Compare commits

...

4 Commits

Author SHA1 Message Date
Siddharth Ganesan
1464cbe078 Fix copilot edit summary for loops and parallels 2026-01-24 12:31:20 -08:00
Siddharth Ganesan
3bbf7f5d1d fix(auth): copilot routes (#2977)
* Fix copilot auth

* Fix

* Fix

* Fix
2026-01-24 12:26:21 -08:00
Vikhyath Mondreti
68683258c3 fix(blog): slash actions description (#2976)
* improvement(docs): loop and parallel var reference syntax

* fix(blog): slash actions description
2026-01-24 11:46:07 -08:00
Vikhyath Mondreti
fc7f56e21b improvement(docs): loop and parallel var reference syntax (#2975) 2026-01-24 11:36:47 -08:00
5 changed files with 97 additions and 22 deletions

View File

@@ -124,11 +124,44 @@ Choose between four types of loops:
3. Drag other blocks inside the loop container
4. Connect the blocks as needed
### Accessing Results
### Referencing Loop Data
After a loop completes, you can access aggregated results:
There's an important distinction between referencing loop data from **inside** vs **outside** the loop:
- **`<loop.results>`**: Array of results from all loop iterations
<Tabs items={['Inside the Loop', 'Outside the Loop']}>
<Tab>
**Inside the loop**, use `<loop.>` references to access the current iteration context:
- **`<loop.index>`**: Current iteration number (0-based)
- **`<loop.currentItem>`**: Current item being processed (forEach only)
- **`<loop.items>`**: Full collection being iterated (forEach only)
```
// Inside a Function block within the loop
const idx = <loop.index>; // 0, 1, 2, ...
const item = <loop.currentItem>; // Current item
```
<Callout type="info">
These references are only available for blocks **inside** the loop container. They give you access to the current iteration's context.
</Callout>
</Tab>
<Tab>
**Outside the loop** (after it completes), reference the loop block by its name to access aggregated results:
- **`<LoopBlockName.results>`**: Array of results from all iterations
```
// If your loop block is named "Process Items"
const allResults = <processitems.results>;
// Returns: [result1, result2, result3, ...]
```
<Callout type="info">
After the loop completes, use the loop's block name (not `loop.`) to access the collected results. The block name is normalized (lowercase, no spaces).
</Callout>
</Tab>
</Tabs>
## Example Use Cases
@@ -184,28 +217,29 @@ Variables (i=0) → Loop (While i<10) → Agent (Process) → Variables (i++)
</ul>
</Tab>
<Tab>
Available **inside** the loop only:
<ul className="list-disc space-y-2 pl-6">
<li>
<strong>loop.currentItem</strong>: Current item being processed
<strong>{"<loop.index>"}</strong>: Current iteration number (0-based)
</li>
<li>
<strong>loop.index</strong>: Current iteration number (0-based)
<strong>{"<loop.currentItem>"}</strong>: Current item being processed (forEach only)
</li>
<li>
<strong>loop.items</strong>: Full collection (forEach loops)
<strong>{"<loop.items>"}</strong>: Full collection (forEach only)
</li>
</ul>
</Tab>
<Tab>
<ul className="list-disc space-y-2 pl-6">
<li>
<strong>loop.results</strong>: Array of all iteration results
<strong>{"<blockname.results>"}</strong>: Array of all iteration results (accessed via block name)
</li>
<li>
<strong>Structure</strong>: Results maintain iteration order
</li>
<li>
<strong>Access</strong>: Available in blocks after the loop
<strong>Access</strong>: Available in blocks after the loop completes
</li>
</ul>
</Tab>

View File

@@ -76,11 +76,44 @@ Choose between two types of parallel execution:
3. Drag a single block inside the parallel container
4. Connect the block as needed
### Accessing Results
### Referencing Parallel Data
After a parallel block completes, you can access aggregated results:
There's an important distinction between referencing parallel data from **inside** vs **outside** the parallel block:
- **`<parallel.results>`**: Array of results from all parallel instances
<Tabs items={['Inside the Parallel', 'Outside the Parallel']}>
<Tab>
**Inside the parallel**, use `<parallel.>` references to access the current instance context:
- **`<parallel.index>`**: Current instance number (0-based)
- **`<parallel.currentItem>`**: Item for this instance (collection-based only)
- **`<parallel.items>`**: Full collection being distributed (collection-based only)
```
// Inside a Function block within the parallel
const idx = <parallel.index>; // 0, 1, 2, ...
const item = <parallel.currentItem>; // This instance's item
```
<Callout type="info">
These references are only available for blocks **inside** the parallel container. They give you access to the current instance's context.
</Callout>
</Tab>
<Tab>
**Outside the parallel** (after it completes), reference the parallel block by its name to access aggregated results:
- **`<ParallelBlockName.results>`**: Array of results from all instances
```
// If your parallel block is named "Process Tasks"
const allResults = <processtasks.results>;
// Returns: [result1, result2, result3, ...]
```
<Callout type="info">
After the parallel completes, use the parallel's block name (not `parallel.`) to access the collected results. The block name is normalized (lowercase, no spaces).
</Callout>
</Tab>
</Tabs>
## Example Use Cases
@@ -98,11 +131,11 @@ Parallel (["gpt-4o", "claude-3.7-sonnet", "gemini-2.5-pro"]) → Agent → Evalu
### Result Aggregation
Results from all parallel instances are automatically collected:
Results from all parallel instances are automatically collected and accessible via the block name:
```javascript
// In a Function block after the parallel
const allResults = input.parallel.results;
// In a Function block after a parallel named "Process Tasks"
const allResults = <processtasks.results>;
// Returns: [result1, result2, result3, ...]
```
@@ -158,25 +191,26 @@ Understanding when to use each:
</ul>
</Tab>
<Tab>
Available **inside** the parallel only:
<ul className="list-disc space-y-2 pl-6">
<li>
<strong>parallel.currentItem</strong>: Item for this instance
<strong>{"<parallel.index>"}</strong>: Instance number (0-based)
</li>
<li>
<strong>parallel.index</strong>: Instance number (0-based)
<strong>{"<parallel.currentItem>"}</strong>: Item for this instance (collection-based only)
</li>
<li>
<strong>parallel.items</strong>: Full collection (collection-based)
<strong>{"<parallel.items>"}</strong>: Full collection (collection-based only)
</li>
</ul>
</Tab>
<Tab>
<ul className="list-disc space-y-2 pl-6">
<li>
<strong>parallel.results</strong>: Array of all instance results
<strong>{"<blockname.results>"}</strong>: Array of all instance results (accessed via block name)
</li>
<li>
<strong>Access</strong>: Available in blocks after the parallel
<strong>Access</strong>: Available in blocks after the parallel completes
</li>
</ul>
</Tab>

View File

@@ -18,6 +18,8 @@ import {
import { CopilotMarkdownRenderer } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/copilot-message/components/markdown-renderer'
import { SmoothStreamingText } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/copilot-message/components/smooth-streaming'
import { ThinkingBlock } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/copilot-message/components/thinking-block'
import { LoopTool } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/subflows/loop/loop-config'
import { ParallelTool } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/subflows/parallel/parallel-config'
import { getDisplayValue } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/workflow-block/workflow-block'
import { getBlock } from '@/blocks/registry'
import type { CopilotToolCall } from '@/stores/panel'
@@ -1131,6 +1133,12 @@ const WorkflowEditSummary = memo(function WorkflowEditSummary({
}
const getBlockConfig = (blockType: string) => {
if (blockType === 'loop') {
return { icon: LoopTool.icon, bgColor: LoopTool.bgColor }
}
if (blockType === 'parallel') {
return { icon: ParallelTool.icon, bgColor: ParallelTool.bgColor }
}
return getBlock(blockType)
}
@@ -1260,7 +1268,6 @@ async function handleRun(
const instance = getClientTool(toolCall.id)
if (!instance && isIntegrationTool(toolCall.name)) {
setToolCallState(toolCall, 'executing')
onStateChange?.('executing')
try {
await useCopilotStore.getState().executeIntegrationTool(toolCall.id)

View File

@@ -496,7 +496,7 @@ export function DeployModal({
</div>
)}
{apiDeployWarnings.length > 0 && (
<div className='mb-3 rounded-[4px] border border-amber-500/30 bg-amber-500/10 p-3 text-amber-700 dark:text-amber-400 text-sm'>
<div className='mb-3 rounded-[4px] border border-amber-500/30 bg-amber-500/10 p-3 text-amber-700 text-sm dark:text-amber-400'>
<div className='font-semibold'>Deployment Warning</div>
{apiDeployWarnings.map((warning, index) => (
<div key={index}>{warning}</div>

View File

@@ -31,7 +31,7 @@ Copilot supports slash commands that trigger specialized capabilities:
- `/fast` — uses a faster model for quick responses when you need speed over depth
- `/research` — performs multi-step web research on a topic, synthesizing results from multiple sources
- `/actions` — enables agentic mode where Copilot can take actions on your behalf, like modifying blocks or creating workflows
- `/actions` — lets Copilot directly use your connected integrations as tools, like reading your Gmail, sending Slack messages, or querying your database—all outside the context of a workflow
- `/search` — searches the web for relevant information
- `/read` — reads and extracts content from a URL
- `/scrape` — scrapes structured data from web pages