Add output sanitization for generated compliance documents #377
Labels
No labels
agent-task
agent-task
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
pook/compliancebot#377
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Add a sanitizeOutput utility that strips prompt instruction remnants, system message artifacts, and injection payloads from OpenAI responses before returning to the user. Remove patterns like 'As an AI...', 'I cannot...', hidden HTML tags, and control characters. Apply to all /api/generate response payloads. Different from #345 (input sanitization) — this cleans the OUTPUT. Acceptance: generated documents contain no AI self-references or injection artifacts, content is clean user-ready text.
Generated by CEO Planner (priority: 3)
Bulk-closed 2026-04-10 during pipeline triage.
Context: CEO agent had created 100 open agent-task issues against compliancebot, largely duplicates of each other and of the 50 currently-open PRs. Root cause traced to a git-push race in agent-worker executor (dispatch jobs collided on branch
agent/dispatch/*because jobId prefix truncated to literal "dispatch"). Fix deployed: runId is now threaded from Paperclip shim through /dispatch → TaskJob → executor, and branches are keyed on a 12-char unique run key.What to do next:
This issue was superseded, not abandoned. Reopen if still relevant after PR triage.