Product updates, new features, improvements, and fixes as we ship them. Subscribe via RSS to stay updated.
This changelog reflects the current mainline release. Availability in your environment depends on your organization's deployment cadence.
Swept now accepts governance events from external applications through a dedicated ingress endpoint
using the versioned swept.governance-event/v1 schema. Teams can route AI activity from tools outside
the Workbench into the same governance record, creating a unified audit trail across their entire AI
stack. The versioned schema keeps integrations stable as the event format evolves.
Administrators can now register additional Model Context Protocol (MCP) tool servers in the Open WebUI environment, extending the toolset available to chat beyond the built-in document generation server. Configuration validates each entry for blank IDs, duplicates, and reserved names, so mistakes are caught before deployment. Teams building custom tooling can wire it directly into the governed chat environment without forking the platform configuration.
Developers can now generate their own Claude Code API keys directly from Workbench using an emailed one-time code. Each key is scoped to the individual developer, so usage is isolated and auditable per person without requiring an admin to issue credentials. The Usage meter uses the same sign-in flow, giving developers a self-service view of their own AI consumption.
Developers on your plan can now request a personal Claude Code API key directly from Workbench. A one-time code arrives by email, and the key is minted on confirmation with no admin ticket required. Keys are scoped per developer, so revocation and usage attribution stay at the individual level rather than a shared credential.
Two new controls give enterprise teams finer authority over who can reach Swept admin interfaces. An opt-in email allowlist lets you restrict Cloud Lock sign-in to a defined set of addresses, with the Settings panel now gated to admins only. Identity-path access control adds enforcement at the authentication layer, limiting which sign-in routes are permitted for each role.
Workbench now supports company-scoped public HTML pages. Organizations can publish content tied to their account and share it via a stable public URL, without relying on external hosting or a separate content delivery setup. Access and ownership stay inside your Swept environment.
The Workbench usage report now captures activity from Claude Code working sessions, including parallel mode, and attributes it correctly alongside chat and API usage. Organizations get a more complete picture of AI consumption across developer tooling, not just the browser interface. The session sample in the report's About section also documents the counting method so the numbers are auditable.
When a user already holds a Swept grant through their identity provider group, company admins can now assign that same grant to them directly. This makes permission management more flexible for individual overrides without waiting for group membership changes to propagate. A clarifying banner explains the source of an existing grant so admins always know how access was granted.
Long numeric values in PDF usage reports now scale down to fit their cells rather than wrapping across lines. Hero bar charts draw bars before placing their labels, so labels on narrow bars no longer overlap neighboring bars. Both fixes improve readability when usage reports are shared with finance teams or exported for leadership review.
Spend data for requests routed through Google Vertex AI now uses the correct per-model pricing instead of falling back to a generic default. The spend log endpoint was also fixed to return complete data in production, so the Usage page and monthly reports reflect accurate totals across all models and users.