Skip to content

docs: add previousAssistantMessages handoff mode to PCI docs#1026

Merged
adhamvapi merged 4 commits intomainfrom
tasker/VAPICS-866-pci-docs-previousassistantmessages
Apr 22, 2026
Merged

docs: add previousAssistantMessages handoff mode to PCI docs#1026
adhamvapi merged 4 commits intomainfrom
tasker/VAPICS-866-pci-docs-previousassistantmessages

Conversation

@adhamvapi
Copy link
Copy Markdown
Contributor

@adhamvapi adhamvapi commented Apr 22, 2026

Summary

  • Corrects the PCI recommendation for userAndAssistantMessages context type in the handoff context configuration table
  • Previously described as a "good alternative" for PCI flows, which is incorrect -- spoken sensitive data (e.g., card numbers read aloud) appears in user messages and would be forwarded
  • Updated to clearly mark it as not recommended for PCI flows
  • Reordered table rows to list the two safe options (previousAssistantMessages, none) first
  • Renamed column header from "When to use" to "PCI Recommendation" for clarity

Test plan

  • Verify the table in fern/security-and-privacy/PCI.mdx renders correctly
  • Confirm previousAssistantMessages is labeled as Recommended
  • Confirm none is labeled as Safe
  • Confirm userAndAssistantMessages is labeled as Not recommended for PCI flows with explanation

Linear: VAPICS-866

Generated with Claude Code

Add a new "Securing Handoffs with Sensitive Data" section to the PCI
compliance documentation explaining the security concern with forwarding
full conversation context (including sensitive tool call data) during
assistant handoffs, the server-side fix Vapi deployed, and the
customer-side steps to configure contextEngineeringPlan appropriately.

Also document the previousAssistantMessages context engineering plan type
in the handoff tool documentation, which was the only type not yet
covered there.

Update the existing Payment Collection Squad example to use
previousAssistantMessages instead of none for a more practical default.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove incident-response framing ("What happened", "What we've fixed",
"What you need to do") from PCI.mdx and present previousAssistantMessages
as a standard feature for controlling handoff context in sensitive flows.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@github-actions
Copy link
Copy Markdown
Contributor

@github-actions
Copy link
Copy Markdown
Contributor

Comment thread fern/security-and-privacy/PCI.mdx Outdated
…type

The table previously described userAndAssistantMessages as a "good
alternative" for PCI flows. This is incorrect — if a user speaks
sensitive data (e.g., card numbers) aloud, those appear in user messages
and would be forwarded to the next assistant. Updated the table to mark
it as not recommended for PCI flows, reordered rows to list safe options
first, and renamed the column header from "When to use" to
"PCI Recommendation" for clarity.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@github-actions
Copy link
Copy Markdown
Contributor

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@adhamvapi adhamvapi enabled auto-merge (squash) April 22, 2026 18:05
@github-actions
Copy link
Copy Markdown
Contributor

@adhamvapi adhamvapi merged commit 0ad7053 into main Apr 22, 2026
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants