fix(chat): stop a removed chip lingering when its label prefixes another

Cursor Bugbot: the mention sync tests each label with a lookahead that rejects
only word characters, so '-', ')' and space all let a shorter label match INSIDE
a longer token. '@notes.md:12' matches within '@notes.md:12-40', and
'@sales (3 rows)' within '@sales (3 rows) (2)'. Deleting the shorter chip left
its context attached, and it was still sent with the message.

The label class is pre-existing, but this PR made it routine: line ranges and
uniqueContextLabel ordinals generate prefix pairs for any two selections of the
same file or table.

Fixed at the sync rather than by reshaping labels to dodge the prefix — a label
format chosen to avoid a matcher bug would just relocate it. Contexts are now
tested longest-label-first, and each matched token is blanked before shorter
labels are tested, so every context is judged against text its own token owns.
Blanked in place, not removed, so the (^|\s) boundary of whatever sits next to
it is preserved; prev order is still what's returned.

Shared with the workflow copilot input, so tests cover both directions: the two
prefix pairs are dropped when only the longer token remains, both survive when
both tokens are present, order is preserved, and trailing punctuation after a
mention still keeps its chip.

Author: waleedlatif1

apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/user-input/hooks/use-context-management.test.tsx

@@ -0,0 +1,100 @@
+/**
+ * @vitest-environment jsdom
+ */
+import { act } from 'react'
+import { createRoot, type Root } from 'react-dom/client'
+import { afterEach, beforeEach, describe, expect, it } from 'vitest'
+import { useContextManagement } from '@/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/user-input/hooks/use-context-management'
+import type { ChatContext } from '@/stores/panel'
+
+let container: HTMLDivElement
+let root: Root
+let latest: ReturnType<typeof useContextManagement>
+
+/** Renders the hook with a fixed message and initial contexts, exposing its result. */
+function renderSync(message: string, initialContexts: ChatContext[]) {
+  function Host() {
+    latest = useContextManagement({ message, initialContexts })
+    return null
+  }
+  act(() => {
+    root.render(<Host />)
+  })
+}
+
+const fileSelection = (label: string): ChatContext => ({
+  kind: 'file_selection',
+  fileId: 'f1',
+  fileName: 'notes.md',
+  label,
+  text: 'passage',
+})
+
+const tableSelection = (label: string, rowIds: string[]): ChatContext => ({
+  kind: 'table_selection',
+  tableId: 't1',
+  tableName: 'Sales',
+  label,
+  rowIds,
+})
+
+describe('useContextManagement label sync', () => {
+  beforeEach(() => {
+    container = document.createElement('div')
+    document.body.appendChild(container)
+    root = createRoot(container)
+  })
+
+  afterEach(() => {
+    act(() => root.unmount())
+    container.remove()
+  })
+
+  it('drops a chip whose label is only a prefix of a surviving one', () => {
+    // `@notes.md:12` matches inside `@notes.md:12-40` — the token lookahead
+    // rejects word characters but not `-`, so only the longer chip is really
+    // present and the shorter must not linger and get sent.
+    renderSync('look at @notes.md:12-40 please', [
+      fileSelection('notes.md:12'),
+      fileSelection('notes.md:12-40'),
+    ])
+
+    expect(latest.selectedContexts.map((c) => c.label)).toEqual(['notes.md:12-40'])
+  })
+
+  it('drops an un-ordinalized chip when only its ordinal twin remains', () => {
+    renderSync('see @Sales (3 rows) (2) here', [
+      tableSelection('Sales (3 rows)', ['r1', 'r2', 'r3']),
+      tableSelection('Sales (3 rows) (2)', ['r7', 'r8', 'r9']),
+    ])
+
+    expect(latest.selectedContexts.map((c) => c.label)).toEqual(['Sales (3 rows) (2)'])
+  })
+
+  it('keeps both when both tokens are present', () => {
+    renderSync('@notes.md:12 and @notes.md:12-40', [
+      fileSelection('notes.md:12'),
+      fileSelection('notes.md:12-40'),
+    ])
+
+    expect(latest.selectedContexts.map((c) => c.label).sort()).toEqual([
+      'notes.md:12',
+      'notes.md:12-40',
+    ])
+  })
+
+  it('preserves the original context order, not the length-sorted one', () => {
+    renderSync('@notes.md:12 and @notes.md:12-40', [
+      fileSelection('notes.md:12'),
+      fileSelection('notes.md:12-40'),
+    ])
+
+    expect(latest.selectedContexts.map((c) => c.label)).toEqual(['notes.md:12', 'notes.md:12-40'])
+  })
+
+  it('still tolerates trailing punctuation after a mention', () => {
+    renderSync('ask @notes.md:12-40, then stop', [fileSelection('notes.md:12-40')])
+
+    expect(latest.selectedContexts).toHaveLength(1)
+  })
+})

apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/copilot/components/user-input/hooks/use-context-management.ts

@@ -68,9 +68,20 @@ export function useContextManagement({ message, initialContexts }: UseContextMan
     setSelectedContexts((prev) => {
       if (prev.length === 0) return prev
 
-      const filtered = prev.filter((c) => {
-        if (!c.label) return false
-        // Check for slash command tokens or mention tokens based on kind.
+      // Longest label first, masking each token once it matches. One label can be
+      // a prefix of another — `notes.md:12` of `notes.md:12-40`, `Sales (3 rows)`
+      // of `Sales (3 rows) (2)` — and the lookahead below only rejects a
+      // following word character, so `-`, `)` and space all let the shorter
+      // pattern match INSIDE the longer token. Without masking, deleting the
+      // shorter chip would leave its context attached and still send it.
+      const byLabelLengthDesc = [...prev].sort(
+        (a, b) => (b.label?.length ?? 0) - (a.label?.length ?? 0)
+      )
+      let unclaimed = message
+      const present = new Set<ChatContext>()
+
+      for (const c of byLabelLengthDesc) {
+        if (!c.label) continue
         // The trailing lookahead `(?![A-Za-z0-9_])` accepts any word-boundary
         // — whitespace, end-of-string, or punctuation — so `@Slack.` and
         // `@Slack,` survive the sync. A strict `(\s|$)` here would strip
@@ -89,8 +100,19 @@ export function useContextManagement({ message, initialContexts }: UseContextMan
         const tokenPattern = new RegExp(
           `(^|\\s)${escapeRegex(prefix)}${escapeRegex(c.label)}(?![A-Za-z0-9_])`
         )
-        return tokenPattern.test(message)
-      })
+        const match = tokenPattern.exec(unclaimed)
+        if (!match) continue
+        present.add(c)
+        // Blank the claimed span (same length, so later indices stay valid)
+        // rather than removing it, keeping the `(^|\s)` boundary intact for
+        // whatever sits next to it.
+        unclaimed =
+          unclaimed.slice(0, match.index) +
+          ' '.repeat(match[0].length) +
+          unclaimed.slice(match.index + match[0].length)
+      }
+
+      const filtered = prev.filter((c) => present.has(c))
       return filtered.length === prev.length ? prev : filtered
     })
   }, [message])