framework/v1.8.1

maximhq/bifrostframework/v1.8.1Oct 6, 2026by akshaydeo

Upgrading?

AI Summary

Framework v1.8.1 adds memoization for model output tokens, enforces strict issuer URL requirements for OAuth configurations, and improves tracking of inference authentication settings.

Key Highlights

  • Memoized retrieval of model max output tokens prevents full-sheet scans
  • Mandatory issuer_url configuration for MCP OAuth modes
  • Explicit tracking of enforce_auth_on_inference setting
  • Enhanced redaction of secrets in client config responses

Breaking Changes

  • oauth2_server_config.issuer_url is now required for MCP OAuth auth modes

New Features

  • Memoized ModelCatalog.GetMaxOutputTokens

Full Release Notes

## Framework Release v1.8.1

- feat: ModelCatalog.GetMaxOutputTokens returns a model's datasheet max_output_tokens, memoized per catalog generation (misses included) so a model missing from the sheet no longer pays a full-sheet scan per call
- fix: oauth2_server_config.issuer_url is required when mcp_server_auth_mode is oauth or both; the issuer is never derived from the request Host header (#7863)
  <Warning>
  Set oauth2_server_config.issuer_url before upgrading any deployment with MCP OAuth discovery enabled, or config load fails.
  </Warning>
- fix: track whether enforce_auth_on_inference was set explicitly so creating the first admin can default inference auth on (#7864)
- fix: redact secret-bearing alias and Bedrock endpoint values in client config responses (#7858)
- chore: upgraded core to v1.11.2

### Installation

```bash
go get github.com/maximhq/bifrost/framework@v1.8.1
```

---
_This release was automatically created and uses core version: `v1.11.2`_

Related Repositories