ + { category: "work", value: "Owner works nights" }, + { category: "health", value: "Owner health note", source: "onboarding" }, + ], + }); + // Connecting an app above already remembered it; this check is about the facts added here. + const ownerFacts = ownerProfile.facts.filter((fact) => fact.source !== "connector"); + const ownerFactIds = ownerFacts.map((fact) => fact.id); + expect(ownerFacts.map((fact) => fact.status).sort()).toEqual(["active", "pending"]); const profileCalls = [ ["profile/update", { confirmFactIds: ownerFactIds }], ["profile/update", { editFacts: [{ id: ownerFactIds[0], value: "Stolen" }] }], diff --git a/packages/testkit/src/cli/harness.ts b/packages/testkit/src/cli/harness.ts index 27415a4..5305a76 100644 --- a/packages/testkit/src/cli/harness.ts +++ b/packages/testkit/src/cli/harness.ts @@ -1,9 +1,11 @@ import { execSync } from "node:child_process"; -import { mkdir, writeFile } from "node:fs/promises"; +import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises"; +import { tmpdir } from "node:os"; import path from "node:path"; import { loadRootEnv } from "@rakazo/core/node/load-root-env"; import { PostgreSqlContainer } from "@testcontainers/postgresql"; import type { createApp } from "../../../../apps/api/src/app.ts"; +import { writeOnboardingScanFixture } from "../onboarding-scan-fixture.js"; import { runProcess } from "./process.js"; loadRootEnv(); @@ -106,6 +108,7 @@ async function main() { "packages/testkit/src/bot-secrets.test.ts", "packages/testkit/src/delegation.postgres.test.ts", "packages/testkit/src/user-profile.postgres.test.ts", + "packages/testkit/src/onboarding-discovery.postgres.test.ts", "packages/db/src/space-membership.postgres.test.ts", "packages/db/src/main-agent.postgres.test.ts", "packages/db/src/user-profile.postgres.test.ts", @@ -180,6 +183,10 @@ async function main() { { fetch: thirdParties.fetch, resolveHostname: thirdParties.resolveHostname }, ); const email = new EmailEmulator(); + // A fixture home folder, so the deployment owner's onboarding offers the real project scan. + const scanHome = await mkdtemp(path.join(tmpdir(), "rakazo-e2e-scan-home-")); + await writeOnboardingScanFixture(scanHome); + process.env.ONBOARDING_SCAN_HOME = scanHome; const handles = await createApp({ databaseUrl, prisma: undefined, @@ -192,13 +199,30 @@ async function main() { }, integrationsCatalogUrl: "https://catalog.example.test/", }); + // No spec user owns the deployment unless it asks (POST /__e2e/deployment-owner), so + // owner-only onboarding steps appear only in the specs that test them, whatever runs first. + await handles.prisma.deploymentSettings.upsert({ + where: { id: "default" }, + create: { + id: "default", + ownerUserId: E2E_NO_OWNER, + signupsEnabled: true, + signupAllowlist: "", + signupPolicyInitialized: true, + }, + update: { ownerUserId: E2E_NO_OWNER }, + }); let activeRequests = 0; const requestWaiters = new Set<() => void>(); const server = serve({ fetch: async (request) => { - if (new URL(request.url).pathname === "/__e2e/emails") { + const { pathname } = new URL(request.url); + if (pathname === "/__e2e/emails") { return Response.json(email.sent, { headers: { "cache-control": "no-store" } }); } + if (pathname === "/__e2e/deployment-owner" && request.method === "POST") { + return Response.json(await setDeploymentOwner(handles, await request.json())); + } activeRequests += 1; try { return await handles.app.fetch(request); @@ -266,6 +290,7 @@ async function main() { await new Promise((resolve) => requestWaiters.add(resolve)); } await handles.stop().catch(() => undefined); + await rm(scanHome, { recursive: true, force: true }).catch(() => undefined); for (let index = 0; index < computers.length; index += 4) { const results = await Promise.allSettled( computers.slice(index, index + 4).map((computer) => @@ -304,6 +329,9 @@ async function main() { type AppHandles = Awaited>; +/** Matches no user, so the first signup does not claim the deployment. */ +const E2E_NO_OWNER = "e2e-no-owner"; + async function managedComputers(handles: AppHandles) { if (!["e2b", "daytona", "box"].includes(sandboxProvider)) return []; return handles.prisma.computer.findMany({ @@ -312,6 +340,33 @@ async function managedComputers(handles: AppHandles) { }); } +/** + * Lets a spec act as the deployment owner (by email) for owner-only steps, then restore the + * previous owner (by id). Returns the owner it replaced. + */ +async function setDeploymentOwner( + handles: AppHandles, + input: { email?: string; userId?: string | null }, +): Promise<{ previousOwnerUserId: string | null }> { + const previous = await handles.prisma.deploymentSettings.findUnique({ + where: { id: "default" }, + select: { ownerUserId: true }, + }); + const ownerUserId = input.email + ? ( + await handles.prisma.user.findUniqueOrThrow({ + where: { email: input.email }, + select: { id: true }, + }) + ).id + : (input.userId ?? E2E_NO_OWNER); + await handles.prisma.deploymentSettings.update({ + where: { id: "default" }, + data: { ownerUserId }, + }); + return { previousOwnerUserId: previous?.ownerUserId ?? null }; +} + async function writeSummary(reportDir: string, summary: Record) { await writeFile( path.join(reportDir, "summary.json"), diff --git a/packages/testkit/src/onboarding-discovery.postgres.test.ts b/packages/testkit/src/onboarding-discovery.postgres.test.ts new file mode 100644 index 0000000..671131b --- /dev/null +++ b/packages/testkit/src/onboarding-discovery.postgres.test.ts @@ -0,0 +1,363 @@ +import { mkdtempSync, realpathSync, rmSync, symlinkSync } from "node:fs"; +import { mkdir, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import path from "node:path"; +import { + ComposioEmulator, + PipedreamConnector, + ThirdPartyConnectorEmulator, +} from "@rakazo/adapters"; +import type { + OnboardingScanApplyResult, + OnboardingScanStatus, + SpaceNavigation, + UserProfileState, +} from "@rakazo/contracts"; +import { afterAll, beforeAll, describe, expect, it, vi } from "vitest"; +import type { createApp } from "../../../apps/api/src/app.ts"; +import { sessionCookieHeader } from "./index.js"; +import { writeOnboardingScanFixture } from "./onboarding-scan-fixture.js"; + +type App = { request: (input: string, init?: RequestInit) => Response | Promise }; +type AppHandles = Awaited>; +type Actor = { userId: string; spaceId: string }; + +process.env.WAKEUP_DRIVER = "memory"; +process.env.SANDBOX_PROVIDER = "fake"; +process.env.AGENT_RUNTIME = "scripted"; + +const hasDb = process.env.VERIFY_DATABASE === "1" && Boolean(process.env.DATABASE_URL); +const describeWithDatabase = hasDb ? describe : describe.skip; +const TEST_ENCRYPTION_KEY = "offline-discovery-test-encryption-key"; + +describeWithDatabase("onboarding discovery through the API", () => { + let handles: AppHandles; + let app: App; + let composio: ComposioEmulator; + const stamp = `${Date.now()}-${Math.random().toString(36).slice(2)}`; + const dataDir = mkdtempSync(path.join(tmpdir(), "rakazo-discovery-")); + const home = realpathSync(mkdtempSync(path.join(tmpdir(), "rakazo-scan-home-"))); + const outside = realpathSync(mkdtempSync(path.join(tmpdir(), "rakazo-scan-outside-"))); + + beforeAll(async () => { + await writeOnboardingScanFixture(home); + const { createApp } = await import("../../../apps/api/src/app.ts"); + composio = new ComposioEmulator(); + const thirdParties = new ThirdPartyConnectorEmulator(); + handles = await createApp({ + databaseUrl: process.env.DATABASE_URL!, + dataDir, + sandboxProvider: "fake", + agentRuntime: "scripted", + wakeupDriver: "memory", + signupsEnabled: "true", + encryptionKey: TEST_ENCRYPTION_KEY, + onboardingScanHome: home, + composio, + pipedream: new PipedreamConnector( + { + clientId: "fake-client-id", + clientSecret: "fake-client-secret", + projectId: "fake-project-id", + environment: "development", + identitySecret: TEST_ENCRYPTION_KEY, + }, + { fetch: thirdParties.fetch, resolveHostname: thirdParties.resolveHostname }, + ), + remoteConnectors: { + fetch: thirdParties.fetch, + resolveHostname: thirdParties.resolveHostname, + }, + }); + app = handles.app; + }); + + afterAll(async () => { + await handles?.stop(); + for (const dir of [dataDir, home, outside]) rmSync(dir, { recursive: true, force: true }); + }); + + async function account(label: string): Promise<{ cookie: string; actor: Actor }> { + const cookie = await signup(app, `${label}-${stamp}@rakazo.test`, label); + return { cookie, actor: await rpc(app, cookie, "me") }; + } + + async function makeDeploymentOwner(actor: Actor): Promise { + await handles.prisma.deploymentSettings.update({ + where: { id: "default" }, + data: { ownerUserId: actor.userId }, + }); + } + + async function finishedScan(cookie: string) { + const { scanId } = await rpc<{ scanId: string }>(app, cookie, "onboarding/scan"); + const status = await vi.waitFor( + async () => { + const current = await rpc(app, cookie, "onboarding/scanStatus", { + scanId, + }); + if (current.status === "scanning") throw new Error("still scanning"); + return current; + }, + { timeout: 10_000, interval: 50 }, + ); + if (status.status !== "complete") throw new Error("scan failed"); + return { scanId, ...status }; + } + + it("offers the scan only to the deployment owner and keeps it with them", async () => { + const owner = await account("discovery-owner"); + const other = await account("discovery-other"); + await makeDeploymentOwner(owner.actor); + + await expect(rpc(app, other.cookie, "onboarding/scanTarget")).resolves.toEqual({ + folder: null, + }); + expect((await raw(app, other.cookie, "onboarding/scan")).status).toBe(403); + await expect(rpc(app, owner.cookie, "onboarding/scanTarget")).resolves.toEqual({ + folder: home, + }); + + const scan = await finishedScan(owner.cookie); + expect(scan.projects).toEqual([ + { id: "project-0", name: "atlas", path: "code/atlas" }, + { id: "project-1", name: "garden", path: "code/garden" }, + ]); + expect(scan.facts.map((fact) => fact.label)).toEqual([ + "Python", + "TypeScript", + "Docker", + "GitHub Actions", + ]); + expect( + (await raw(app, other.cookie, "onboarding/scanStatus", { scanId: scan.scanId })).status, + ).toBe(404); + expect( + ( + await raw(app, other.cookie, "onboarding/applyScan", { + scanId: scan.scanId, + projectIds: ["project-0"], + factIds: ["language:Python"], + }) + ).status, + ).toBe(404); + await expect(rpc(app, other.cookie, "profile/get")).resolves.toMatchObject({ + facts: [], + }); + }); + + it("creates the chosen projects in the owner's own spaces and saves only the chosen facts", async () => { + const owner = await account("discovery-creator"); + const intruder = await account("discovery-intruder"); + await makeDeploymentOwner(owner.actor); + const atlasFolder = path.join(home, "code/atlas"); + // Another tenant already linked a space with the same name to the same folder. + const foreign = await rpc<{ id: string }>(app, intruder.cookie, "spaces/create", { + name: "atlas", + workspacePath: atlasFolder, + }); + + const scan = await finishedScan(owner.cookie); + const choice = { + scanId: scan.scanId, + projectIds: ["project-0"], + factIds: ["language:TypeScript", "tool:Docker"], + }; + const applied = await rpc( + app, + owner.cookie, + "onboarding/applyScan", + choice, + ); + + expect(applied.factsAdded).toBe(2); + expect(applied.spaces).toEqual([{ id: expect.any(String), name: "atlas" }]); + const created = applied.spaces[0]!.id; + expect(created).not.toBe(foreign.id); + const ownerOrg = await handles.prisma.space.findUniqueOrThrow({ + where: { id: owner.actor.spaceId }, + select: { organizationId: true }, + }); + await expect( + handles.prisma.space.findUniqueOrThrow({ + where: { id: created }, + select: { organizationId: true, workspacePath: true }, + }), + ).resolves.toEqual({ organizationId: ownerOrg.organizationId, workspacePath: atlasFolder }); + await expect( + handles.prisma.spaceMember.findMany({ + where: { spaceId: { in: [created, foreign.id] } }, + select: { spaceId: true, userId: true, role: true }, + orderBy: { spaceId: "asc" }, + }), + ).resolves.toEqual( + expect.arrayContaining([ + { spaceId: created, userId: owner.actor.userId, role: "owner" }, + { spaceId: foreign.id, userId: intruder.actor.userId, role: "owner" }, + ]), + ); + expect( + await handles.prisma.spaceMember.count({ where: { spaceId: { in: [created, foreign.id] } } }), + ).toBe(2); + await expect( + handles.prisma.memoryDocument.count({ + where: { spaceId: created, userId: owner.actor.userId, scope: "user" }, + }), + ).resolves.toBe(1); + + const ownerSpaces = await rpc(app, owner.cookie, "spaces/list"); + expect(ownerSpaces.spaces).toContainEqual( + expect.objectContaining({ + id: created, + name: "atlas", + workspace: expect.objectContaining({ path: atlasFolder }), + }), + ); + expect(ownerSpaces.spaces.map((space) => space.id)).not.toContain(foreign.id); + const intruderSpaces = await rpc(app, intruder.cookie, "spaces/list"); + expect(intruderSpaces.spaces.map((space) => space.id)).not.toContain(created); + + const profile = await rpc(app, owner.cookie, "profile/get"); + expect( + profile.facts.map(({ category, value, source }) => ({ category, value, source })), + ).toEqual( + expect.arrayContaining([ + { category: "work", value: "Codes in TypeScript", source: "onboarding" }, + { category: "tools", value: "Uses Docker", source: "onboarding" }, + ]), + ); + expect(profile.facts).toHaveLength(2); + await expect(rpc(app, intruder.cookie, "profile/get")).resolves.toMatchObject( + { facts: [] }, + ); + + // Applying again reuses the space and the facts. + await expect( + rpc(app, owner.cookie, "onboarding/applyScan", choice), + ).resolves.toEqual({ spaces: [{ id: created, name: "atlas" }], factsAdded: 0 }); + expect(await handles.prisma.spaceMember.count({ where: { userId: owner.actor.userId } })).toBe( + 2, + ); + }); + + it("refuses a chosen project that left the scan folder and writes nothing", async () => { + const owner = await account("discovery-escape"); + await makeDeploymentOwner(owner.actor); + const scan = await finishedScan(owner.cookie); + await mkdir(path.join(outside, "elsewhere", ".git"), { recursive: true }); + await rm(path.join(home, "code/garden"), { recursive: true, force: true }); + symlinkSync(path.join(outside, "elsewhere"), path.join(home, "code/garden")); + + const response = await raw(app, owner.cookie, "onboarding/applyScan", { + scanId: scan.scanId, + projectIds: ["project-1"], + factIds: ["language:Python"], + }); + expect(response.status).toBe(400); + expect(await handles.prisma.spaceMember.count({ where: { userId: owner.actor.userId } })).toBe( + 1, + ); + await expect(rpc(app, owner.cookie, "profile/get")).resolves.toMatchObject({ + facts: [], + }); + }); + + it("remembers each connected app once as a tools fact and keeps it after revoking", async () => { + const user = await account("discovery-apps"); + const other = await account("discovery-apps-other"); + // A featured app is named by its label, whatever the account is called. + const gmail = await rpc<{ connectionId: string }>(app, user.cookie, "connections/begin", { + connectorId: "composio", + provider: "GMAIL", + displayName: "Personal", + }); + // Other apps take the first account's name; a second account adds nothing. + for (const displayName of ["GitHub", "GitHub 2"]) { + await rpc(app, user.cookie, "connections/begin", { + connectorId: "composio", + provider: "GITHUB", + displayName, + }); + } + // Connected through the authorization round trip. + const linear = await rpc<{ connectionId: string; authorizationUrl: string | null }>( + app, + user.cookie, + "connections/begin", + { connectorId: "pipedream", provider: "linear", displayName: "Linear" }, + ); + expect(linear.authorizationUrl).not.toBeNull(); + await expect( + rpc<{ status: string }>(app, user.cookie, "connections/complete", { + connectionId: linear.connectionId, + }), + ).resolves.toMatchObject({ status: "connected" }); + // Connected remotely, then noticed when the catalog reconciles a pending row. + await handles.prisma.connection.create({ + data: { + spaceId: user.actor.spaceId, + userId: user.actor.userId, + provider: "SLACK", + displayName: "SLACK", + status: "pending", + }, + }); + await composio.begin( + { provider: "SLACK", redirectUrl: "http://127.0.0.1.invalid/callback" }, + { + operationId: "discovery-test", + traceId: "discovery-test", + spaceId: user.actor.spaceId, + userId: user.actor.userId, + signal: new AbortController().signal, + }, + ); + await rpc(app, user.cookie, "connections/catalog", { connectorId: "composio" }); + await rpc(app, user.cookie, "connections/revoke", { connectionId: gmail.connectionId }); + + const profile = await rpc(app, user.cookie, "profile/get"); + expect( + profile.facts + .map(({ category, value, source }) => ({ category, value, source })) + .sort((left, right) => left.value.localeCompare(right.value)), + ).toEqual([ + { category: "tools", value: "Uses GitHub", source: "connector" }, + { category: "tools", value: "Uses Gmail", source: "connector" }, + { category: "tools", value: "Uses Linear", source: "connector" }, + { category: "tools", value: "Uses Slack", source: "connector" }, + ]); + await expect(rpc(app, other.cookie, "profile/get")).resolves.toMatchObject({ + facts: [], + }); + }); +}); + +async function signup(app: App, email: string, name: string) { + const response = await app.request("/api/auth/sign-up/email", { + method: "POST", + headers: { "content-type": "application/json", origin: "http://127.0.0.1:5173" }, + body: JSON.stringify({ email, password: "password12", name }), + }); + if (response.status >= 400) { + throw new Error(`signup failed ${response.status}: ${await response.text()}`); + } + return sessionCookieHeader(response); +} + +async function raw(app: App, cookie: string, procedure: string, body: unknown = {}) { + return app.request(`/rpc/${procedure}`, { + method: "POST", + headers: { "content-type": "application/json", cookie, origin: "http://127.0.0.1:5173" }, + body: JSON.stringify({ json: body }), + }); +} + +async function rpc(app: App, cookie: string, procedure: string, body: unknown = {}) { + const response = await raw(app, cookie, procedure, body); + const text = await response.text(); + const payload = JSON.parse(text) as { json?: T; error?: { message?: string } }; + if (response.status >= 400 || payload.error) { + throw new Error(`${procedure} ${response.status}: ${payload.error?.message ?? text}`); + } + return payload.json as T; +} diff --git a/packages/testkit/src/onboarding-scan-fixture.ts b/packages/testkit/src/onboarding-scan-fixture.ts new file mode 100644 index 0000000..f79e884 --- /dev/null +++ b/packages/testkit/src/onboarding-scan-fixture.ts @@ -0,0 +1,35 @@ +import { mkdir, writeFile } from "node:fs/promises"; +import path from "node:path"; + +/** An empty but valid git directory, so git commands stop here instead of searching upwards. */ +async function writeGitDirectory(project: string): Promise { + await mkdir(path.join(project, ".git", "objects"), { recursive: true }); + await mkdir(path.join(project, ".git", "refs"), { recursive: true }); + await writeFile(path.join(project, ".git", "HEAD"), "ref: refs/heads/main\n"); +} + +async function writeFiles(root: string, files: Record): Promise { + for (const [relative, content] of Object.entries(files)) { + const file = path.join(root, relative); + await mkdir(path.dirname(file), { recursive: true }); + await writeFile(file, content); + } +} + +/** + * A home folder for the onboarding scan: two projects ("code/atlas" in TypeScript with Docker and + * GitHub Actions, "code/garden" in Python) and a notes folder that is not a project. + */ +export async function writeOnboardingScanFixture(home: string): Promise { + await writeFiles(home, { + "code/atlas/src/index.ts": "export const atlas = 1;\n", + "code/atlas/src/app.tsx": "export const App = () => null;\n", + "code/atlas/Dockerfile": "FROM scratch\n", + "code/atlas/.github/workflows/ci.yml": "on: push\n", + "code/garden/main.py": "print('garden')\n", + "code/garden/util.py": "VALUE = 1\n", + "notes/todo.md": "- water the plants\n", + }); + await writeGitDirectory(path.join(home, "code/atlas")); + await writeGitDirectory(path.join(home, "code/garden")); +}