improvement(docs): add quick reference page and update SDK documentation (#2994 )

* docs(sdk): update README to reflect new interface * improvement(docs): add quick reference page and update SDK documentation * docs(copilot): update copilot documentation with all features
fix(sdk): improve input handling and separate input from options (#2993 )
2026-01-25 06:48:12 -05:00 · 2026-01-25 02:21:02 -08:00 · 2026-01-25 00:50:09 -08:00 · 2026-01-24 22:33:04 -08:00 · 2026-01-24 22:13:57 -08:00 · 2026-01-24 22:05:27 -08:00
26 changed files with 1075 additions and 346 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -27,10 +27,11 @@ jobs:
    steps:
      - name: Extract version from commit message
        id: extract
+        env:
+          COMMIT_MSG: ${{ github.event.head_commit.message }}
        run: |
-          COMMIT_MSG="${{ github.event.head_commit.message }}"
          # Only tag versions on main branch
-          if [ "${{ github.ref }}" = "refs/heads/main" ] && [[ "$COMMIT_MSG" =~ ^(v[0-9]+\.[0-9]+\.[0-9]+): ]]; then
+          if [ "$GITHUB_REF" = "refs/heads/main" ] && [[ "$COMMIT_MSG" =~ ^(v[0-9]+\.[0-9]+\.[0-9]+): ]]; then
            VERSION="${BASH_REMATCH[1]}"
            echo "version=${VERSION}" >> $GITHUB_OUTPUT
            echo "is_release=true" >> $GITHUB_OUTPUT
--- a/apps/docs/app/global.css
+++ b/apps/docs/app/global.css
@@ -119,6 +119,19 @@ aside#nd-sidebar {
  }
 }

+/* Hide TOC popover on tablet/medium screens (768px - 1279px) */
+/* Keeps it visible on mobile (<768px) for easy navigation */
+/* Desktop (>=1280px) already hides it via fumadocs xl:hidden */
+@media (min-width: 768px) and (max-width: 1279px) {
+  #nd-docs-layout {
+    --fd-toc-popover-height: 0px !important;
+  }
+
+  [data-toc-popover] {
+    display: none !important;
+  }
+}
+
 /* Desktop only: Apply custom navbar offset, sidebar width and margin offsets */
 /* On mobile, let fumadocs handle the layout natively */
@media (min-width: 1024px) {
--- a/apps/docs/content/docs/en/copilot/index.mdx
+++ b/apps/docs/content/docs/en/copilot/index.mdx
@@ -5,45 +5,25 @@ title: Copilot
 import { Callout } from 'fumadocs-ui/components/callout'
 import { Card, Cards } from 'fumadocs-ui/components/card'
 import { Image } from '@/components/ui/image'
-import { MessageCircle, Package, Zap, Infinity as InfinityIcon, Brain, BrainCircuit } from 'lucide-react'
+import { MessageCircle, Hammer, Zap, Globe, Paperclip, History, RotateCcw, Brain } from 'lucide-react'

-Copilot is your in-editor assistant that helps you build and edit workflows with Sim Copilot, as well as understand and improve them. It can:
+Copilot is your in-editor assistant that helps you build and edit workflows. It can:

 - **Explain**: Answer questions about Sim and your current workflow
 - **Guide**: Suggest edits and best practices
- **Edit**: Make changes to blocks, connections, and settings when you approve
+- **Build**: Add blocks, wire connections, and configure settings
+- **Debug**: Analyze execution issues and optimize performance

 <Callout type="info">
-  Copilot is a Sim-managed service. For self-hosted deployments, generate a Copilot API key in the hosted app (sim.ai → Settings → Copilot)
+  Copilot is a Sim-managed service. For self-hosted deployments:
  1. Go to [sim.ai](https://sim.ai) → Settings → Copilot and generate a Copilot API key
-  2. Set `COPILOT_API_KEY` in your self-hosted environment to that value
+  2. Set `COPILOT_API_KEY` in your self-hosted environment
 </Callout>

-## Context Menu (@)
-
-Use the `@` symbol to reference various resources and give Copilot more context about your workspace:
-
-<Image
-  src="/static/copilot/copilot-menu.png"
-  alt="Copilot context menu showing available reference options"
-  width={600}
-  height={400}
-/>
-
-The `@` menu provides access to:
- **Chats**: Reference previous copilot conversations
- **All workflows**: Reference any workflow in your workspace
- **Workflow Blocks**: Reference specific blocks from workflows
- **Blocks**: Reference block types and templates
- **Knowledge**: Reference your uploaded documents and knowledgebase
- **Docs**: Reference Sim documentation
- **Templates**: Reference workflow templates
- **Logs**: Reference execution logs and results
-
-This contextual information helps Copilot provide more accurate and relevant assistance for your specific use case.
-
 ## Modes

+Switch between modes using the mode selector at the bottom of the input area.
+
 <Cards>
  <Card
    title={
@@ -60,113 +40,153 @@ This contextual information helps Copilot provide more accurate and relevant ass
  <Card
    title={
      <span className="inline-flex items-center gap-2">
-        <Package className="h-4 w-4 text-muted-foreground" />
-        Agent
+        <Hammer className="h-4 w-4 text-muted-foreground" />
+        Build
      </span>
    }
  >
    <div className="m-0 text-sm">
-      Build-and-edit mode. Copilot proposes specific edits (add blocks, wire variables, tweak settings) and applies them when you approve.
+      Workflow building mode. Copilot can add blocks, wire connections, edit configurations, and debug issues.
    </div>
  </Card>
 </Cards>

-<div className="flex justify-center">
-  <Image
-    src="/static/copilot/copilot-mode.png"
-    alt="Copilot mode selection interface"
-    width={600}
-    height={400}
-    className="my-6"
-  />
-</div>
+## Models

-## Depth Levels
+Select your preferred AI model using the model selector at the bottom right of the input area.

-<Cards>
-  <Card
-    title={
-      <span className="inline-flex items-center gap-2">
-        <Zap className="h-4 w-4 text-muted-foreground" />
-        Fast
-      </span>
-    }
-  >
-    <div className="m-0 text-sm">Quickest and cheapest. Best for small edits, simple workflows, and minor tweaks.</div>
-  </Card>
-  <Card
-    title={
-      <span className="inline-flex items-center gap-2">
-        <InfinityIcon className="h-4 w-4 text-muted-foreground" />
-        Auto
-      </span>
-    }
-  >
-    <div className="m-0 text-sm">Balanced speed and reasoning. Recommended default for most tasks.</div>
-  </Card>
-  <Card
-    title={
-      <span className="inline-flex items-center gap-2">
-        <Brain className="h-4 w-4 text-muted-foreground" />
-        Advanced
-      </span>
-    }
-  >
-    <div className="m-0 text-sm">More reasoning for larger workflows and complex edits while staying performant.</div>
-  </Card>
-  <Card
-    title={
-      <span className="inline-flex items-center gap-2">
-        <BrainCircuit className="h-4 w-4 text-muted-foreground" />
-        Behemoth
-      </span>
-    }
-  >
-    <div className="m-0 text-sm">Maximum reasoning for deep planning, debugging, and complex architectural changes.</div>
-  </Card>
-</Cards>
+**Available Models:**
+- Claude 4.5 Opus, Sonnet (default), Haiku
+- GPT 5.2 Codex, Pro
+- Gemini 3 Pro

-### Mode Selection Interface
+Choose based on your needs: faster models for simple tasks, more capable models for complex workflows.

-You can easily switch between different reasoning modes using the mode selector in the Copilot interface:
+## Context Menu (@)

-<Image
-  src="/static/copilot/copilot-models.png"
-  alt="Copilot mode selection showing Advanced mode with MAX toggle"
-  width={600}
-  height={300}
-/>
+Use the `@` symbol to reference resources and give Copilot more context:

-The interface allows you to:
- **Select reasoning level**: Choose from Fast, Auto, Advanced, or Behemoth
- **Enable MAX mode**: Toggle for maximum reasoning capabilities when you need the most thorough analysis
- **See mode descriptions**: Understand what each mode is optimized for
+| Reference | Description |
+|-----------|-------------|
+| **Chats** | Previous copilot conversations |
+| **Workflows** | Any workflow in your workspace |
+| **Workflow Blocks** | Blocks in the current workflow |
+| **Blocks** | Block types and templates |
+| **Knowledge** | Uploaded documents and knowledge bases |
+| **Docs** | Sim documentation |
+| **Templates** | Workflow templates |
+| **Logs** | Execution logs and results |

-Choose your mode based on the complexity of your task - use Fast for simple questions and Behemoth for complex architectural changes.
+Type `@` in the input field to open the context menu, then search or browse to find what you need.

-## Billing and Cost Calculation
+## Slash Commands (/)

-### How Costs Are Calculated
+Use slash commands for quick actions:

-Copilot usage is billed per token from the underlying LLM:
+| Command | Description |
+|---------|-------------|
+| `/fast` | Fast mode execution |
+| `/research` | Research and exploration mode |
+| `/actions` | Execute agent actions |

- **Input tokens**: billed at the provider's base rate (**at-cost**)
- **Output tokens**: billed at **1.5×** the provider's base output rate
+**Web Commands:**

-```javascript
-copilotCost = (inputTokens × inputPrice + outputTokens × (outputPrice × 1.5)) / 1,000,000
-```
+| Command | Description |
+|---------|-------------|
+| `/search` | Search the web |
+| `/read` | Read a specific URL |
+| `/scrape` | Scrape web page content |
+| `/crawl` | Crawl multiple pages |

-| Component | Rate Applied         |
-|----------|----------------------|
-| Input    | inputPrice           |
-| Output   | outputPrice × 1.5    |
+Type `/` in the input field to see available commands.

-<Callout type="warning">
-  Pricing shown reflects rates as of September 4, 2025. Check provider documentation for current pricing.
-</Callout>
+## Chat Management
+
+### Starting a New Chat
+
+Click the **+** button in the Copilot header to start a fresh conversation.
+
+### Chat History
+
+Click **History** to view previous conversations grouped by date. You can:
+- Click a chat to resume it
+- Delete chats you no longer need
+
+### Editing Messages
+
+Hover over any of your messages and click **Edit** to modify and resend it. This is useful for refining your prompts.
+
+### Message Queue
+
+If you send a message while Copilot is still responding, it gets queued. You can:
+- View queued messages in the expandable queue panel
+- Send a queued message immediately (aborts current response)
+- Remove messages from the queue
+
+## File Attachments
+
+Click the attachment icon to upload files with your message. Supported file types include:
+- Images (preview thumbnails shown)
+- PDFs
+- Text files, JSON, XML
+- Other document formats
+
+Files are displayed as clickable thumbnails that open in a new tab.
+
+## Checkpoints & Changes
+
+When Copilot makes changes to your workflow, it saves checkpoints so you can revert if needed.
+
+### Viewing Checkpoints
+
+Hover over a Copilot message and click the checkpoints icon to see saved workflow states for that message.
+
+### Reverting Changes
+
+Click **Revert** on any checkpoint to restore your workflow to that state. A confirmation dialog will warn that this action cannot be undone.
+
+### Accepting Changes
+
+When Copilot proposes changes, you can:
+- **Accept**: Apply the proposed changes (`Mod+Shift+Enter`)
+- **Reject**: Dismiss the changes and keep your current workflow
+
+## Thinking Blocks
+
+For complex requests, Copilot may show its reasoning process in expandable thinking blocks:
+
+- Blocks auto-expand while Copilot is thinking
+- Click to manually expand/collapse
+- Shows duration of the thinking process
+- Helps you understand how Copilot arrived at its solution
+
+## Options Selection
+
+When Copilot presents multiple options, you can select using:
+
+| Control | Action |
+|---------|--------|
+| **1-9** | Select option by number |
+| **Arrow Up/Down** | Navigate between options |
+| **Enter** | Select highlighted option |
+
+Selected options are highlighted; unselected options appear struck through.
+
+## Keyboard Shortcuts
+
+| Shortcut | Action |
+|----------|--------|
+| `@` | Open context menu |
+| `/` | Open slash commands |
+| `Arrow Up/Down` | Navigate menu items |
+| `Enter` | Select menu item |
+| `Esc` | Close menus |
+| `Mod+Shift+Enter` | Accept Copilot changes |
+
+## Usage Limits
+
+Copilot usage is billed per token from the underlying LLM. If you reach your usage limit, Copilot will prompt you to increase your limit. You can add usage in increments ($50, $100) from your current base.

 <Callout type="info">
-  Model prices are per million tokens. The calculation divides by 1,000,000 to get the actual cost. See <a href="/execution/costs">the Cost Calculation page</a> for background and examples.
+  See the [Cost Calculation page](/execution/costs) for billing details.
 </Callout>
-
--- a/apps/docs/content/docs/en/keyboard-shortcuts/index.mdx
+++ b/apps/docs/content/docs/en/keyboard-shortcuts/index.mdx
@@ -34,6 +34,8 @@ Speed up your workflow building with these keyboard shortcuts and mouse controls
 | `Mod` + `V` | Paste blocks |
 | `Delete` or `Backspace` | Delete selected blocks or edges |
 | `Shift` + `L` | Auto-layout canvas |
+| `Mod` + `Shift` + `F` | Fit to view |
+| `Mod` + `Shift` + `Enter` | Accept Copilot changes |

 ## Panel Navigation

--- a/apps/docs/content/docs/en/meta.json
+++ b/apps/docs/content/docs/en/meta.json
@@ -3,6 +3,7 @@
  "pages": [
    "./introduction/index",
    "./getting-started/index",
+    "./quick-reference/index",
    "triggers",
    "blocks",
    "tools",
--- a/apps/docs/content/docs/en/quick-reference/index.mdx
+++ b/apps/docs/content/docs/en/quick-reference/index.mdx
@@ -0,0 +1,136 @@
+---
+title: Quick Reference
+description: Essential actions for navigating and using the Sim workflow editor
+---
+
+import { Callout } from 'fumadocs-ui/components/callout'
+
+A quick lookup for everyday actions in the Sim workflow editor. For keyboard shortcuts, see [Keyboard Shortcuts](/keyboard-shortcuts).
+
+<Callout type="info">
+  **Mod** refers to `Cmd` on macOS and `Ctrl` on Windows/Linux.
+</Callout>
+
+## Workspaces
+
+| Action | How |
+|--------|-----|
+| Create a workspace | Click workspace dropdown in sidebar → **New Workspace** |
+| Rename a workspace | Workspace settings → Edit name |
+| Switch workspaces | Click workspace dropdown in sidebar → Select workspace |
+| Invite team members | Workspace settings → **Team** → **Invite** |
+
+## Workflows
+
+| Action | How |
+|--------|-----|
+| Create a workflow | Click **New Workflow** button or `Mod+Shift+A` |
+| Rename a workflow | Double-click workflow name in sidebar, or right-click → **Rename** |
+| Duplicate a workflow | Right-click workflow → **Duplicate** |
+| Reorder workflows | Drag workflow up/down in the sidebar list |
+| Import a workflow | Sidebar menu → **Import** → Select file |
+| Create a folder | Right-click in sidebar → **New Folder** |
+| Rename a folder | Right-click folder → **Rename** |
+| Delete a folder | Right-click folder → **Delete** |
+| Collapse/expand folder | Click folder arrow, or double-click folder |
+| Move workflow to folder | Drag workflow onto folder in sidebar |
+| Delete a workflow | Right-click workflow → **Delete** |
+| Export a workflow | Right-click workflow → **Export** |
+| Assign workflow color | Right-click workflow → **Change Color** |
+| Multi-select workflows | `Mod+Click` or `Shift+Click` workflows in sidebar |
+| Open in new tab | Right-click workflow → **Open in New Tab** |
+
+## Blocks
+
+| Action | How |
+|--------|-----|
+| Add a block | Drag from Toolbar panel, or right-click canvas → **Add Block** |
+| Select a block | Click on the block |
+| Multi-select blocks | `Mod+Click` additional blocks, or right-drag to draw selection box |
+| Move blocks | Drag selected block(s) to new position |
+| Copy blocks | `Mod+C` with blocks selected |
+| Paste blocks | `Mod+V` to paste copied blocks |
+| Duplicate blocks | Right-click → **Duplicate** |
+| Delete blocks | `Delete` or `Backspace` key, or right-click → **Delete** |
+| Rename a block | Click block name in header, or edit in the Editor panel |
+| Enable/Disable a block | Right-click → **Enable/Disable** |
+| Toggle handle orientation | Right-click → **Toggle Handles** |
+| Toggle trigger mode | Right-click trigger block → **Toggle Trigger Mode** |
+| Configure a block | Select block → use Editor panel on right |
+
+## Connections
+
+| Action | How |
+|--------|-----|
+| Create a connection | Drag from output handle to input handle |
+| Delete a connection | Click edge to select → `Delete` key |
+| Use output in another block | Drag connection tag into input field |
+
+## Canvas Navigation
+
+| Action | How |
+|--------|-----|
+| Pan/move canvas | Left-drag on empty space, or scroll/trackpad |
+| Zoom in/out | Scroll wheel or pinch gesture |
+| Auto-layout | `Shift+L` |
+| Draw selection box | Right-drag on empty canvas area |
+
+## Panels & Views
+
+| Action | How |
+|--------|-----|
+| Open Copilot tab | Press `C` or click Copilot tab |
+| Open Toolbar tab | Press `T` or click Toolbar tab |
+| Open Editor tab | Press `E` or click Editor tab |
+| Search toolbar | `Mod+F` |
+| Toggle advanced mode | Click toggle button on input fields |
+| Resize panels | Drag panel edge |
+| Collapse/expand sidebar | Click collapse button on sidebar |
+
+## Running & Testing
+
+| Action | How |
+|--------|-----|
+| Run workflow | Click Play button or `Mod+Enter` |
+| Stop workflow | Click Stop button or `Mod+Enter` while running |
+| Test with chat | Use Chat panel on the right side |
+| Select output to view | Click dropdown in Chat panel → Select block output |
+| Clear chat history | Click clear button in Chat panel |
+| View execution logs | Open terminal panel at bottom, or `Mod+L` |
+| Filter logs by block | Click block filter in terminal |
+| Filter logs by status | Click status filter in terminal |
+| Search logs | Use search field in terminal |
+| Copy log entry | Right-click log entry → **Copy** |
+| Clear terminal | `Mod+D` |
+
+## Deployment
+
+| Action | How |
+|--------|-----|
+| Deploy a workflow | Click **Deploy** button in Deploy tab |
+| Update deployment | Click **Update** when changes are detected |
+| View deployment status | Check status indicator (Live/Update/Deploy) in Deploy tab |
+| Revert deployment | Access previous versions in Deploy tab |
+| Copy webhook URL | Deploy tab → Copy webhook URL |
+| Copy API endpoint | Deploy tab → Copy API endpoint URL |
+| Set up a schedule | Add Schedule trigger block → Configure interval |
+
+## Variables
+
+| Action | How |
+|--------|-----|
+| Add workflow variable | Variables tab → **Add Variable** |
+| Edit workflow variable | Variables tab → Click variable to edit |
+| Delete workflow variable | Variables tab → Click delete icon on variable |
+| Add environment variable | Settings → **Environment Variables** → **Add** |
+| Reference a variable | Use `{{variableName}}` syntax in block inputs |
+
+## Credentials
+
+| Action | How |
+|--------|-----|
+| Add API key | Block credential field → **Add Credential** → Enter API key |
+| Connect OAuth account | Block credential field → **Connect** → Authorize with provider |
+| Manage credentials | Settings → **Credentials** |
+| Remove credential | Settings → **Credentials** → Delete credential |
+
--- a/apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/editor/components/sub-block/sub-block.tsx
+++ b/apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/editor/components/sub-block/sub-block.tsx
@@ -284,22 +284,37 @@ const renderLabel = (
          </>
        )}
        {showCanonicalToggle && (
-          <button
-            type='button'
-            className='flex h-[12px] w-[12px] flex-shrink-0 items-center justify-center bg-transparent p-0 disabled:cursor-not-allowed disabled:opacity-50'
-            onClick={canonicalToggle?.onToggle}
-            disabled={canonicalToggleDisabledResolved}
-            aria-label={canonicalToggle?.mode === 'advanced' ? 'Use selector' : 'Enter manual ID'}
-          >
-            <ArrowLeftRight
-              className={cn(
-                '!h-[12px] !w-[12px]',
-                canonicalToggle?.mode === 'advanced'
-                  ? 'text-[var(--text-primary)]'
-                  : 'text-[var(--text-secondary)]'
-              )}
-            />
-          </button>
+          <Tooltip.Root>
+            <Tooltip.Trigger asChild>
+              <button
+                type='button'
+                className='flex h-[12px] w-[12px] flex-shrink-0 items-center justify-center bg-transparent p-0 disabled:cursor-not-allowed disabled:opacity-50'
+                onClick={canonicalToggle?.onToggle}
+                disabled={canonicalToggleDisabledResolved}
+                aria-label={
+                  canonicalToggle?.mode === 'advanced'
+                    ? 'Switch to selector'
+                    : 'Switch to manual ID'
+                }
+              >
+                <ArrowLeftRight
+                  className={cn(
+                    '!h-[12px] !w-[12px]',
+                    canonicalToggle?.mode === 'advanced'
+                      ? 'text-[var(--text-primary)]'
+                      : 'text-[var(--text-secondary)]'
+                  )}
+                />
+              </button>
+            </Tooltip.Trigger>
+            <Tooltip.Content side='top'>
+              <p>
+                {canonicalToggle?.mode === 'advanced'
+                  ? 'Switch to selector'
+                  : 'Switch to manual ID'}
+              </p>
+            </Tooltip.Content>
+          </Tooltip.Root>
        )}
      </div>
    </div>
--- a/apps/sim/app/workspace/[workspaceId]/w/[workflowId]/hooks/use-canvas-context-menu.ts
+++ b/apps/sim/app/workspace/[workspaceId]/w/[workflowId]/hooks/use-canvas-context-menu.ts
@@ -13,7 +13,11 @@ interface UseCanvasContextMenuProps {

 /**
 * Hook for managing workflow canvas context menus.
- * Handles right-click events, menu state, click-outside detection, and block info extraction.
+ *
+ * Handles right-click events on nodes, pane, and selections with proper multi-select behavior.
+ *
+ * @param props - Hook configuration
+ * @returns Context menu state and handlers
 */
 export function useCanvasContextMenu({ blocks, getNodes, setNodes }: UseCanvasContextMenuProps) {
  const [activeMenu, setActiveMenu] = useState<MenuType>(null)
@@ -46,19 +50,29 @@ export function useCanvasContextMenu({ blocks, getNodes, setNodes }: UseCanvasCo
      event.stopPropagation()

      const isMultiSelect = event.shiftKey || event.metaKey || event.ctrlKey
-      setNodes((nodes) =>
-        nodes.map((n) => ({
-          ...n,
-          selected: isMultiSelect ? (n.id === node.id ? true : n.selected) : n.id === node.id,
-        }))
-      )
+      const currentSelectedNodes = getNodes().filter((n) => n.selected)
+      const isClickedNodeSelected = currentSelectedNodes.some((n) => n.id === node.id)

-      const selectedNodes = getNodes().filter((n) => n.selected)
-      const nodesToUse = isMultiSelect
-        ? selectedNodes.some((n) => n.id === node.id)
-          ? selectedNodes
-          : [...selectedNodes, node]
-        : [node]
+      let nodesToUse: Node[]
+      if (isClickedNodeSelected) {
+        nodesToUse = currentSelectedNodes
+      } else if (isMultiSelect) {
+        nodesToUse = [...currentSelectedNodes, node]
+        setNodes((nodes) =>
+          nodes.map((n) => ({
+            ...n,
+            selected: n.id === node.id ? true : n.selected,
+          }))
+        )
+      } else {
+        nodesToUse = [node]
+        setNodes((nodes) =>
+          nodes.map((n) => ({
+            ...n,
+            selected: n.id === node.id,
+          }))
+        )
+      }

      setPosition({ x: event.clientX, y: event.clientY })
      setSelectedBlocks(nodesToBlockInfos(nodesToUse))
--- a/apps/sim/app/workspace/[workspaceId]/w/components/sidebar/hooks/use-context-menu.ts
+++ b/apps/sim/app/workspace/[workspaceId]/w/components/sidebar/hooks/use-context-menu.ts
@@ -27,18 +27,13 @@ export function useContextMenu({ onContextMenu }: UseContextMenuProps = {}) {
  const [isOpen, setIsOpen] = useState(false)
  const [position, setPosition] = useState<ContextMenuPosition>({ x: 0, y: 0 })
  const menuRef = useRef<HTMLDivElement>(null)
-  // Used to prevent click-outside dismissal when trigger is clicked
  const dismissPreventedRef = useRef(false)

-  /**
-   * Handle right-click event
-   */
  const handleContextMenu = useCallback(
    (e: React.MouseEvent) => {
      e.preventDefault()
      e.stopPropagation()

-      // Calculate position relative to viewport
      const x = e.clientX
      const y = e.clientY

@@ -50,17 +45,10 @@ export function useContextMenu({ onContextMenu }: UseContextMenuProps = {}) {
    [onContextMenu]
  )

-  /**
-   * Close the context menu
-   */
  const closeMenu = useCallback(() => {
    setIsOpen(false)
  }, [])

-  /**
-   * Prevent the next click-outside from dismissing the menu.
-   * Call this on pointerdown of a toggle trigger to allow proper toggle behavior.
-   */
  const preventDismiss = useCallback(() => {
    dismissPreventedRef.current = true
  }, [])
@@ -72,7 +60,6 @@ export function useContextMenu({ onContextMenu }: UseContextMenuProps = {}) {
    if (!isOpen) return

    const handleClickOutside = (e: MouseEvent) => {
-      // Check if dismissal was prevented (e.g., by toggle trigger's pointerdown)
      if (dismissPreventedRef.current) {
        dismissPreventedRef.current = false
        return
@@ -82,7 +69,6 @@ export function useContextMenu({ onContextMenu }: UseContextMenuProps = {}) {
      }
    }

-    // Small delay to prevent immediate close from the same click that opened the menu
    const timeoutId = setTimeout(() => {
      document.addEventListener('click', handleClickOutside)
    }, 0)
--- a/apps/sim/executor/handlers/evaluator/evaluator-handler.ts
+++ b/apps/sim/executor/handlers/evaluator/evaluator-handler.ts
@@ -4,9 +4,9 @@ import { createLogger } from '@sim/logger'
 import { eq } from 'drizzle-orm'
 import { refreshTokenIfNeeded } from '@/app/api/auth/oauth/utils'
 import type { BlockOutput } from '@/blocks/types'
-import { BlockType, DEFAULTS, EVALUATOR, HTTP } from '@/executor/constants'
+import { BlockType, DEFAULTS, EVALUATOR } from '@/executor/constants'
 import type { BlockHandler, ExecutionContext } from '@/executor/types'
-import { buildAPIUrl, extractAPIErrorMessage } from '@/executor/utils/http'
+import { buildAPIUrl, buildAuthHeaders, extractAPIErrorMessage } from '@/executor/utils/http'
 import { isJSONString, parseJSON, stringifyJSON } from '@/executor/utils/json'
 import { validateModelProvider } from '@/executor/utils/permission-check'
 import { calculateCost, getProviderFromModel } from '@/providers/utils'
@@ -143,9 +143,7 @@ export class EvaluatorBlockHandler implements BlockHandler {

      const response = await fetch(url.toString(), {
        method: 'POST',
-        headers: {
-          'Content-Type': HTTP.CONTENT_TYPE.JSON,
-        },
+        headers: await buildAuthHeaders(),
        body: stringifyJSON(providerRequest),
      })

--- a/apps/sim/executor/handlers/router/router-handler.ts
+++ b/apps/sim/executor/handlers/router/router-handler.ts
@@ -9,12 +9,12 @@ import type { BlockOutput } from '@/blocks/types'
 import {
  BlockType,
  DEFAULTS,
-  HTTP,
  isAgentBlockType,
  isRouterV2BlockType,
  ROUTER,
 } from '@/executor/constants'
 import type { BlockHandler, ExecutionContext } from '@/executor/types'
+import { buildAuthHeaders } from '@/executor/utils/http'
 import { validateModelProvider } from '@/executor/utils/permission-check'
 import { calculateCost, getProviderFromModel } from '@/providers/utils'
 import type { SerializedBlock } from '@/serializer/types'
@@ -118,9 +118,7 @@ export class RouterBlockHandler implements BlockHandler {

      const response = await fetch(url.toString(), {
        method: 'POST',
-        headers: {
-          'Content-Type': HTTP.CONTENT_TYPE.JSON,
-        },
+        headers: await buildAuthHeaders(),
        body: JSON.stringify(providerRequest),
      })

@@ -277,9 +275,7 @@ export class RouterBlockHandler implements BlockHandler {

      const response = await fetch(url.toString(), {
        method: 'POST',
-        headers: {
-          'Content-Type': HTTP.CONTENT_TYPE.JSON,
-        },
+        headers: await buildAuthHeaders(),
        body: JSON.stringify(providerRequest),
      })

--- a/apps/sim/lib/copilot/tools/server/workflow/edit-workflow.ts
+++ b/apps/sim/lib/copilot/tools/server/workflow/edit-workflow.ts
@@ -11,9 +11,10 @@ import { extractAndPersistCustomTools } from '@/lib/workflows/persistence/custom
 import { loadWorkflowFromNormalizedTables } from '@/lib/workflows/persistence/utils'
 import { isValidKey } from '@/lib/workflows/sanitization/key-validation'
 import { validateWorkflowState } from '@/lib/workflows/sanitization/validation'
+import { buildCanonicalIndex, isCanonicalPair } from '@/lib/workflows/subblocks/visibility'
 import { TriggerUtils } from '@/lib/workflows/triggers/triggers'
 import { getAllBlocks, getBlock } from '@/blocks/registry'
-import type { SubBlockConfig } from '@/blocks/types'
+import type { BlockConfig, SubBlockConfig } from '@/blocks/types'
 import { EDGE, normalizeName, RESERVED_BLOCK_NAMES } from '@/executor/constants'
 import { getUserPermissionConfig } from '@/executor/utils/permission-check'
 import { generateLoopBlocks, generateParallelBlocks } from '@/stores/workflows/workflow/utils'
@@ -667,11 +668,47 @@ function createBlockFromParams(
        }
      }
    })
+
+    if (validatedInputs) {
+      updateCanonicalModesForInputs(blockState, Object.keys(validatedInputs), blockConfig)
+    }
  }

  return blockState
 }

+function updateCanonicalModesForInputs(
+  block: { data?: { canonicalModes?: Record<string, 'basic' | 'advanced'> } },
+  inputKeys: string[],
+  blockConfig: BlockConfig
+): void {
+  if (!blockConfig.subBlocks?.length) return
+
+  const canonicalIndex = buildCanonicalIndex(blockConfig.subBlocks)
+  const canonicalModeUpdates: Record<string, 'basic' | 'advanced'> = {}
+
+  for (const inputKey of inputKeys) {
+    const canonicalId = canonicalIndex.canonicalIdBySubBlockId[inputKey]
+    if (!canonicalId) continue
+
+    const group = canonicalIndex.groupsById[canonicalId]
+    if (!group || !isCanonicalPair(group)) continue
+
+    const isAdvanced = group.advancedIds.includes(inputKey)
+    const existingMode = canonicalModeUpdates[canonicalId]
+
+    if (!existingMode || isAdvanced) {
+      canonicalModeUpdates[canonicalId] = isAdvanced ? 'advanced' : 'basic'
+    }
+  }
+
+  if (Object.keys(canonicalModeUpdates).length > 0) {
+    if (!block.data) block.data = {}
+    if (!block.data.canonicalModes) block.data.canonicalModes = {}
+    Object.assign(block.data.canonicalModes, canonicalModeUpdates)
+  }
+}
+
 /**
 * Normalize tools array by adding back fields that were sanitized for training
 */
@@ -1654,6 +1691,15 @@ function applyOperationsToWorkflowState(
              block.data.collection = params.inputs.collection
            }
          }
+
+          const editBlockConfig = getBlock(block.type)
+          if (editBlockConfig) {
+            updateCanonicalModesForInputs(
+              block,
+              Object.keys(validationResult.validInputs),
+              editBlockConfig
+            )
+          }
        }

        // Update basic properties
@@ -2256,6 +2302,15 @@ function applyOperationsToWorkflowState(
                existingBlock.subBlocks[key].value = sanitizedValue
              }
            })
+
+            const existingBlockConfig = getBlock(existingBlock.type)
+            if (existingBlockConfig) {
+              updateCanonicalModesForInputs(
+                existingBlock,
+                Object.keys(validationResult.validInputs),
+                existingBlockConfig
+              )
+            }
          }
        } else {
          // Special container types (loop, parallel) are not in the block registry but are valid
--- a/apps/sim/package.json
+++ b/apps/sim/package.json
@@ -24,7 +24,7 @@
  },
  "dependencies": {
    "@a2a-js/sdk": "0.3.7",
-    "@anthropic-ai/sdk": "^0.39.0",
+    "@anthropic-ai/sdk": "0.71.2",
    "@aws-sdk/client-bedrock-runtime": "3.940.0",
    "@aws-sdk/client-dynamodb": "3.940.0",
    "@aws-sdk/client-rds-data": "3.940.0",
--- a/apps/sim/providers/anthropic/index.ts
+++ b/apps/sim/providers/anthropic/index.ts
@@ -1,4 +1,5 @@
 import Anthropic from '@anthropic-ai/sdk'
+import { transformJSONSchema } from '@anthropic-ai/sdk/lib/transform-json-schema'
 import { createLogger } from '@sim/logger'
 import type { StreamingExecution } from '@/executor/types'
 import { MAX_TOOL_ITERATIONS } from '@/providers'
@@ -185,13 +186,10 @@ export const anthropicProvider: ProviderConfig = {
      const schema = request.responseFormat.schema || request.responseFormat

      if (useNativeStructuredOutputs) {
-        const schemaWithConstraints = {
-          ...schema,
-          additionalProperties: false,
-        }
+        const transformedSchema = transformJSONSchema(schema)
        payload.output_format = {
          type: 'json_schema',
-          schema: schemaWithConstraints,
+          schema: transformedSchema,
        }
        logger.info(`Using native structured outputs for model: ${modelId}`)
      } else {
--- a/bun.lock
+++ b/bun.lock
@@ -1,6 +1,5 @@
 {
  "lockfileVersion": 1,
-  "configVersion": 0,
  "workspaces": {
    "": {
      "name": "simstudio",
@@ -55,7 +54,7 @@
      "version": "0.1.0",
      "dependencies": {
        "@a2a-js/sdk": "0.3.7",
-        "@anthropic-ai/sdk": "^0.39.0",
+        "@anthropic-ai/sdk": "0.71.2",
        "@aws-sdk/client-bedrock-runtime": "3.940.0",
        "@aws-sdk/client-dynamodb": "3.940.0",
        "@aws-sdk/client-rds-data": "3.940.0",
@@ -363,7 +362,7 @@

    "@ampproject/remapping": ["@ampproject/remapping@2.3.0", "", { "dependencies": { "@jridgewell/gen-mapping": "^0.3.5", "@jridgewell/trace-mapping": "^0.3.24" } }, "sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw=="],

-    "@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.39.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" } }, "sha512-eMyDIPRZbt1CCLErRCi3exlAvNkBtRe+kW5vvJyef93PmNr/clstYgHhtvmkxN82nlKgzyGPCyGxrm0JQ1ZIdg=="],
+    "@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.71.2", "", { "dependencies": { "json-schema-to-ts": "^3.1.1" }, "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["zod"], "bin": { "anthropic-ai-sdk": "bin/cli" } }, "sha512-TGNDEUuEstk/DKu0/TflXAEt+p+p/WhTlFzEnoosvbaDU2LTjm42igSdlL0VijrKpWejtOKxX0b8A7uc+XiSAQ=="],

    "@ark/schema": ["@ark/schema@0.56.0", "", { "dependencies": { "@ark/util": "0.56.0" } }, "sha512-ECg3hox/6Z/nLajxXqNhgPtNdHWC9zNsDyskwO28WinoFEnWow4IsERNz9AnXRhTZJnYIlAJ4uGn3nlLk65vZA=="],

@@ -547,6 +546,8 @@

    "@babel/plugin-transform-react-jsx-source": ["@babel/plugin-transform-react-jsx-source@7.27.1", "", { "dependencies": { "@babel/helper-plugin-utils": "^7.27.1" }, "peerDependencies": { "@babel/core": "^7.0.0-0" } }, "sha512-zbwoTsBruTeKB9hSq73ha66iFeJHuaFkUbwvqElnygoNbj/jHRsSeokowZFN3CZ64IvEqcmmkVe89OPXc7ldAw=="],

+    "@babel/runtime": ["@babel/runtime@7.28.6", "", {}, "sha512-05WQkdpL9COIMz4LjTxGpPNCdlpyimKppYNoJ5Di5EUObifl8t4tuLuUBBZEpoLYOmfvIWrsp9fCl0HoPRVTdA=="],
+
    "@babel/template": ["@babel/template@7.28.6", "", { "dependencies": { "@babel/code-frame": "^7.28.6", "@babel/parser": "^7.28.6", "@babel/types": "^7.28.6" } }, "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ=="],

    "@babel/traverse": ["@babel/traverse@7.28.6", "", { "dependencies": { "@babel/code-frame": "^7.28.6", "@babel/generator": "^7.28.6", "@babel/helper-globals": "^7.28.0", "@babel/parser": "^7.28.6", "@babel/template": "^7.28.6", "@babel/types": "^7.28.6", "debug": "^4.3.1" } }, "sha512-fgWX62k02qtjqdSNTAGxmKYY/7FSL9WAS1o2Hu5+I5m9T0yxZzr4cnrfXQ/MX0rIifthCSs6FKTlzYbJcPtMNg=="],
@@ -2443,6 +2444,8 @@

    "json-schema": ["json-schema@0.4.0", "", {}, "sha512-es94M3nTIfsEPisRafak+HDLfHXnKBhV3vU5eqPcS3flIWqcxJWgXHXiey3YrpaNsanY5ei1VoYEbOzijuq9BA=="],

+    "json-schema-to-ts": ["json-schema-to-ts@3.1.1", "", { "dependencies": { "@babel/runtime": "^7.18.3", "ts-algebra": "^2.0.0" } }, "sha512-+DWg8jCJG2TEnpy7kOm/7/AxaYoaRbjVB4LFZLySZlWn8exGs3A4OLJR966cVvU26N7X9TWxl+Jsw7dzAqKT6g=="],
+
    "json-schema-traverse": ["json-schema-traverse@0.4.1", "", {}, "sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg=="],

    "json5": ["json5@2.2.3", "", { "bin": { "json5": "lib/cli.js" } }, "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg=="],
@@ -3387,6 +3390,8 @@

    "trough": ["trough@2.2.0", "", {}, "sha512-tmMpK00BjZiUyVyvrBK7knerNgmgvcV/KLVyuma/SC+TQN167GrMRciANTz09+k3zW8L8t60jWO1GpfkZdjTaw=="],

+    "ts-algebra": ["ts-algebra@2.0.0", "", {}, "sha512-FPAhNPFMrkwz76P7cdjdmiShwMynZYN6SgOujD1urY4oNm80Ou9oMdmbR45LotcKOXoy7wSmHkRFE6Mxbrhefw=="],
+
    "ts-interface-checker": ["ts-interface-checker@0.1.13", "", {}, "sha512-Y/arvbn+rrz3JCKl9C4kVNfTfSm2/mEp5FSz5EsZSANGPSlQrpRI5M4PKF+mJnE52jOO90PnPSc3Ur3bTQw0gA=="],

    "tsafe": ["tsafe@1.8.12", "", {}, "sha512-nFRqW0ttu/2o6XTXsHiVZWJBCOaxhVqZLg7dgs3coZNsCMPXPfwz+zPHAQA+70fNnVJLAPg1EgGIqK9Q84tvAw=="],
@@ -3593,10 +3598,6 @@

    "zwitch": ["zwitch@2.0.4", "", {}, "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A=="],

-    "@anthropic-ai/sdk/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],
-
-    "@anthropic-ai/sdk/node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],
-
    "@asamuzakjp/css-color/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],

    "@aws-crypto/crc32/@aws-sdk/types": ["@aws-sdk/types@3.969.0", "", { "dependencies": { "@smithy/types": "^4.12.0", "tslib": "^2.6.2" } }, "sha512-7IIzM5TdiXn+VtgPdVLjmE6uUBUtnga0f4RiSEI1WW10RPuNvZ9U+pL3SwDiRDAdoGrOF9tSLJOFZmfuwYuVYQ=="],
@@ -3713,6 +3714,8 @@

    "@browserbasehq/sdk/node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],

+    "@browserbasehq/stagehand/@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.39.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" } }, "sha512-eMyDIPRZbt1CCLErRCi3exlAvNkBtRe+kW5vvJyef93PmNr/clstYgHhtvmkxN82nlKgzyGPCyGxrm0JQ1ZIdg=="],
+
    "@cerebras/cerebras_cloud_sdk/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],

    "@cerebras/cerebras_cloud_sdk/node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],
@@ -4215,10 +4218,6 @@

    "xml2js/xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="],

-    "@anthropic-ai/sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],
-
-    "@anthropic-ai/sdk/node-fetch/whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="],
-
    "@aws-crypto/sha1-browser/@smithy/util-utf8/@smithy/util-buffer-from": ["@smithy/util-buffer-from@2.2.0", "", { "dependencies": { "@smithy/is-array-buffer": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-IJdWBbTcMQ6DA0gdNhh/BwrLkDR+ADW5Kr1aZmd4k3DIF6ezMV4R2NIAmT08wQJ3yUK82thHWmC/TnK/wpMMIA=="],

    "@aws-crypto/sha256-browser/@smithy/util-utf8/@smithy/util-buffer-from": ["@smithy/util-buffer-from@2.2.0", "", { "dependencies": { "@smithy/is-array-buffer": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-IJdWBbTcMQ6DA0gdNhh/BwrLkDR+ADW5Kr1aZmd4k3DIF6ezMV4R2NIAmT08wQJ3yUK82thHWmC/TnK/wpMMIA=="],
@@ -4275,6 +4274,10 @@

    "@browserbasehq/sdk/node-fetch/whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="],

+    "@browserbasehq/stagehand/@anthropic-ai/sdk/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],
+
+    "@browserbasehq/stagehand/@anthropic-ai/sdk/node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],
+
    "@cerebras/cerebras_cloud_sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],

    "@cerebras/cerebras_cloud_sdk/node-fetch/whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="],
@@ -4685,10 +4688,6 @@

    "vite/esbuild/@esbuild/win32-x64": ["@esbuild/win32-x64@0.27.2", "", { "os": "win32", "cpu": "x64" }, "sha512-sRdU18mcKf7F+YgheI/zGf5alZatMUTKj/jNS6l744f9u3WFu4v7twcUI9vu4mknF4Y9aDlblIie0IM+5xxaqQ=="],

-    "@anthropic-ai/sdk/node-fetch/whatwg-url/tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],
-
-    "@anthropic-ai/sdk/node-fetch/whatwg-url/webidl-conversions": ["webidl-conversions@3.0.1", "", {}, "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="],
-
    "@aws-crypto/sha1-browser/@smithy/util-utf8/@smithy/util-buffer-from/@smithy/is-array-buffer": ["@smithy/is-array-buffer@2.2.0", "", { "dependencies": { "tslib": "^2.6.2" } }, "sha512-GGP3O9QFD24uGeAXYUjwSTXARoqpZykHadOmA8G5vfJPK0/DC67qa//0qvqrJzL1xc8WQWX7/yc7fwudjPHPhA=="],

    "@aws-crypto/sha256-browser/@smithy/util-utf8/@smithy/util-buffer-from/@smithy/is-array-buffer": ["@smithy/is-array-buffer@2.2.0", "", { "dependencies": { "tslib": "^2.6.2" } }, "sha512-GGP3O9QFD24uGeAXYUjwSTXARoqpZykHadOmA8G5vfJPK0/DC67qa//0qvqrJzL1xc8WQWX7/yc7fwudjPHPhA=="],
@@ -4737,6 +4736,10 @@

    "@browserbasehq/sdk/node-fetch/whatwg-url/webidl-conversions": ["webidl-conversions@3.0.1", "", {}, "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="],

+    "@browserbasehq/stagehand/@anthropic-ai/sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],
+
+    "@browserbasehq/stagehand/@anthropic-ai/sdk/node-fetch/whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="],
+
    "@cerebras/cerebras_cloud_sdk/node-fetch/whatwg-url/tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],

    "@cerebras/cerebras_cloud_sdk/node-fetch/whatwg-url/webidl-conversions": ["webidl-conversions@3.0.1", "", {}, "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="],
@@ -4829,6 +4832,10 @@

    "@aws-sdk/client-sqs/@aws-sdk/credential-provider-node/@aws-sdk/credential-provider-sso/@aws-sdk/token-providers/@aws-sdk/nested-clients": ["@aws-sdk/nested-clients@3.947.0", "", { "dependencies": { "@aws-crypto/sha256-browser": "5.2.0", "@aws-crypto/sha256-js": "5.2.0", "@aws-sdk/core": "3.947.0", "@aws-sdk/middleware-host-header": "3.936.0", "@aws-sdk/middleware-logger": "3.936.0", "@aws-sdk/middleware-recursion-detection": "3.936.0", "@aws-sdk/middleware-user-agent": "3.947.0", "@aws-sdk/region-config-resolver": "3.936.0", "@aws-sdk/types": "3.936.0", "@aws-sdk/util-endpoints": "3.936.0", "@aws-sdk/util-user-agent-browser": "3.936.0", "@aws-sdk/util-user-agent-node": "3.947.0", "@smithy/config-resolver": "^4.4.3", "@smithy/core": "^3.18.7", "@smithy/fetch-http-handler": "^5.3.6", "@smithy/hash-node": "^4.2.5", "@smithy/invalid-dependency": "^4.2.5", "@smithy/middleware-content-length": "^4.2.5", "@smithy/middleware-endpoint": "^4.3.14", "@smithy/middleware-retry": "^4.4.14", "@smithy/middleware-serde": "^4.2.6", "@smithy/middleware-stack": "^4.2.5", "@smithy/node-config-provider": "^4.3.5", "@smithy/node-http-handler": "^4.4.5", "@smithy/protocol-http": "^5.3.5", "@smithy/smithy-client": "^4.9.10", "@smithy/types": "^4.9.0", "@smithy/url-parser": "^4.2.5", "@smithy/util-base64": "^4.3.0", "@smithy/util-body-length-browser": "^4.2.0", "@smithy/util-body-length-node": "^4.2.1", "@smithy/util-defaults-mode-browser": "^4.3.13", "@smithy/util-defaults-mode-node": "^4.2.16", "@smithy/util-endpoints": "^3.2.5", "@smithy/util-middleware": "^4.2.5", "@smithy/util-retry": "^4.2.5", "@smithy/util-utf8": "^4.2.0", "tslib": "^2.6.2" } }, "sha512-DjRJEYNnHUTu9kGPPQDTSXquwSEd6myKR4ssI4FaYLFhdT3ldWpj73yYt807H3tdmhS7vPmdVqchSJnjurUQAw=="],

+    "@browserbasehq/stagehand/@anthropic-ai/sdk/node-fetch/whatwg-url/tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],
+
+    "@browserbasehq/stagehand/@anthropic-ai/sdk/node-fetch/whatwg-url/webidl-conversions": ["webidl-conversions@3.0.1", "", {}, "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="],
+
    "@trigger.dev/core/socket.io/engine.io/@types/node/undici-types": ["undici-types@7.10.0", "", {}, "sha512-t5Fy/nfn+14LuOc2KNYg75vZqClpAiqscVvMygNnlsHBFpSXdJaYtXMcdNLpl/Qvc3P2cB3s6lOV51nqsFq4ag=="],

    "lint-staged/listr2/cli-truncate/string-width/strip-ansi": ["strip-ansi@7.1.2", "", { "dependencies": { "ansi-regex": "^6.0.1" } }, "sha512-gmBGslpoQJtgnMAvOVqGZpEz9dyoKTCzy2nfz/n8aIFhN/jCE/rCmcxabB6jOOHV+0WNnylOxaxBQPSvcWklhA=="],
--- a/packages/python-sdk/.gitignore
+++ b/packages/python-sdk/.gitignore
@@ -81,4 +81,7 @@ Thumbs.db
 # mypy
 .mypy_cache/
 .dmypy.json
-dmypy.json 
+dmypy.json
+
+# uv
+uv.lock 
--- a/packages/python-sdk/README.md
+++ b/packages/python-sdk/README.md
@@ -43,24 +43,30 @@ SimStudioClient(api_key: str, base_url: str = "https://sim.ai")

 #### Methods

-##### execute_workflow(workflow_id, input_data=None, timeout=30.0)
+##### execute_workflow(workflow_id, input=None, *, timeout=30.0, stream=None, selected_outputs=None, async_execution=None)

 Execute a workflow with optional input data.

 ```python
-result = client.execute_workflow(
-    "workflow-id",
-    input_data={"message": "Hello, world!"},
-    timeout=30.0  # 30 seconds
-)
+# With dict input (spread at root level of request body)
+result = client.execute_workflow("workflow-id", {"message": "Hello, world!"})
+
+# With primitive input (wrapped as { input: value })
+result = client.execute_workflow("workflow-id", "NVDA")
+
+# With options (keyword-only arguments)
+result = client.execute_workflow("workflow-id", {"message": "Hello"}, timeout=60.0)
 ```

 **Parameters:**
 - `workflow_id` (str): The ID of the workflow to execute
- `input_data` (dict, optional): Input data to pass to the workflow. File objects are automatically converted to base64.
- `timeout` (float): Timeout in seconds (default: 30.0)
+- `input` (any, optional): Input data to pass to the workflow. Dicts are spread at the root level, primitives/lists are wrapped in `{ input: value }`. File objects are automatically converted to base64.
+- `timeout` (float, keyword-only): Timeout in seconds (default: 30.0)
+- `stream` (bool, keyword-only): Enable streaming responses
+- `selected_outputs` (list, keyword-only): Block outputs to stream (e.g., `["agent1.content"]`)
+- `async_execution` (bool, keyword-only): Execute asynchronously and return execution ID

-**Returns:** `WorkflowExecutionResult`
+**Returns:** `WorkflowExecutionResult` or `AsyncExecutionResult`

 ##### get_workflow_status(workflow_id)

@@ -92,24 +98,89 @@ if is_ready:

 **Returns:** `bool`

-##### execute_workflow_sync(workflow_id, input_data=None, timeout=30.0)
+##### execute_workflow_sync(workflow_id, input=None, *, timeout=30.0, stream=None, selected_outputs=None)

-Execute a workflow and poll for completion (useful for long-running workflows).
+Execute a workflow synchronously (ensures non-async mode).

 ```python
-result = client.execute_workflow_sync(
+result = client.execute_workflow_sync("workflow-id", {"data": "some input"}, timeout=60.0)
+```
+
+**Parameters:**
+- `workflow_id` (str): The ID of the workflow to execute
+- `input` (any, optional): Input data to pass to the workflow
+- `timeout` (float, keyword-only): Timeout in seconds (default: 30.0)
+- `stream` (bool, keyword-only): Enable streaming responses
+- `selected_outputs` (list, keyword-only): Block outputs to stream (e.g., `["agent1.content"]`)
+
+**Returns:** `WorkflowExecutionResult`
+
+##### get_job_status(task_id)
+
+Get the status of an async job.
+
+```python
+status = client.get_job_status("task-id-from-async-execution")
+print("Job status:", status)
+```
+
+**Parameters:**
+- `task_id` (str): The task ID returned from async execution
+
+**Returns:** `dict`
+
+##### execute_with_retry(workflow_id, input=None, *, timeout=30.0, stream=None, selected_outputs=None, async_execution=None, max_retries=3, initial_delay=1.0, max_delay=30.0, backoff_multiplier=2.0)
+
+Execute a workflow with automatic retry on rate limit errors.
+
+```python
+result = client.execute_with_retry(
    "workflow-id",
-    input_data={"data": "some input"},
-    timeout=60.0
+    {"message": "Hello"},
+    timeout=30.0,
+    max_retries=3,
+    initial_delay=1.0,
+    max_delay=30.0,
+    backoff_multiplier=2.0
 )
 ```

 **Parameters:**
 - `workflow_id` (str): The ID of the workflow to execute
- `input_data` (dict, optional): Input data to pass to the workflow
- `timeout` (float): Timeout for the initial request in seconds
+- `input` (any, optional): Input data to pass to the workflow
+- `timeout` (float, keyword-only): Timeout in seconds (default: 30.0)
+- `stream` (bool, keyword-only): Enable streaming responses
+- `selected_outputs` (list, keyword-only): Block outputs to stream
+- `async_execution` (bool, keyword-only): Execute asynchronously
+- `max_retries` (int, keyword-only): Maximum retry attempts (default: 3)
+- `initial_delay` (float, keyword-only): Initial delay in seconds (default: 1.0)
+- `max_delay` (float, keyword-only): Maximum delay in seconds (default: 30.0)
+- `backoff_multiplier` (float, keyword-only): Backoff multiplier (default: 2.0)

-**Returns:** `WorkflowExecutionResult`
+**Returns:** `WorkflowExecutionResult` or `AsyncExecutionResult`
+
+##### get_rate_limit_info()
+
+Get current rate limit information from the last API response.
+
+```python
+rate_info = client.get_rate_limit_info()
+if rate_info:
+    print("Remaining requests:", rate_info.remaining)
+```
+
+**Returns:** `RateLimitInfo` or `None`
+
+##### get_usage_limits()
+
+Get current usage limits and quota information.
+
+```python
+limits = client.get_usage_limits()
+print("Current usage:", limits.usage)
+```
+
+**Returns:** `UsageLimits`

 ##### set_api_key(api_key)

@@ -171,6 +242,39 @@ class SimStudioError(Exception):
        self.status = status
 ```

+### AsyncExecutionResult
+
+```python
+@dataclass
+class AsyncExecutionResult:
+    success: bool
+    task_id: str
+    status: str  # 'queued'
+    created_at: str
+    links: Dict[str, str]
+```
+
+### RateLimitInfo
+
+```python
+@dataclass
+class RateLimitInfo:
+    limit: int
+    remaining: int
+    reset: int
+    retry_after: Optional[int] = None
+```
+
+### UsageLimits
+
+```python
+@dataclass
+class UsageLimits:
+    success: bool
+    rate_limit: Dict[str, Any]
+    usage: Dict[str, Any]
+```
+
 ## Examples

 ### Basic Workflow Execution
@@ -191,7 +295,7 @@ def run_workflow():
        # Execute the workflow
        result = client.execute_workflow(
            "my-workflow-id",
-            input_data={
+            {
                "message": "Process this data",
                "user_id": "12345"
            }
@@ -298,7 +402,7 @@ client = SimStudioClient(api_key=os.getenv("SIM_API_KEY"))
 with open('document.pdf', 'rb') as f:
    result = client.execute_workflow(
        'workflow-id',
-        input_data={
+        {
            'documents': [f],  # Must match your workflow's "files" field name
            'instructions': 'Analyze this document'
        }
@@ -308,7 +412,7 @@ with open('document.pdf', 'rb') as f:
 with open('doc1.pdf', 'rb') as f1, open('doc2.pdf', 'rb') as f2:
    result = client.execute_workflow(
        'workflow-id',
-        input_data={
+        {
            'attachments': [f1, f2],  # Must match your workflow's "files" field name
            'query': 'Compare these documents'
        }
@@ -327,14 +431,14 @@ def execute_workflows_batch(workflow_data_pairs):
    """Execute multiple workflows with different input data."""
    results = []

-    for workflow_id, input_data in workflow_data_pairs:
+    for workflow_id, workflow_input in workflow_data_pairs:
        try:
            # Validate workflow before execution
            if not client.validate_workflow(workflow_id):
                print(f"Skipping {workflow_id}: not deployed")
                continue

-            result = client.execute_workflow(workflow_id, input_data)
+            result = client.execute_workflow(workflow_id, workflow_input)
            results.append({
                "workflow_id": workflow_id,
                "success": result.success,
--- a/packages/python-sdk/pyproject.toml
+++ b/packages/python-sdk/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "simstudio-sdk"
-version = "0.1.1"
+version = "0.1.2"
 authors = [
    {name = "Sim", email = "help@sim.ai"},
 ]
--- a/packages/python-sdk/simstudio/init.py
+++ b/packages/python-sdk/simstudio/init.py
@@ -13,7 +13,7 @@ import os
 import requests


-__version__ = "0.1.0"
+__version__ = "0.1.2"
 __all__ = [
    "SimStudioClient",
    "SimStudioError",
@@ -64,15 +64,6 @@ class RateLimitInfo:
    retry_after: Optional[int] = None


-@dataclass
-class RateLimitStatus:
-    """Rate limit status for sync/async requests."""
-    is_limited: bool
-    limit: int
-    remaining: int
-    reset_at: str
-
-
@dataclass
 class UsageLimits:
    """Usage limits and quota information."""
@@ -115,7 +106,6 @@ class SimStudioClient:
        Recursively processes nested dicts and lists.
        """
        import base64
-        import io

        # Check if this is a file-like object
        if hasattr(value, 'read') and callable(value.read):
@@ -159,7 +149,8 @@ class SimStudioClient:
    def execute_workflow(
        self,
        workflow_id: str,
-        input_data: Optional[Dict[str, Any]] = None,
+        input: Optional[Any] = None,
+        *,
        timeout: float = 30.0,
        stream: Optional[bool] = None,
        selected_outputs: Optional[list] = None,
@@ -169,11 +160,13 @@ class SimStudioClient:
        Execute a workflow with optional input data.
        If async_execution is True, returns immediately with a task ID.

-        File objects in input_data will be automatically detected and converted to base64.
+        File objects in input will be automatically detected and converted to base64.

        Args:
            workflow_id: The ID of the workflow to execute
-            input_data: Input data to pass to the workflow (can include file-like objects)
+            input: Input data to pass to the workflow. Can be a dict (spread at root level),
+                   primitive value (string, number, bool), or list (wrapped in 'input' field).
+                   File-like objects within dicts are automatically converted to base64.
            timeout: Timeout in seconds (default: 30.0)
            stream: Enable streaming responses (default: None)
            selected_outputs: Block outputs to stream (e.g., ["agent1.content"])
@@ -193,8 +186,15 @@ class SimStudioClient:
            headers['X-Execution-Mode'] = 'async'

        try:
-            # Build JSON body - spread input at root level, then add API control parameters
-            body = input_data.copy() if input_data is not None else {}
+            # Build JSON body - spread dict inputs at root level, wrap primitives/lists in 'input' field
+            body = {}
+            if input is not None:
+                if isinstance(input, dict):
+                    # Dict input: spread at root level (matches curl/API behavior)
+                    body = input.copy()
+                else:
+                    # Primitive or list input: wrap in 'input' field
+                    body = {'input': input}

            # Convert any file objects in the input to base64 format
            body = self._convert_files_to_base64(body)
@@ -320,20 +320,18 @@ class SimStudioClient:
    def execute_workflow_sync(
        self,
        workflow_id: str,
-        input_data: Optional[Dict[str, Any]] = None,
+        input: Optional[Any] = None,
+        *,
        timeout: float = 30.0,
        stream: Optional[bool] = None,
        selected_outputs: Optional[list] = None
    ) -> WorkflowExecutionResult:
        """
-        Execute a workflow and poll for completion (useful for long-running workflows).
-
-        Note: Currently, the API is synchronous, so this method just calls execute_workflow.
-        In the future, if async execution is added, this method can be enhanced.
+        Execute a workflow synchronously (ensures non-async mode).

        Args:
            workflow_id: The ID of the workflow to execute
-            input_data: Input data to pass to the workflow (can include file-like objects)
+            input: Input data to pass to the workflow (can include file-like objects)
            timeout: Timeout for the initial request in seconds
            stream: Enable streaming responses (default: None)
            selected_outputs: Block outputs to stream (e.g., ["agent1.content"])
@@ -344,9 +342,14 @@ class SimStudioClient:
        Raises:
            SimStudioError: If the workflow execution fails
        """
-        # For now, the API is synchronous, so we just execute directly
-        # In the future, if async execution is added, this method can be enhanced
-        return self.execute_workflow(workflow_id, input_data, timeout, stream, selected_outputs)
+        return self.execute_workflow(
+            workflow_id,
+            input,
+            timeout=timeout,
+            stream=stream,
+            selected_outputs=selected_outputs,
+            async_execution=False
+        )
    
    def set_api_key(self, api_key: str) -> None:
        """
@@ -410,7 +413,8 @@ class SimStudioClient:
    def execute_with_retry(
        self,
        workflow_id: str,
-        input_data: Optional[Dict[str, Any]] = None,
+        input: Optional[Any] = None,
+        *,
        timeout: float = 30.0,
        stream: Optional[bool] = None,
        selected_outputs: Optional[list] = None,
@@ -425,7 +429,7 @@ class SimStudioClient:

        Args:
            workflow_id: The ID of the workflow to execute
-            input_data: Input data to pass to the workflow (can include file-like objects)
+            input: Input data to pass to the workflow (can include file-like objects)
            timeout: Timeout in seconds
            stream: Enable streaming responses
            selected_outputs: Block outputs to stream
@@ -448,11 +452,11 @@ class SimStudioClient:
            try:
                return self.execute_workflow(
                    workflow_id,
-                    input_data,
-                    timeout,
-                    stream,
-                    selected_outputs,
-                    async_execution
+                    input,
+                    timeout=timeout,
+                    stream=stream,
+                    selected_outputs=selected_outputs,
+                    async_execution=async_execution
                )
            except SimStudioError as e:
                if e.code != 'RATE_LIMIT_EXCEEDED':
--- a/packages/python-sdk/tests/test_client.py
+++ b/packages/python-sdk/tests/test_client.py
@@ -91,11 +91,9 @@ def test_context_manager(mock_close):
    """Test SimStudioClient as context manager."""
    with SimStudioClient(api_key="test-api-key") as client:
        assert client.api_key == "test-api-key"
-    # Should close without error
    mock_close.assert_called_once()


-# Tests for async execution
@patch('simstudio.requests.Session.post')
 def test_async_execution_returns_task_id(mock_post):
    """Test async execution returns AsyncExecutionResult."""
@@ -115,7 +113,7 @@ def test_async_execution_returns_task_id(mock_post):
    client = SimStudioClient(api_key="test-api-key")
    result = client.execute_workflow(
        "workflow-id",
-        input_data={"message": "Hello"},
+        {"message": "Hello"},
        async_execution=True
    )

@@ -124,7 +122,6 @@ def test_async_execution_returns_task_id(mock_post):
    assert result.status == "queued"
    assert result.links["status"] == "/api/jobs/task-123"

-    # Verify X-Execution-Mode header was set
    call_args = mock_post.call_args
    assert call_args[1]["headers"]["X-Execution-Mode"] == "async"

@@ -146,7 +143,7 @@ def test_sync_execution_returns_result(mock_post):
    client = SimStudioClient(api_key="test-api-key")
    result = client.execute_workflow(
        "workflow-id",
-        input_data={"message": "Hello"},
+        {"message": "Hello"},
        async_execution=False
    )

@@ -166,13 +163,12 @@ def test_async_header_not_set_when_false(mock_post):
    mock_post.return_value = mock_response

    client = SimStudioClient(api_key="test-api-key")
-    client.execute_workflow("workflow-id", input_data={"message": "Hello"})
+    client.execute_workflow("workflow-id", {"message": "Hello"})

    call_args = mock_post.call_args
    assert "X-Execution-Mode" not in call_args[1]["headers"]


-# Tests for job status
@patch('simstudio.requests.Session.get')
 def test_get_job_status_success(mock_get):
    """Test getting job status."""
@@ -222,7 +218,6 @@ def test_get_job_status_not_found(mock_get):
    assert "Job not found" in str(exc_info.value)


-# Tests for retry with rate limiting
@patch('simstudio.requests.Session.post')
@patch('simstudio.time.sleep')
 def test_execute_with_retry_success_first_attempt(mock_sleep, mock_post):
@@ -238,7 +233,7 @@ def test_execute_with_retry_success_first_attempt(mock_sleep, mock_post):
    mock_post.return_value = mock_response

    client = SimStudioClient(api_key="test-api-key")
-    result = client.execute_with_retry("workflow-id", input_data={"message": "test"})
+    result = client.execute_with_retry("workflow-id", {"message": "test"})

    assert result.success is True
    assert mock_post.call_count == 1
@@ -278,7 +273,7 @@ def test_execute_with_retry_retries_on_rate_limit(mock_sleep, mock_post):
    client = SimStudioClient(api_key="test-api-key")
    result = client.execute_with_retry(
        "workflow-id",
-        input_data={"message": "test"},
+        {"message": "test"},
        max_retries=3,
        initial_delay=0.01
    )
@@ -307,7 +302,7 @@ def test_execute_with_retry_max_retries_exceeded(mock_sleep, mock_post):
    with pytest.raises(SimStudioError) as exc_info:
        client.execute_with_retry(
            "workflow-id",
-            input_data={"message": "test"},
+            {"message": "test"},
            max_retries=2,
            initial_delay=0.01
        )
@@ -333,13 +328,12 @@ def test_execute_with_retry_no_retry_on_other_errors(mock_post):
    client = SimStudioClient(api_key="test-api-key")

    with pytest.raises(SimStudioError) as exc_info:
-        client.execute_with_retry("workflow-id", input_data={"message": "test"})
+        client.execute_with_retry("workflow-id", {"message": "test"})

    assert "Server error" in str(exc_info.value)
    assert mock_post.call_count == 1  # No retries


-# Tests for rate limit info
 def test_get_rate_limit_info_returns_none_initially():
    """Test rate limit info is None before any API calls."""
    client = SimStudioClient(api_key="test-api-key")
@@ -362,7 +356,7 @@ def test_get_rate_limit_info_after_api_call(mock_post):
    mock_post.return_value = mock_response

    client = SimStudioClient(api_key="test-api-key")
-    client.execute_workflow("workflow-id", input_data={})
+    client.execute_workflow("workflow-id", {})

    info = client.get_rate_limit_info()
    assert info is not None
@@ -371,7 +365,6 @@ def test_get_rate_limit_info_after_api_call(mock_post):
    assert info.reset == 1704067200


-# Tests for usage limits
@patch('simstudio.requests.Session.get')
 def test_get_usage_limits_success(mock_get):
    """Test getting usage limits."""
@@ -435,7 +428,6 @@ def test_get_usage_limits_unauthorized(mock_get):
    assert "Invalid API key" in str(exc_info.value)


-# Tests for streaming with selectedOutputs
@patch('simstudio.requests.Session.post')
 def test_execute_workflow_with_stream_and_selected_outputs(mock_post):
    """Test execution with stream and selectedOutputs parameters."""
@@ -449,7 +441,7 @@ def test_execute_workflow_with_stream_and_selected_outputs(mock_post):
    client = SimStudioClient(api_key="test-api-key")
    client.execute_workflow(
        "workflow-id",
-        input_data={"message": "test"},
+        {"message": "test"},
        stream=True,
        selected_outputs=["agent1.content", "agent2.content"]
    )
@@ -459,4 +451,85 @@ def test_execute_workflow_with_stream_and_selected_outputs(mock_post):

    assert request_body["message"] == "test"
    assert request_body["stream"] is True
-    assert request_body["selectedOutputs"] == ["agent1.content", "agent2.content"] 
+    assert request_body["selectedOutputs"] == ["agent1.content", "agent2.content"]
+
+
+# Tests for primitive and list inputs
+@patch('simstudio.requests.Session.post')
+def test_execute_workflow_with_string_input(mock_post):
+    """Test execution with primitive string input wraps in input field."""
+    mock_response = Mock()
+    mock_response.ok = True
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"success": True, "output": {}}
+    mock_response.headers.get.return_value = None
+    mock_post.return_value = mock_response
+
+    client = SimStudioClient(api_key="test-api-key")
+    client.execute_workflow("workflow-id", "NVDA")
+
+    call_args = mock_post.call_args
+    request_body = call_args[1]["json"]
+
+    assert request_body["input"] == "NVDA"
+    assert "0" not in request_body  # Should not spread string characters
+
+
+@patch('simstudio.requests.Session.post')
+def test_execute_workflow_with_number_input(mock_post):
+    """Test execution with primitive number input wraps in input field."""
+    mock_response = Mock()
+    mock_response.ok = True
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"success": True, "output": {}}
+    mock_response.headers.get.return_value = None
+    mock_post.return_value = mock_response
+
+    client = SimStudioClient(api_key="test-api-key")
+    client.execute_workflow("workflow-id", 42)
+
+    call_args = mock_post.call_args
+    request_body = call_args[1]["json"]
+
+    assert request_body["input"] == 42
+
+
+@patch('simstudio.requests.Session.post')
+def test_execute_workflow_with_list_input(mock_post):
+    """Test execution with list input wraps in input field."""
+    mock_response = Mock()
+    mock_response.ok = True
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"success": True, "output": {}}
+    mock_response.headers.get.return_value = None
+    mock_post.return_value = mock_response
+
+    client = SimStudioClient(api_key="test-api-key")
+    client.execute_workflow("workflow-id", ["NVDA", "AAPL", "GOOG"])
+
+    call_args = mock_post.call_args
+    request_body = call_args[1]["json"]
+
+    assert request_body["input"] == ["NVDA", "AAPL", "GOOG"]
+    assert "0" not in request_body  # Should not spread list
+
+
+@patch('simstudio.requests.Session.post')
+def test_execute_workflow_with_dict_input_spreads_at_root(mock_post):
+    """Test execution with dict input spreads at root level."""
+    mock_response = Mock()
+    mock_response.ok = True
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"success": True, "output": {}}
+    mock_response.headers.get.return_value = None
+    mock_post.return_value = mock_response
+
+    client = SimStudioClient(api_key="test-api-key")
+    client.execute_workflow("workflow-id", {"ticker": "NVDA", "quantity": 100})
+
+    call_args = mock_post.call_args
+    request_body = call_args[1]["json"]
+
+    assert request_body["ticker"] == "NVDA"
+    assert request_body["quantity"] == 100
+    assert "input" not in request_body  # Should not wrap in input field 
--- a/packages/testing/src/mocks/executor.mock.ts
+++ b/packages/testing/src/mocks/executor.mock.ts
@@ -71,6 +71,19 @@ vi.mock('@/executor/path')
 vi.mock('@/executor/resolver', () => ({
  InputResolver: vi.fn(),
 }))
+vi.mock('@/executor/utils/http', () => ({
+  buildAuthHeaders: vi.fn().mockResolvedValue({ 'Content-Type': 'application/json' }),
+  buildAPIUrl: vi.fn((path: string) => new URL(path, 'http://localhost:3000')),
+  extractAPIErrorMessage: vi.fn(async (response: Response) => {
+    const defaultMessage = `API request failed with status ${response.status}`
+    try {
+      const errorData = await response.json()
+      return errorData.error || defaultMessage
+    } catch {
+      return defaultMessage
+    }
+  }),
+}))

 // Specific block utilities
 vi.mock('@/blocks/blocks/router')
--- a/packages/ts-sdk/README.md
+++ b/packages/ts-sdk/README.md
@@ -47,24 +47,35 @@ new SimStudioClient(config: SimStudioConfig)

 #### Methods

-##### executeWorkflow(workflowId, options?)
+##### executeWorkflow(workflowId, input?, options?)

 Execute a workflow with optional input data.

 ```typescript
+// With object input (spread at root level of request body)
 const result = await client.executeWorkflow('workflow-id', {
-  input: { message: 'Hello, world!' },
-  timeout: 30000 // 30 seconds
+  message: 'Hello, world!'
+});
+
+// With primitive input (wrapped as { input: value })
+const result = await client.executeWorkflow('workflow-id', 'NVDA');
+
+// With options
+const result = await client.executeWorkflow('workflow-id', { message: 'Hello' }, {
+  timeout: 60000
 });
 ```

 **Parameters:**
 - `workflowId` (string): The ID of the workflow to execute
+- `input` (any, optional): Input data to pass to the workflow. Objects are spread at the root level, primitives/arrays are wrapped in `{ input: value }`. File objects are automatically converted to base64.
 - `options` (ExecutionOptions, optional):
-  - `input` (any): Input data to pass to the workflow. File objects are automatically converted to base64.
  - `timeout` (number): Timeout in milliseconds (default: 30000)
+  - `stream` (boolean): Enable streaming responses
+  - `selectedOutputs` (string[]): Block outputs to stream (e.g., `["agent1.content"]`)
+  - `async` (boolean): Execute asynchronously and return execution ID

-**Returns:** `Promise<WorkflowExecutionResult>`
+**Returns:** `Promise<WorkflowExecutionResult | AsyncExecutionResult>`

 ##### getWorkflowStatus(workflowId)

@@ -96,25 +107,89 @@ if (isReady) {

 **Returns:** `Promise<boolean>`

-##### executeWorkflowSync(workflowId, options?)
+##### executeWorkflowSync(workflowId, input?, options?)

 Execute a workflow and poll for completion (useful for long-running workflows).

 ```typescript
-const result = await client.executeWorkflowSync('workflow-id', {
-  input: { data: 'some input' },
+const result = await client.executeWorkflowSync('workflow-id', { data: 'some input' }, {
  timeout: 60000
 });
 ```

 **Parameters:**
 - `workflowId` (string): The ID of the workflow to execute
+- `input` (any, optional): Input data to pass to the workflow
 - `options` (ExecutionOptions, optional):
-  - `input` (any): Input data to pass to the workflow
  - `timeout` (number): Timeout for the initial request in milliseconds

 **Returns:** `Promise<WorkflowExecutionResult>`

+##### getJobStatus(taskId)
+
+Get the status of an async job.
+
+```typescript
+const status = await client.getJobStatus('task-id-from-async-execution');
+console.log('Job status:', status);
+```
+
+**Parameters:**
+- `taskId` (string): The task ID returned from async execution
+
+**Returns:** `Promise<any>`
+
+##### executeWithRetry(workflowId, input?, options?, retryOptions?)
+
+Execute a workflow with automatic retry on rate limit errors.
+
+```typescript
+const result = await client.executeWithRetry('workflow-id', { message: 'Hello' }, {
+  timeout: 30000
+}, {
+  maxRetries: 3,
+  initialDelay: 1000,
+  maxDelay: 30000,
+  backoffMultiplier: 2
+});
+```
+
+**Parameters:**
+- `workflowId` (string): The ID of the workflow to execute
+- `input` (any, optional): Input data to pass to the workflow
+- `options` (ExecutionOptions, optional): Execution options
+- `retryOptions` (RetryOptions, optional):
+  - `maxRetries` (number): Maximum retry attempts (default: 3)
+  - `initialDelay` (number): Initial delay in ms (default: 1000)
+  - `maxDelay` (number): Maximum delay in ms (default: 30000)
+  - `backoffMultiplier` (number): Backoff multiplier (default: 2)
+
+**Returns:** `Promise<WorkflowExecutionResult | AsyncExecutionResult>`
+
+##### getRateLimitInfo()
+
+Get current rate limit information from the last API response.
+
+```typescript
+const rateInfo = client.getRateLimitInfo();
+if (rateInfo) {
+  console.log('Remaining requests:', rateInfo.remaining);
+}
+```
+
+**Returns:** `RateLimitInfo | null`
+
+##### getUsageLimits()
+
+Get current usage limits and quota information.
+
+```typescript
+const limits = await client.getUsageLimits();
+console.log('Current usage:', limits.usage);
+```
+
+**Returns:** `Promise<UsageLimits>`
+
 ##### setApiKey(apiKey)

 Update the API key.
@@ -170,6 +245,81 @@ class SimStudioError extends Error {
 }
 ```

+### AsyncExecutionResult
+
+```typescript
+interface AsyncExecutionResult {
+  success: boolean;
+  taskId: string;
+  status: 'queued';
+  createdAt: string;
+  links: {
+    status: string;
+  };
+}
+```
+
+### RateLimitInfo
+
+```typescript
+interface RateLimitInfo {
+  limit: number;
+  remaining: number;
+  reset: number;
+  retryAfter?: number;
+}
+```
+
+### UsageLimits
+
+```typescript
+interface UsageLimits {
+  success: boolean;
+  rateLimit: {
+    sync: {
+      isLimited: boolean;
+      limit: number;
+      remaining: number;
+      resetAt: string;
+    };
+    async: {
+      isLimited: boolean;
+      limit: number;
+      remaining: number;
+      resetAt: string;
+    };
+    authType: string;
+  };
+  usage: {
+    currentPeriodCost: number;
+    limit: number;
+    plan: string;
+  };
+}
+```
+
+### ExecutionOptions
+
+```typescript
+interface ExecutionOptions {
+  timeout?: number;
+  stream?: boolean;
+  selectedOutputs?: string[];
+  async?: boolean;
+}
+```
+
+### RetryOptions
+
+```typescript
+interface RetryOptions {
+  maxRetries?: number;
+  initialDelay?: number;
+  maxDelay?: number;
+  backoffMultiplier?: number;
+}
+```
+
 ## Examples

 ### Basic Workflow Execution
@@ -191,10 +341,8 @@ async function runWorkflow() {

    // Execute the workflow
    const result = await client.executeWorkflow('my-workflow-id', {
-      input: {
-        message: 'Process this data',
-        userId: '12345'
-      }
+      message: 'Process this data',
+      userId: '12345'
    });

    if (result.success) {
@@ -298,22 +446,18 @@ const file = new File([fileBuffer], 'document.pdf', { type: 'application/pdf' })

 // Include files under the field name from your API trigger's input format
 const result = await client.executeWorkflow('workflow-id', {
-  input: {
-    documents: [file],  // Field name must match your API trigger's file input field
-    instructions: 'Process this document'
-  }
+  documents: [file],  // Field name must match your API trigger's file input field
+  instructions: 'Process this document'
 });

 // Browser: From file input
 const handleFileUpload = async (event: Event) => {
-  const input = event.target as HTMLInputElement;
-  const files = Array.from(input.files || []);
+  const inputEl = event.target as HTMLInputElement;
+  const files = Array.from(inputEl.files || []);

  const result = await client.executeWorkflow('workflow-id', {
-    input: {
-      attachments: files,  // Field name must match your API trigger's file input field
-      query: 'Analyze these files'
-    }
+    attachments: files,  // Field name must match your API trigger's file input field
+    query: 'Analyze these files'
  });
 };
 ```
--- a/packages/ts-sdk/package.json
+++ b/packages/ts-sdk/package.json
@@ -1,6 +1,6 @@
 {
  "name": "simstudio-ts-sdk",
-  "version": "0.1.1",
+  "version": "0.1.2",
  "description": "Sim SDK - Execute workflows programmatically",
  "type": "module",
  "exports": {
--- a/packages/ts-sdk/src/index.test.ts
+++ b/packages/ts-sdk/src/index.test.ts
@@ -119,10 +119,11 @@ describe('SimStudioClient', () => {
      }
      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      const result = await client.executeWorkflow('workflow-id', {
-        input: { message: 'Hello' },
-        async: true,
-      })
+      const result = await client.executeWorkflow(
+        'workflow-id',
+        { message: 'Hello' },
+        { async: true }
+      )

      expect(result).toHaveProperty('taskId', 'task-123')
      expect(result).toHaveProperty('status', 'queued')
@@ -152,10 +153,11 @@ describe('SimStudioClient', () => {
      }
      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      const result = await client.executeWorkflow('workflow-id', {
-        input: { message: 'Hello' },
-        async: false,
-      })
+      const result = await client.executeWorkflow(
+        'workflow-id',
+        { message: 'Hello' },
+        { async: false }
+      )

      expect(result).toHaveProperty('success', true)
      expect(result).toHaveProperty('output')
@@ -177,9 +179,7 @@ describe('SimStudioClient', () => {
      }
      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      await client.executeWorkflow('workflow-id', {
-        input: { message: 'Hello' },
-      })
+      await client.executeWorkflow('workflow-id', { message: 'Hello' })

      const calls = vi.mocked(fetch.default).mock.calls
      expect(calls[0][1]?.headers).not.toHaveProperty('X-Execution-Mode')
@@ -256,9 +256,7 @@ describe('SimStudioClient', () => {
      }
      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      const result = await client.executeWithRetry('workflow-id', {
-        input: { message: 'test' },
-      })
+      const result = await client.executeWithRetry('workflow-id', { message: 'test' })

      expect(result).toHaveProperty('success', true)
      expect(vi.mocked(fetch.default)).toHaveBeenCalledTimes(1)
@@ -305,7 +303,8 @@ describe('SimStudioClient', () => {

      const result = await client.executeWithRetry(
        'workflow-id',
-        { input: { message: 'test' } },
+        { message: 'test' },
+        {},
        { maxRetries: 3, initialDelay: 10 }
      )

@@ -336,7 +335,8 @@ describe('SimStudioClient', () => {
      await expect(
        client.executeWithRetry(
          'workflow-id',
-          { input: { message: 'test' } },
+          { message: 'test' },
+          {},
          { maxRetries: 2, initialDelay: 10 }
        )
      ).rejects.toThrow('Rate limit exceeded')
@@ -361,9 +361,9 @@ describe('SimStudioClient', () => {

      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      await expect(
-        client.executeWithRetry('workflow-id', { input: { message: 'test' } })
-      ).rejects.toThrow('Server error')
+      await expect(client.executeWithRetry('workflow-id', { message: 'test' })).rejects.toThrow(
+        'Server error'
+      )

      expect(vi.mocked(fetch.default)).toHaveBeenCalledTimes(1) // No retries
    })
@@ -393,7 +393,7 @@ describe('SimStudioClient', () => {

      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      await client.executeWorkflow('workflow-id', { input: {} })
+      await client.executeWorkflow('workflow-id', {})

      const info = client.getRateLimitInfo()
      expect(info).not.toBeNull()
@@ -490,11 +490,11 @@ describe('SimStudioClient', () => {

      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)

-      await client.executeWorkflow('workflow-id', {
-        input: { message: 'test' },
-        stream: true,
-        selectedOutputs: ['agent1.content', 'agent2.content'],
-      })
+      await client.executeWorkflow(
+        'workflow-id',
+        { message: 'test' },
+        { stream: true, selectedOutputs: ['agent1.content', 'agent2.content'] }
+      )

      const calls = vi.mocked(fetch.default).mock.calls
      const requestBody = JSON.parse(calls[0][1]?.body as string)
@@ -505,6 +505,134 @@ describe('SimStudioClient', () => {
      expect(requestBody.selectedOutputs).toEqual(['agent1.content', 'agent2.content'])
    })
  })
+
+  describe('executeWorkflow - primitive and array inputs', () => {
+    it('should wrap primitive string input in input field', async () => {
+      const fetch = await import('node-fetch')
+      const mockResponse = {
+        ok: true,
+        status: 200,
+        json: vi.fn().mockResolvedValue({
+          success: true,
+          output: {},
+        }),
+        headers: {
+          get: vi.fn().mockReturnValue(null),
+        },
+      }
+
+      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)
+
+      await client.executeWorkflow('workflow-id', 'NVDA')
+
+      const calls = vi.mocked(fetch.default).mock.calls
+      const requestBody = JSON.parse(calls[0][1]?.body as string)
+
+      expect(requestBody).toHaveProperty('input', 'NVDA')
+      expect(requestBody).not.toHaveProperty('0') // Should not spread string characters
+    })
+
+    it('should wrap primitive number input in input field', async () => {
+      const fetch = await import('node-fetch')
+      const mockResponse = {
+        ok: true,
+        status: 200,
+        json: vi.fn().mockResolvedValue({
+          success: true,
+          output: {},
+        }),
+        headers: {
+          get: vi.fn().mockReturnValue(null),
+        },
+      }
+
+      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)
+
+      await client.executeWorkflow('workflow-id', 42)
+
+      const calls = vi.mocked(fetch.default).mock.calls
+      const requestBody = JSON.parse(calls[0][1]?.body as string)
+
+      expect(requestBody).toHaveProperty('input', 42)
+    })
+
+    it('should wrap array input in input field', async () => {
+      const fetch = await import('node-fetch')
+      const mockResponse = {
+        ok: true,
+        status: 200,
+        json: vi.fn().mockResolvedValue({
+          success: true,
+          output: {},
+        }),
+        headers: {
+          get: vi.fn().mockReturnValue(null),
+        },
+      }
+
+      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)
+
+      await client.executeWorkflow('workflow-id', ['NVDA', 'AAPL', 'GOOG'])
+
+      const calls = vi.mocked(fetch.default).mock.calls
+      const requestBody = JSON.parse(calls[0][1]?.body as string)
+
+      expect(requestBody).toHaveProperty('input')
+      expect(requestBody.input).toEqual(['NVDA', 'AAPL', 'GOOG'])
+      expect(requestBody).not.toHaveProperty('0') // Should not spread array
+    })
+
+    it('should spread object input at root level', async () => {
+      const fetch = await import('node-fetch')
+      const mockResponse = {
+        ok: true,
+        status: 200,
+        json: vi.fn().mockResolvedValue({
+          success: true,
+          output: {},
+        }),
+        headers: {
+          get: vi.fn().mockReturnValue(null),
+        },
+      }
+
+      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)
+
+      await client.executeWorkflow('workflow-id', { ticker: 'NVDA', quantity: 100 })
+
+      const calls = vi.mocked(fetch.default).mock.calls
+      const requestBody = JSON.parse(calls[0][1]?.body as string)
+
+      expect(requestBody).toHaveProperty('ticker', 'NVDA')
+      expect(requestBody).toHaveProperty('quantity', 100)
+      expect(requestBody).not.toHaveProperty('input') // Should not wrap in input field
+    })
+
+    it('should handle null input as no input (empty body)', async () => {
+      const fetch = await import('node-fetch')
+      const mockResponse = {
+        ok: true,
+        status: 200,
+        json: vi.fn().mockResolvedValue({
+          success: true,
+          output: {},
+        }),
+        headers: {
+          get: vi.fn().mockReturnValue(null),
+        },
+      }
+
+      vi.mocked(fetch.default).mockResolvedValue(mockResponse as any)
+
+      await client.executeWorkflow('workflow-id', null)
+
+      const calls = vi.mocked(fetch.default).mock.calls
+      const requestBody = JSON.parse(calls[0][1]?.body as string)
+
+      // null treated as "no input" - sends empty body (consistent with Python SDK)
+      expect(requestBody).toEqual({})
+    })
+  })
 })

 describe('SimStudioError', () => {
--- a/packages/ts-sdk/src/index.ts
+++ b/packages/ts-sdk/src/index.ts
@@ -26,7 +26,6 @@ export interface WorkflowStatus {
 }

 export interface ExecutionOptions {
-  input?: any
  timeout?: number
  stream?: boolean
  selectedOutputs?: string[]
@@ -117,10 +116,6 @@ export class SimStudioClient {
    this.baseUrl = normalizeBaseUrl(config.baseUrl || 'https://sim.ai')
  }

-  /**
-   * Execute a workflow with optional input data
-   * If async is true, returns immediately with a task ID
-   */
  /**
   * Convert File objects in input to API format (base64)
   * Recursively processes nested objects and arrays
@@ -170,20 +165,25 @@ export class SimStudioClient {
    return value
  }

+  /**
+   * Execute a workflow with optional input data
+   * @param workflowId - The ID of the workflow to execute
+   * @param input - Input data to pass to the workflow (object, primitive, or array)
+   * @param options - Execution options (timeout, stream, async, etc.)
+   */
  async executeWorkflow(
    workflowId: string,
+    input?: any,
    options: ExecutionOptions = {}
  ): Promise<WorkflowExecutionResult | AsyncExecutionResult> {
    const url = `${this.baseUrl}/api/workflows/${workflowId}/execute`
-    const { input, timeout = 30000, stream, selectedOutputs, async } = options
+    const { timeout = 30000, stream, selectedOutputs, async } = options

    try {
-      // Create a timeout promise
      const timeoutPromise = new Promise<never>((_, reject) => {
        setTimeout(() => reject(new Error('TIMEOUT')), timeout)
      })

-      // Build headers - async execution uses X-Execution-Mode header
      const headers: Record<string, string> = {
        'Content-Type': 'application/json',
        'X-API-Key': this.apiKey,
@@ -192,10 +192,15 @@ export class SimStudioClient {
        headers['X-Execution-Mode'] = 'async'
      }

-      // Build JSON body - spread input at root level, then add API control parameters
-      let jsonBody: any = input !== undefined ? { ...input } : {}
+      let jsonBody: any = {}
+      if (input !== undefined && input !== null) {
+        if (typeof input === 'object' && input !== null && !Array.isArray(input)) {
+          jsonBody = { ...input }
+        } else {
+          jsonBody = { input }
+        }
+      }

-      // Convert any File objects in the input to base64 format
      jsonBody = await this.convertFilesToBase64(jsonBody)

      if (stream !== undefined) {
@@ -213,10 +218,8 @@ export class SimStudioClient {

      const response = await Promise.race([fetchPromise, timeoutPromise])

-      // Extract rate limit headers
      this.updateRateLimitInfo(response)

-      // Handle rate limiting with retry
      if (response.status === 429) {
        const retryAfter = this.rateLimitInfo?.retryAfter || 1000
        throw new SimStudioError(
@@ -285,15 +288,18 @@ export class SimStudioClient {
  }

  /**
-   * Execute a workflow and poll for completion (useful for long-running workflows)
+   * Execute a workflow synchronously (ensures non-async mode)
+   * @param workflowId - The ID of the workflow to execute
+   * @param input - Input data to pass to the workflow
+   * @param options - Execution options (timeout, stream, etc.)
   */
  async executeWorkflowSync(
    workflowId: string,
+    input?: any,
    options: ExecutionOptions = {}
  ): Promise<WorkflowExecutionResult> {
-    // Ensure sync mode by explicitly setting async to false
    const syncOptions = { ...options, async: false }
-    return this.executeWorkflow(workflowId, syncOptions) as Promise<WorkflowExecutionResult>
+    return this.executeWorkflow(workflowId, input, syncOptions) as Promise<WorkflowExecutionResult>
  }

  /**
@@ -361,9 +367,14 @@ export class SimStudioClient {

  /**
   * Execute workflow with automatic retry on rate limit
+   * @param workflowId - The ID of the workflow to execute
+   * @param input - Input data to pass to the workflow
+   * @param options - Execution options (timeout, stream, async, etc.)
+   * @param retryOptions - Retry configuration (maxRetries, delays, etc.)
   */
  async executeWithRetry(
    workflowId: string,
+    input?: any,
    options: ExecutionOptions = {},
    retryOptions: RetryOptions = {}
  ): Promise<WorkflowExecutionResult | AsyncExecutionResult> {
@@ -379,7 +390,7 @@ export class SimStudioClient {

    for (let attempt = 0; attempt <= maxRetries; attempt++) {
      try {
-        return await this.executeWorkflow(workflowId, options)
+        return await this.executeWorkflow(workflowId, input, options)
      } catch (error: any) {
        if (!(error instanceof SimStudioError) || error.code !== 'RATE_LIMIT_EXCEEDED') {
          throw error
@@ -387,23 +398,19 @@ export class SimStudioClient {

        lastError = error

-        // Don't retry after last attempt
        if (attempt === maxRetries) {
          break
        }

-        // Use retry-after if provided, otherwise use exponential backoff
        const waitTime =
          error.status === 429 && this.rateLimitInfo?.retryAfter
            ? this.rateLimitInfo.retryAfter
            : Math.min(delay, maxDelay)

-        // Add jitter (±25%)
        const jitter = waitTime * (0.75 + Math.random() * 0.5)

        await new Promise((resolve) => setTimeout(resolve, jitter))

-        // Exponential backoff for next attempt
        delay *= backoffMultiplier
      }
    }
@@ -475,5 +482,4 @@ export class SimStudioClient {
  }
 }

-// Export types and classes
 export { SimStudioClient as default }
--- a/scripts/create-single-release.ts
+++ b/scripts/create-single-release.ts
@@ -126,7 +126,7 @@ async function fetchGitHubCommitDetails(

      const githubUsername = commit.author?.login || commit.committer?.login || 'unknown'

-      let cleanMessage = commit.commit.message.split('\n')[0] // First line only
+      let cleanMessage = commit.commit.message.split('\n')[0]
      if (prNumber) {
        cleanMessage = cleanMessage.replace(/\s*\(#\d+\)\s*$/, '')
      }
@@ -226,12 +226,23 @@ async function getCommitsBetweenVersions(
 function categorizeCommit(message: string): 'features' | 'fixes' | 'improvements' | 'other' {
  const msgLower = message.toLowerCase()

-  if (
-    msgLower.includes('feat') ||
-    msgLower.includes('add') ||
-    msgLower.includes('implement') ||
-    msgLower.includes('new ')
-  ) {
+  if (/^feat(\(|:|!)/.test(msgLower)) {
+    return 'features'
+  }
+
+  if (/^fix(\(|:|!)/.test(msgLower)) {
+    return 'fixes'
+  }
+
+  if (/^(improvement|improve|perf|refactor)(\(|:|!)/.test(msgLower)) {
+    return 'improvements'
+  }
+
+  if (/^(chore|docs|style|test|ci|build)(\(|:|!)/.test(msgLower)) {
+    return 'other'
+  }
+
+  if (msgLower.includes('feat') || msgLower.includes('implement') || msgLower.includes('new ')) {
    return 'features'
  }

@@ -242,9 +253,10 @@ function categorizeCommit(message: string): 'features' | 'fixes' | 'improvements
  if (
    msgLower.includes('improve') ||
    msgLower.includes('enhance') ||
-    msgLower.includes('update') ||
    msgLower.includes('upgrade') ||
-    msgLower.includes('optimization')
+    msgLower.includes('optimization') ||
+    msgLower.includes('add') ||
+    msgLower.includes('update')
  ) {
    return 'improvements'
  }
Author	SHA1	Message	Date
Waleed	1bf5ed4586	improvement(docs): add quick reference page and update SDK documentation (#2994 ) * docs(sdk): update README to reflect new interface * improvement(docs): add quick reference page and update SDK documentation * docs(copilot): update copilot documentation with all features	2026-01-25 02:21:02 -08:00
Waleed	dc0ed842c4	fix(sdk): improve input handling and separate input from options (#2993 ) * fix(sdk): improve input handling and separate input from options * fix(sdk): treat null as no input for consistency with Python SDK	2026-01-25 00:50:09 -08:00
Waleed	1952b196a0	fix(releases): improve commit categorization and ci security (#2992 ) * fix(releases): improve commit categorization and CI security * fix(releases): remove redundant update check	2026-01-24 22:33:04 -08:00
Vikhyath Mondreti	fa03d4d818	fix(copilot): canonical modes should be constructed on edit (#2989 ) * fix(copilot): canonical modes should be constructed * reuse canonicalIndex * fix insert into subflow case:	2026-01-24 22:13:57 -08:00
Waleed	e14cebeec5	fix(context-menu): preserve selection when right-clicking selected block (#2991 ) * fix(context-menu): preserve selection when right-clicking selected block * added tsdoc	2026-01-24 22:05:27 -08:00
Waleed	404d8c006e	fix(tooltip): add tooltip to canonical toggle button (#2990 ) * fix(tooltip): add tooltip to canonical toggle button * ack comments	2026-01-24 21:58:09 -08:00
Waleed	ac91d78834	fix(anthropic): use anthropic sdk to transform malformed response schemas to anthropic format (#2988 ) * fix(anthropic): use anthropic sdk to transform malformed response schemas to anthropic format * copy internal transformJSONSchema from anthropic * remove dep update * use built-in func from anthropic	2026-01-24 20:31:07 -08:00
Waleed	6f0a093869	fix(llm): update router and llm_chat tool to call providers routes (#2986 ) * fix(llm): update router and llm_chat tool to call providers routes * updated failing tests	2026-01-24 18:50:37 -08:00