Skip to content

chore: update changelog for 2.10.0 #968

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
b4s36t4 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore: update changelog for 2.10.0 #968

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 40 additions & 2 deletions changelog/enterprise.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,51 @@
---
title: "Enterprise Gateway"
sidebarTitle: "Enterprise Gateway [2.9.0]"
sidebarTitle: "Enterprise Gateway [2.10.0]"
rss: true
---

<Card title="Schedule Call" href="https://portkey.sh/demo-21" icon="calendar" horizontal>
Discuss how Portkey's AI Gateway can enhance your organization's AI infrastructure
</Card>

<Update label="2.10.0" description="2026-05-28">

## v2.10.0
---

### New Plugins and Deployment Support

- **Cato plugin**: Added support for Cato in plugin workflows.
- **Claude Platform on AWS**: Added support for Claude Platform on AWS deployments.
- **Allowed request types**: Extended allowed-request-type plugin coverage to proxy routes and allowed OpenTelemetry traffic in the allow list.
- **AIDR guardrails**: Request metadata is now forwarded to the AIDR guard endpoint for richer guardrail context.

### Observability and Metrics

- Prometheus metrics can now export config name and API key name as optional extra labels.
- Logs now store the `tokens` object for more complete token usage details.

### Provider, Pricing, and Routing Updates

- Added multi-dimensional pricing support.
- Vertex AI now supports the `zai-org` model provider and applies the service-tier header where applicable.
- Improved Cloudflare Workers AI compatibility for the newer OpenAI-compatible response format.
- Fixed model extraction from `@slug/model` in request bodies for azure-openai.
- Fixed Together AI streamed usage parsing when usage appears in stream chunks.

### Security, Auth, and Network Reliability

- Updated dependencies to patch security vulnerabilities.
- Fixed Azure Managed Identity Redis token refresh.

### Fixes and Improvements

- Re-applies `default_params`, `override_params`, and `drop_params` after Messages/Responses request transforms so config behavior stays consistent across transformed requests.
- Improved rate-limit error messages.
- Fixed Anthropic-style streaming tool-use handling so `tool_use` blocks are not closed solely on `finish_reason`.

</Update>

<Update label="2.9.0" description="2026-05-21">

## v2.9.0
Expand Down Expand Up @@ -2695,4 +2733,4 @@ We are redacting this release and will be releasing a patch with out Workspace B

### Fixes & Enhancements:
- Exclude files, batches, threads, etc. (all passthrough) from ```llm_cost_sum``` prometheus metric to avoid unnecessary labels.
</Update>
</Update>