Merge branch 'improvement/v2-endpoints' into feat/sim-cli

Author: TheodoreSpeaks

.devcontainer/docker-compose.yml

@@ -19,6 +19,7 @@ services:
       - BETTER_AUTH_SECRET=${BETTER_AUTH_SECRET:-your_auth_secret_here}
       - ENCRYPTION_KEY=${ENCRYPTION_KEY:-your_encryption_key_here}
       - COPILOT_API_KEY=${COPILOT_API_KEY}
+      - NEXT_PUBLIC_CHAT_DISABLED=${NEXT_PUBLIC_CHAT_DISABLED:-}
       - SIM_AGENT_API_URL=${SIM_AGENT_API_URL}
       - OLLAMA_URL=${OLLAMA_URL:-http://localhost:11434}
       - NEXT_PUBLIC_SOCKET_URL=${NEXT_PUBLIC_SOCKET_URL:-}

apps/docs/content/docs/en/integrations/managed_agent.mdx

@@ -64,4 +64,200 @@ Open a Claude Platform Managed Agent session and return the assistant response a
 | `inputTokens` | number | Cumulative input tokens for the session. |
 | `outputTokens` | number | Cumulative output tokens for the session. |
 
+### `managed_agent_create_session`
+
+Create a Claude Platform Managed Agent session and return its id without waiting for a reply.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `agent` | string | Yes | Managed-agent id inside the linked Claude workspace. |
+| `environment` | string | Yes | Environment id inside the linked Claude workspace. |
+| `environmentType` | string | No | Environment execution model hint \('cloud' \| 'self_hosted'\). |
+| `userMessage` | string | No | Optional first message; seeds initial_events and starts the agent immediately. |
+| `vaults` | array | No | Zero or more vault ids for MCP tool auth. |
+| `vaultsAck` | boolean | No | Acknowledgement that the author may use the attached vaults. |
+| `memoryStoreId` | string | No | Optional Agent Memory Store id. |
+| `memoryAccess` | string | No | Memory store access mode: 'read_write' \(default\) or 'read_only'. |
+| `memoryInstructions` | string | No | Per-attachment guidance for how the agent should use the memory store. |
+| `files` | array | No | File attachments \(cloud envs only\), as \[\{fileId, mountPath?\}\]. |
+| `sessionParameters` | object | No | Key/value session metadata forwarded to the session. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | Anthropic session id \(sesn_...\). |
+| `started` | boolean | True when a first message was seeded, so the agent is already running. |
+
+### `managed_agent_send_message`
+
+Send a user message to an existing Claude Platform Managed Agent session.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `userMessage` | string | Yes | The user message to send to the session. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session the message was sent to. |
+| `sent` | boolean | True when the event was accepted by the API. |
+
+### `managed_agent_get_session`
+
+Read a Managed Agent session: status, stop reason, token usage, metadata, and any tool calls awaiting approval.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was read. |
+| `status` | string | Session status — 'idle', 'running', 'rescheduling', or 'terminated'. |
+| `stopReason` | string | Why the session last stopped, e.g. 'end_turn' or 'requires_action'. |
+| `requiresAction` | boolean | True when the session is waiting on a tool confirmation or custom tool result. If this is true while pendingTools is empty, the session is blocked but the API named no blocking events — surface it rather than treating the session as done. |
+| `pendingTools` | json | Blocking tool calls — \[\{id, eventType, kind, name, input\}\]. Route by kind: 'confirmation' ids go to Respond To Tool Confirmation, 'custom_tool_result' ids go to Respond To Custom Tool. |
+| `metadata` | json | Session metadata. |
+| `title` | string | Session title. |
+| `inputTokens` | number | Cumulative input tokens. |
+| `outputTokens` | number | Cumulative output tokens. |
+
+### `managed_agent_list_events`
+
+Read a Managed Agent session's event history and the agent's reply text.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `eventTypes` | array | No | Optional event-type filter, e.g. \['agent.message'\]. Omit to return every event. |
+| `limit` | number | No | Maximum events to return, keeping the most recent \(default 500\). |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was read. |
+| `events` | json | Session events, oldest first. |
+| `count` | number | Number of events returned. |
+| `assistantText` | string | Concatenated text of every persisted agent.message, in order. |
+| `truncated` | boolean | True when the limit was hit and older events were dropped. |
+
+### `managed_agent_update_session`
+
+Update a Managed Agent session's title or metadata.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `title` | string | No | New session title. |
+| `sessionParameters` | object | No | Replacement metadata map \(replaces all stored metadata, not merged\). Leaving it empty leaves the stored metadata unchanged — use clearMetadata to remove it. |
+| `clearMetadata` | boolean | No | Removes all of the session's stored metadata. Overrides any map supplied above. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was updated. |
+| `updated` | boolean | True when the update was accepted. |
+| `metadata` | json | Metadata after the update. |
+| `title` | string | Title after the update. |
+
+### `managed_agent_interrupt_session`
+
+Stop a running Managed Agent session; it stays usable afterwards.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was interrupted. |
+| `interrupted` | boolean | True when the interrupt was accepted. |
+
+### `managed_agent_respond_tool_confirmation`
+
+Allow or deny the tool calls a Managed Agent session is waiting on before it can continue.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `toolUseIds` | array | Yes | Blocking tool-use EVENT ids, from Get Session pendingTools\[\].id where kind is 'confirmation' \(not toolu_ ids\). |
+| `decision` | string | Yes | 'allow' to let the tools run, or 'deny' to reject them. |
+| `denyMessage` | string | No | Reason surfaced to the agent. Only sent when the decision is deny. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was answered. |
+| `decision` | string | The decision applied — 'allow' or 'deny'. |
+| `confirmedToolUseIds` | json | The tool-use event ids that were answered. |
+
+### `managed_agent_respond_custom_tool`
+
+Return the result of a custom tool a Managed Agent session is waiting on so it can continue.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `customToolUseId` | string | Yes | The custom tool-use EVENT id being answered, from Get Session pendingTools\[\].id where kind is 'custom_tool_result'. |
+| `result` | string | Yes | The tool's output, returned to the agent as text. |
+| `isError` | boolean | No | Mark the result as a failure so the agent can adjust its approach. |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was answered. |
+| `answeredToolUseId` | string | The custom tool-use event id that was answered. |
+
+### `managed_agent_archive_session`
+
+Archive a Managed Agent session, preserving its history. Not reversible.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was archived. |
+| `archived` | boolean | True when the archive was accepted. |
+
+### `managed_agent_delete_session`
+
+Permanently delete a Managed Agent session, its events, and its sandbox. Not reversible.
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+
+#### Output
+
+| Parameter | Type | Description |
+| --------- | ---- | ----------- |
+| `sessionId` | string | The session that was deleted. |
+| `deleted` | boolean | True when the delete was accepted. |
+
 

apps/docs/content/docs/en/platform/self-hosting/environment-variables.mdx

@@ -64,7 +64,8 @@ import { Callout } from 'fumadocs-ui/components/callout'
 | Variable | Description |
 |----------|-------------|
 | `API_ENCRYPTION_KEY` | Encrypts stored API keys (32 hex chars): `openssl rand -hex 32` |
-| `COPILOT_API_KEY` | API key for copilot features |
+| `COPILOT_API_KEY` | API key for Chat. Without it the Sim Chat block, scheduled prompt jobs, and Inbox cannot run |
+| `NEXT_PUBLIC_CHAT_DISABLED` | Set to `true` to hide the Chat module: the workspace lands on your first workflow, with no chats list, scheduled tasks, or editor Chat panel. Chat is shown when unset; `bun run setup` sets it for you if you skip the chat key |
 | `ADMIN_API_KEY` | Admin API key for GitOps operations |
 | `ALLOWED_LOGIN_DOMAINS` | Restrict signups to domains (comma-separated) |
 | `ALLOWED_LOGIN_EMAILS` | Restrict signups to specific emails (comma-separated) |

apps/realtime/package.json

@@ -33,9 +33,12 @@
     "@sim/workflow-types": "workspace:*",
     "@socket.io/redis-adapter": "8.3.0",
     "drizzle-orm": "^0.45.2",
+    "lib0": "0.2.117",
     "postgres": "^3.4.5",
     "redis": "5.10.0",
     "socket.io": "^4.8.1",
+    "y-protocols": "1.0.7",
+    "yjs": "13.6.31",
     "zod": "4.3.6"
   },
   "devDependencies": {

apps/realtime/src/access-revalidation.test.ts

@@ -50,16 +50,14 @@ function makeManager(sockets: FakeSocket[], presence: Partial<UserPresence>[] =
   const manager = {
     io: { sockets: { sockets: socketMap } },
     isReady: () => true,
-    getWorkflowUsers: vi.fn().mockResolvedValue(presence),
-    getWorkflowIdForSocket: vi.fn().mockResolvedValue(null),
-    removeUserFromRoom: vi
-      .fn()
-      .mockImplementation(async (_socketId: string, workflowId?: string) => workflowId ?? null),
+    getRoomUsers: vi.fn().mockResolvedValue(presence),
+    getRoomForSocket: vi.fn().mockResolvedValue(null),
+    removeUserFromRoom: vi.fn().mockResolvedValue(true),
     broadcastPresenceUpdate: vi.fn().mockResolvedValue(undefined),
   }
   return manager as unknown as IRoomManager & {
-    getWorkflowUsers: ReturnType<typeof vi.fn>
-    getWorkflowIdForSocket: ReturnType<typeof vi.fn>
+    getRoomUsers: ReturnType<typeof vi.fn>
+    getRoomForSocket: ReturnType<typeof vi.fn>
     removeUserFromRoom: ReturnType<typeof vi.fn>
     broadcastPresenceUpdate: ReturnType<typeof vi.fn>
   }
@@ -84,8 +82,11 @@ describe('access-revalidation sweep', () => {
       expect.objectContaining({ workflowId: 'wf-1' })
     )
     expect(socket.leave).toHaveBeenCalledWith('wf-1')
-    expect(manager.removeUserFromRoom).toHaveBeenCalledWith('sock-1', 'wf-1')
-    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith('wf-1')
+    expect(manager.removeUserFromRoom).toHaveBeenCalledWith(
+      { type: 'workflow', id: 'wf-1' },
+      'sock-1'
+    )
+    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith({ type: 'workflow', id: 'wf-1' })
   })
 
   it('keeps a socket whose access is still valid', async () => {
@@ -141,7 +142,30 @@ describe('access-revalidation sweep', () => {
 
     expect(mockResolveRole).toHaveBeenCalledWith('user-1', 'wf-1', 'read')
     // The security scan must stay Redis-free — presence is never consulted.
-    expect(manager.getWorkflowUsers).not.toHaveBeenCalled()
+    expect(manager.getRoomUsers).not.toHaveBeenCalled()
+  })
+
+  it('never evicts a socket joined only to a non-workflow room (files/tables/file-doc)', async () => {
+    // The sweep shares one io with the files/tables/file-doc handlers. Those rooms are
+    // namespaced (`workspace-files:ws-1`, `table:t-1`), so treating every socket.rooms
+    // entry as a workflow id would resolve a bogus permission → null → evict the socket
+    // from its files/table room every pass. Non-workflow rooms must be filtered out.
+    const filesSocket = makeSocket('sock-1', 'user-1', 'workspace-files:ws-1')
+    const tableSocket = makeSocket('sock-2', 'user-2', 'table:t-1')
+    const manager = makeManager([filesSocket, tableSocket])
+    // Even if the role resolver would say "no access", these must never be swept.
+    mockResolveRole.mockResolvedValue(null)
+
+    const sweep = startAccessRevalidationSweep(manager)
+    await sweep.runOnce()
+    sweep.stop()
+
+    expect(mockResolveRole).not.toHaveBeenCalled()
+    expect(filesSocket.leave).not.toHaveBeenCalled()
+    expect(filesSocket.emit).not.toHaveBeenCalled()
+    expect(tableSocket.leave).not.toHaveBeenCalled()
+    expect(tableSocket.emit).not.toHaveBeenCalled()
+    expect(manager.removeUserFromRoom).not.toHaveBeenCalled()
   })
 
   it('evicts only the revoked socket, not co-members of the room', async () => {
@@ -199,37 +223,37 @@ describe('access-revalidation sweep', () => {
     sweep.stop()
 
     expect(manager.removeUserFromRoom).toHaveBeenCalledTimes(2)
-    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith('wf-1')
+    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith({ type: 'workflow', id: 'wf-1' })
   })
 
-  it('defers cleanup when removal fails with expired socket mappings', async () => {
+  it('drops eviction cleanup when the socket is no longer mapped to the room (no infinite retry)', async () => {
     const socket = makeSocket('sock-1', 'user-1', 'wf-1')
     const manager = makeManager([socket], [{ socketId: 'sock-1', role: 'read' }])
-    // Mapping keys already expired (lookup resolves null) AND the removal fails
-    // (the Redis manager swallows the transport error into null) — the failed
-    // removal must still defer instead of reading as success.
-    manager.removeUserFromRoom.mockResolvedValueOnce(null)
+    // A healthy lookup shows the socket is no longer mapped to any workflow room (its presence
+    // is already gone), and removeUserFromRoom reports a no-op `false`. This is "already clean",
+    // not a deferrable failure — the cleanup must drop it, never re-enqueue a still-connected
+    // socket forever. (A genuine failure — still mapped + false — is covered by the next test.)
+    manager.getRoomForSocket.mockResolvedValue(null)
+    manager.removeUserFromRoom.mockResolvedValue(false)
     mockResolveRole.mockResolvedValue(null)
 
     const sweep = startAccessRevalidationSweep(manager)
     await sweep.runOnce()
-
-    expect(manager.broadcastPresenceUpdate).not.toHaveBeenCalled()
-
     await sweep.runOnce()
     sweep.stop()
 
-    expect(manager.removeUserFromRoom).toHaveBeenCalledTimes(2)
-    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith('wf-1')
+    // Attempted once, then dropped — not re-enqueued across passes, and no broadcast.
+    expect(manager.removeUserFromRoom).toHaveBeenCalledTimes(1)
+    expect(manager.broadcastPresenceUpdate).not.toHaveBeenCalled()
   })
 
   it('defers cleanup when the manager swallows a removal failure into null', async () => {
     const socket = makeSocket('sock-1', 'user-1', 'wf-1')
     const manager = makeManager([socket], [{ socketId: 'sock-1', role: 'read' }])
     // Live mapping but the removal reports nothing removed — the Redis manager
     // swallows transport errors into null, so this is the only failure signal.
-    manager.getWorkflowIdForSocket.mockResolvedValue('wf-1')
-    manager.removeUserFromRoom.mockResolvedValueOnce(null)
+    manager.getRoomForSocket.mockResolvedValue({ type: 'workflow', id: 'wf-1' })
+    manager.removeUserFromRoom.mockResolvedValueOnce(false)
     mockResolveRole.mockResolvedValue(null)
 
     const sweep = startAccessRevalidationSweep(manager)
@@ -243,15 +267,15 @@ describe('access-revalidation sweep', () => {
     sweep.stop()
 
     expect(manager.removeUserFromRoom).toHaveBeenCalledTimes(2)
-    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith('wf-1')
+    expect(manager.broadcastPresenceUpdate).toHaveBeenCalledWith({ type: 'workflow', id: 'wf-1' })
   })
 
   it('skips removal when the socket has since moved to a different workflow', async () => {
     const socket = makeSocket('sock-1', 'user-1', 'wf-1')
     const manager = makeManager([socket], [{ socketId: 'sock-1', role: 'read' }])
     // Between the membership snapshot and cleanup, the socket switched to a
     // workflow it can still access — removal must not touch its new presence.
-    manager.getWorkflowIdForSocket.mockResolvedValue('wf-2')
+    manager.getRoomForSocket.mockResolvedValue({ type: 'workflow', id: 'wf-2' })
     mockResolveRole.mockResolvedValue(null)
 
     const sweep = startAccessRevalidationSweep(manager)
@@ -357,7 +381,7 @@ describe('access-revalidation sweep', () => {
       const manager = makeManager([socket], [{ socketId: 'sock-1', role: 'read' }])
       // A Redis outage where commands hang in the offline queue instead of
       // failing: the cleanup lane stalls, but scans must keep running.
-      manager.getWorkflowIdForSocket.mockReturnValue(new Promise(() => {}))
+      manager.getRoomForSocket.mockReturnValue(new Promise(() => {}))
       mockResolveRole.mockResolvedValue(null)
 
       const sweep = startAccessRevalidationSweep(manager)